chore: bump version to v5.4.0a1

.github/pull_request_template.md

@@ -19,4 +19,3 @@
 - [ ] _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)_

SECURITY.md

@@ -1,14 +0,0 @@
-# Security Policy
-
-## Supported Versions
-
-Only the latest version of Invoke will receive security updates. 
-We do not currently maintain multiple versions of the application with updates.
-
-## Reporting a Vulnerability
-
-To report a vulnerability, contact the Invoke team directly at security@invoke.ai
-
-At this time, we do not maintain a formal bug bounty program. 
-
-You can also share identified security issues with our team on huntr.com

docs/contributing/MODEL_MANAGER.md

@@ -1364,6 +1364,7 @@ the in-memory loaded model:
 |----------------|-----------------|------------------|
 | `config`       | AnyModelConfig         | A copy of the model's configuration record for retrieving base type, etc. |
 | `model`        | AnyModel               | The instantiated model (details below) |
+| `locker`       | ModelLockerBase        | A context manager that mediates the movement of the model into VRAM |
 
 ### get_model_by_key(key, [submodel]) -> LoadedModel
 

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](../LOCAL_DEVELOPMENT.md). Feel free to skip this step if you already have tooling you're comfortable with.
+- [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] 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/index.md

@@ -38,7 +38,7 @@ This project is a combined effort of dedicated people from across the world. [C
 
 ## Code of Conduct
 
-The InvokeAI community is a welcoming place, and we want your help in maintaining that. Please review our [Code of Conduct](https://github.com/invoke-ai/InvokeAI/blob/main/docs/CODE_OF_CONDUCT.md) to learn more - it's essential to maintaining a respectful and inclusive environment.
+The InvokeAI community is a welcoming place, and we want your help in maintaining that. Please review our [Code of Conduct](https://github.com/invoke-ai/InvokeAI/blob/main/CODE_OF_CONDUCT.md) to learn more - it's essential to maintaining a respectful and inclusive environment.
 
 By making a contribution to this project, you certify that:
 

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 convert the
+button in the upper right of your browser window. This will conver 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`, `blas`, and required dependencies:
+2. Install `opencv` and `blas`:
 
    ```sh
-   sudo pacman -S opencv blas fmt glew vtk hdf5
+   sudo pacman -S opencv blas
    ```
 
    or for CUDA support
 
    ```sh
-   sudo pacman -S opencv-cuda blas fmt glew vtk hdf5
+   sudo pacman -S opencv-cuda blas
    ```
 
 3. Fix the naming of the `opencv` package configuration file:

docs/nodes/defaultNodes.md

@@ -99,6 +99,7 @@ their descriptions.
 | Scale Latents                                                 | Scales latents by a given factor.                                                                                                                    |
 | Segment Anything Processor                                    | Applies segment anything processing to image                                                                                                         |
 | Show Image                                                    | Displays a provided image, and passes it forward in the pipeline.                                                                                    |
+| Step Param Easing                                             | Experimental per-step parameter easing for denoising steps                                                                                           |
 | String Primitive Collection                                   | A collection of string primitive values                                                                                                              |
 | String Primitive                                              | A string primitive value                                                                                                                             |
 | Subtract Integers                                             | Subtracts two numbers                                                                                                                                |

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/installation/requirements/[/] to ensure your system meets the minimum requirements.",
+                        "See [deep_sky_blue1]https://invoke-ai.github.io/InvokeAI/#system[/] 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

@@ -40,8 +40,6 @@ 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

@@ -1,7 +1,6 @@
 # Copyright (c) 2023 Lincoln D. Stein
 """FastAPI route for model configuration records."""
 
-import contextlib
 import io
 import pathlib
 import shutil
@@ -11,7 +10,6 @@ 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
@@ -29,7 +27,6 @@ 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,
@@ -37,7 +34,7 @@ from invokeai.backend.model_manager.config import (
     ModelFormat,
     ModelType,
 )
-from invokeai.backend.model_manager.load.model_cache.cache_stats import CacheStats
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import CacheStats
 from invokeai.backend.model_manager.metadata.fetch.huggingface import HuggingFaceMetadataFetch
 from invokeai.backend.model_manager.metadata.metadata_base import ModelMetadataWithFiles, UnknownMetadataException
 from invokeai.backend.model_manager.search import ModelSearch
@@ -926,51 +923,3 @@ 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/api/routers/session_queue.py

@@ -110,7 +110,7 @@ async def cancel_by_batch_ids(
 @session_queue_router.put(
     "/{queue_id}/cancel_by_destination",
     operation_id="cancel_by_destination",
-    responses={200: {"model": CancelByDestinationResult}},
+    responses={200: {"model": CancelByBatchIDsResult}},
 )
 async def cancel_by_destination(
     queue_id: str = Path(description="The queue id to perform this operation on"),

invokeai/app/invocations/baseinvocation.py

@@ -4,7 +4,6 @@ from __future__ import annotations
 
 import inspect
 import re
-import sys
 import warnings
 from abc import ABC, abstractmethod
 from enum import Enum
@@ -63,7 +62,6 @@ class Classification(str, Enum, metaclass=MetaEnum):
     - `Prototype`: The invocation is not yet stable and may be removed from the application at any time. Workflows built around this invocation may break, and we are *not* committed to supporting this invocation.
     - `Deprecated`: The invocation is deprecated and may be removed in a future version.
     - `Internal`: The invocation is not intended for use by end-users. It may be changed or removed at any time, but is exposed for users to play with.
-    - `Special`: The invocation is a special case and does not fit into any of the other classifications.
     """
 
     Stable = "stable"
@@ -71,7 +69,6 @@ class Classification(str, Enum, metaclass=MetaEnum):
     Prototype = "prototype"
     Deprecated = "deprecated"
     Internal = "internal"
-    Special = "special"
 
 
 class UIConfigBase(BaseModel):
@@ -195,19 +192,12 @@ 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.get_invocations())], Field(discriminator="type")]
+                "AnyInvocation", Annotated[Union[tuple(cls._invocation_classes)], 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."""
@@ -489,26 +479,6 @@ 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/blend_latents.py

@@ -1,120 +1,98 @@
-from typing import Optional, Union
+from typing import Any, Union
 
 import numpy as np
+import numpy.typing as npt
 import torch
-import torchvision.transforms as T
-from PIL import Image
-from torchvision.transforms.functional import resize as tv_resize
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation, invocation
-from invokeai.app.invocations.fields import FieldDescriptions, ImageField, Input, InputField, LatentsField
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, LatentsField
 from invokeai.app.invocations.primitives import LatentsOutput
 from invokeai.app.services.shared.invocation_context import InvocationContext
-from invokeai.backend.stable_diffusion.diffusers_pipeline import image_resized_to_grid_as_tensor
 from invokeai.backend.util.devices import TorchDevice
 
 
-def slerp(
-    t: Union[float, np.ndarray],
-    v0: Union[torch.Tensor, np.ndarray],
-    v1: Union[torch.Tensor, np.ndarray],
-    device: torch.device,
-    DOT_THRESHOLD: float = 0.9995,
-):
-    """
-    Spherical linear interpolation
-    Args:
-        t (float/np.ndarray): Float value between 0.0 and 1.0
-        v0 (np.ndarray): Starting vector
-        v1 (np.ndarray): Final vector
-        DOT_THRESHOLD (float): Threshold for considering the two vectors as
-                            colineal. Not recommended to alter this.
-    Returns:
-        v2 (np.ndarray): Interpolation vector between v0 and v1
-    """
-    inputs_are_torch = False
-    if not isinstance(v0, np.ndarray):
-        inputs_are_torch = True
-        v0 = v0.detach().cpu().numpy()
-    if not isinstance(v1, np.ndarray):
-        inputs_are_torch = True
-        v1 = v1.detach().cpu().numpy()
-
-    dot = np.sum(v0 * v1 / (np.linalg.norm(v0) * np.linalg.norm(v1)))
-    if np.abs(dot) > DOT_THRESHOLD:
-        v2 = (1 - t) * v0 + t * v1
-    else:
-        theta_0 = np.arccos(dot)
-        sin_theta_0 = np.sin(theta_0)
-        theta_t = theta_0 * t
-        sin_theta_t = np.sin(theta_t)
-        s0 = np.sin(theta_0 - theta_t) / sin_theta_0
-        s1 = sin_theta_t / sin_theta_0
-        v2 = s0 * v0 + s1 * v1
-
-    if inputs_are_torch:
-        v2 = torch.from_numpy(v2).to(device)
-
-    return v2
-
-
 @invocation(
     "lblend",
     title="Blend Latents",
-    tags=["latents", "blend", "mask"],
+    tags=["latents", "blend"],
     category="latents",
-    version="1.1.0",
+    version="1.0.3",
 )
 class BlendLatentsInvocation(BaseInvocation):
-    """Blend two latents using a given alpha. If a mask is provided, the second latents will be masked before blending.
-    Latents must have same size. Masking functionality added by @dwringer."""
+    """Blend two latents using a given alpha. Latents must have same size."""
 
-    latents_a: LatentsField = InputField(description=FieldDescriptions.latents, input=Input.Connection)
-    latents_b: LatentsField = InputField(description=FieldDescriptions.latents, input=Input.Connection)
-    mask: Optional[ImageField] = InputField(default=None, description="Mask for blending in latents B")
-    alpha: float = InputField(ge=0, default=0.5, description=FieldDescriptions.blend_alpha)
-
-    def prep_mask_tensor(self, mask_image: Image.Image) -> torch.Tensor:
-        if mask_image.mode != "L":
-            mask_image = mask_image.convert("L")
-        mask_tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
-        if mask_tensor.dim() == 3:
-            mask_tensor = mask_tensor.unsqueeze(0)
-        return mask_tensor
-
-    def replace_tensor_from_masked_tensor(
-        self, tensor: torch.Tensor, other_tensor: torch.Tensor, mask_tensor: torch.Tensor
-    ):
-        output = tensor.clone()
-        mask_tensor = mask_tensor.expand(output.shape)
-        if output.dtype != torch.float16:
-            output = torch.add(output, mask_tensor * torch.sub(other_tensor, tensor))
-        else:
-            output = torch.add(output, mask_tensor.half() * torch.sub(other_tensor, tensor))
-        return output
+    latents_a: LatentsField = InputField(
+        description=FieldDescriptions.latents,
+        input=Input.Connection,
+    )
+    latents_b: LatentsField = InputField(
+        description=FieldDescriptions.latents,
+        input=Input.Connection,
+    )
+    alpha: float = InputField(default=0.5, description=FieldDescriptions.blend_alpha)
 
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         latents_a = context.tensors.load(self.latents_a.latents_name)
         latents_b = context.tensors.load(self.latents_b.latents_name)
-        if self.mask is None:
-            mask_tensor = torch.zeros(latents_a.shape[-2:])
-        else:
-            mask_tensor = self.prep_mask_tensor(context.images.get_pil(self.mask.image_name))
-            mask_tensor = tv_resize(mask_tensor, latents_a.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
-
-        latents_b = self.replace_tensor_from_masked_tensor(latents_b, latents_a, mask_tensor)
 
         if latents_a.shape != latents_b.shape:
-            raise ValueError("Latents to blend must be the same size.")
+            raise Exception("Latents to blend must be the same size.")
 
         device = TorchDevice.choose_torch_device()
 
+        def slerp(
+            t: Union[float, npt.NDArray[Any]],  # FIXME: maybe use np.float32 here?
+            v0: Union[torch.Tensor, npt.NDArray[Any]],
+            v1: Union[torch.Tensor, npt.NDArray[Any]],
+            DOT_THRESHOLD: float = 0.9995,
+        ) -> Union[torch.Tensor, npt.NDArray[Any]]:
+            """
+            Spherical linear interpolation
+            Args:
+                t (float/np.ndarray): Float value between 0.0 and 1.0
+                v0 (np.ndarray): Starting vector
+                v1 (np.ndarray): Final vector
+                DOT_THRESHOLD (float): Threshold for considering the two vectors as
+                                    colineal. Not recommended to alter this.
+            Returns:
+                v2 (np.ndarray): Interpolation vector between v0 and v1
+            """
+            inputs_are_torch = False
+            if not isinstance(v0, np.ndarray):
+                inputs_are_torch = True
+                v0 = v0.detach().cpu().numpy()
+            if not isinstance(v1, np.ndarray):
+                inputs_are_torch = True
+                v1 = v1.detach().cpu().numpy()
+
+            dot = np.sum(v0 * v1 / (np.linalg.norm(v0) * np.linalg.norm(v1)))
+            if np.abs(dot) > DOT_THRESHOLD:
+                v2 = (1 - t) * v0 + t * v1
+            else:
+                theta_0 = np.arccos(dot)
+                sin_theta_0 = np.sin(theta_0)
+                theta_t = theta_0 * t
+                sin_theta_t = np.sin(theta_t)
+                s0 = np.sin(theta_0 - theta_t) / sin_theta_0
+                s1 = sin_theta_t / sin_theta_0
+                v2 = s0 * v0 + s1 * v1
+
+            if inputs_are_torch:
+                v2_torch: torch.Tensor = torch.from_numpy(v2).to(device)
+                return v2_torch
+            else:
+                assert isinstance(v2, np.ndarray)
+                return v2
+
         # blend
-        blended_latents = slerp(self.alpha, latents_a, latents_b, device)
+        bl = slerp(self.alpha, latents_a, latents_b)
+        assert isinstance(bl, torch.Tensor)
+        blended_latents: torch.Tensor = bl  # for type checking convenience
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         blended_latents = blended_latents.to("cpu")
-        torch.cuda.empty_cache()
+
+        TorchDevice.empty_cache()
 
         name = context.tensors.save(tensor=blended_latents)
-        return LatentsOutput.build(latents_name=name, latents=blended_latents)
+        return LatentsOutput.build(latents_name=name, latents=blended_latents, seed=self.latents_a.seed)

invokeai/app/invocations/compel.py

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

@@ -65,7 +65,6 @@ 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

@@ -131,7 +131,6 @@ 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

@@ -622,7 +622,7 @@ 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, mode="RGB")
+            image = context.images.get_pil(t2i_adapter_field.image.image_name)
 
             # 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:
@@ -640,39 +640,29 @@ 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=control_width_resize,
-                    height=control_height_resize,
+                    width=t2i_input_width,
+                    height=t2i_input_height,
                     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:

invokeai/app/invocations/fields.py

@@ -41,7 +41,6 @@ class UIType(str, Enum, metaclass=MetaEnum):
     # region Model Field Types
     MainModel = "MainModelField"
     FluxMainModel = "FluxMainModelField"
-    SD3MainModel = "SD3MainModelField"
     SDXLMainModel = "SDXLMainModelField"
     SDXLRefinerModel = "SDXLRefinerModelField"
     ONNXModel = "ONNXModelField"
@@ -53,8 +52,6 @@ class UIType(str, Enum, metaclass=MetaEnum):
     T2IAdapterModel = "T2IAdapterModelField"
     T5EncoderModel = "T5EncoderModelField"
     CLIPEmbedModel = "CLIPEmbedModelField"
-    CLIPLEmbedModel = "CLIPLEmbedModelField"
-    CLIPGEmbedModel = "CLIPGEmbedModelField"
     SpandrelImageToImageModel = "SpandrelImageToImageModelField"
     # endregion
 
@@ -134,10 +131,8 @@ 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"
     vae = "VAE"
     cond = "Conditioning tensor"
     controlnet_model = "ControlNet model to load"
@@ -145,7 +140,6 @@ class FieldDescriptions:
     lora_model = "LoRA model to load"
     main_model = "Main model (UNet, VAE, CLIP) to load"
     flux_model = "Flux model (Transformer) to load"
-    sd3_model = "SD3 model (MMDiTX) to load"
     sdxl_main_model = "SDXL Main model (UNet, VAE, CLIP1, CLIP2) to load"
     sdxl_refiner_model = "SDXL Refiner Main Modde (UNet, VAE, CLIP2) to load"
     onnx_main_model = "ONNX Main model (UNet, VAE, CLIP) to load"
@@ -250,17 +244,6 @@ class FluxConditioningField(BaseModel):
     """A conditioning tensor primitive value"""
 
     conditioning_name: str = Field(description="The name of conditioning tensor")
-    mask: Optional[TensorField] = Field(
-        default=None,
-        description="The mask associated with this conditioning tensor. Excluded regions should be set to False, "
-        "included regions should be set to True.",
-    )
-
-
-class SD3ConditioningField(BaseModel):
-    """A conditioning tensor primitive value"""
-
-    conditioning_name: str = Field(description="The name of conditioning tensor")
 
 
 class ConditioningField(BaseModel):

invokeai/app/invocations/flux_denoise.py

@@ -30,7 +30,6 @@ from invokeai.backend.flux.controlnet.xlabs_controlnet_flux import XLabsControlN
 from invokeai.backend.flux.denoise import denoise
 from invokeai.backend.flux.extensions.inpaint_extension import InpaintExtension
 from invokeai.backend.flux.extensions.instantx_controlnet_extension import InstantXControlNetExtension
-from invokeai.backend.flux.extensions.regional_prompting_extension import RegionalPromptingExtension
 from invokeai.backend.flux.extensions.xlabs_controlnet_extension import XLabsControlNetExtension
 from invokeai.backend.flux.extensions.xlabs_ip_adapter_extension import XLabsIPAdapterExtension
 from invokeai.backend.flux.ip_adapter.xlabs_ip_adapter_flux import XlabsIpAdapterFlux
@@ -43,7 +42,6 @@ from invokeai.backend.flux.sampling_utils import (
     pack,
     unpack,
 )
-from invokeai.backend.flux.text_conditioning import FluxTextConditioning
 from invokeai.backend.lora.conversions.flux_lora_constants import FLUX_LORA_TRANSFORMER_PREFIX
 from invokeai.backend.lora.lora_model_raw import LoRAModelRaw
 from invokeai.backend.lora.lora_patcher import LoRAPatcher
@@ -58,7 +56,7 @@ from invokeai.backend.util.devices import TorchDevice
     title="FLUX Denoise",
     tags=["image", "flux"],
     category="image",
-    version="3.2.2",
+    version="3.2.0",
     classification=Classification.Prototype,
 )
 class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
@@ -83,16 +81,15 @@ 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,
         title="Transformer",
     )
-    positive_text_conditioning: FluxConditioningField | list[FluxConditioningField] = InputField(
+    positive_text_conditioning: FluxConditioningField = InputField(
         description=FieldDescriptions.positive_cond, input=Input.Connection
     )
-    negative_text_conditioning: FluxConditioningField | list[FluxConditioningField] | None = InputField(
+    negative_text_conditioning: FluxConditioningField | None = InputField(
         default=None,
         description="Negative conditioning tensor. Can be None if cfg_scale is 1.0.",
         input=Input.Connection,
@@ -141,12 +138,36 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         name = context.tensors.save(tensor=latents)
         return LatentsOutput.build(latents_name=name, latents=latents, seed=None)
 
+    def _load_text_conditioning(
+        self, context: InvocationContext, conditioning_name: str, dtype: torch.dtype
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        # Load the conditioning data.
+        cond_data = context.conditioning.load(conditioning_name)
+        assert len(cond_data.conditionings) == 1
+        flux_conditioning = cond_data.conditionings[0]
+        assert isinstance(flux_conditioning, FLUXConditioningInfo)
+        flux_conditioning = flux_conditioning.to(dtype=dtype)
+        t5_embeddings = flux_conditioning.t5_embeds
+        clip_embeddings = flux_conditioning.clip_embeds
+        return t5_embeddings, clip_embeddings
+
     def _run_diffusion(
         self,
         context: InvocationContext,
     ):
         inference_dtype = torch.bfloat16
 
+        # Load the conditioning data.
+        pos_t5_embeddings, pos_clip_embeddings = self._load_text_conditioning(
+            context, self.positive_text_conditioning.conditioning_name, inference_dtype
+        )
+        neg_t5_embeddings: torch.Tensor | None = None
+        neg_clip_embeddings: torch.Tensor | None = None
+        if self.negative_text_conditioning is not None:
+            neg_t5_embeddings, neg_clip_embeddings = self._load_text_conditioning(
+                context, self.negative_text_conditioning.conditioning_name, inference_dtype
+            )
+
         # Load the input latents, if provided.
         init_latents = context.tensors.load(self.latents.latents_name) if self.latents else None
         if init_latents is not None:
@@ -161,45 +182,15 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
             dtype=inference_dtype,
             seed=self.seed,
         )
-        b, _c, latent_h, latent_w = noise.shape
-        packed_h = latent_h // 2
-        packed_w = latent_w // 2
-
-        # Load the conditioning data.
-        pos_text_conditionings = self._load_text_conditioning(
-            context=context,
-            cond_field=self.positive_text_conditioning,
-            packed_height=packed_h,
-            packed_width=packed_w,
-            dtype=inference_dtype,
-            device=TorchDevice.choose_torch_device(),
-        )
-        neg_text_conditionings: list[FluxTextConditioning] | None = None
-        if self.negative_text_conditioning is not None:
-            neg_text_conditionings = self._load_text_conditioning(
-                context=context,
-                cond_field=self.negative_text_conditioning,
-                packed_height=packed_h,
-                packed_width=packed_w,
-                dtype=inference_dtype,
-                device=TorchDevice.choose_torch_device(),
-            )
-        pos_regional_prompting_extension = RegionalPromptingExtension.from_text_conditioning(
-            pos_text_conditionings, img_seq_len=packed_h * packed_w
-        )
-        neg_regional_prompting_extension = (
-            RegionalPromptingExtension.from_text_conditioning(neg_text_conditionings, img_seq_len=packed_h * packed_w)
-            if neg_text_conditionings
-            else None
-        )
 
         transformer_info = context.models.load(self.transformer.transformer)
         is_schnell = "schnell" in transformer_info.config.config_path
 
         # Calculate the timestep schedule.
+        image_seq_len = noise.shape[-1] * noise.shape[-2] // 4
         timesteps = get_schedule(
             num_steps=self.num_steps,
-            image_seq_len=packed_h * packed_w,
+            image_seq_len=image_seq_len,
             shift=not is_schnell,
         )
 
@@ -216,12 +207,9 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
                     "to be poor. Consider using a FLUX dev model instead."
                 )
 
-            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
+            # 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:
             # 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:
@@ -236,17 +224,28 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
 
         inpaint_mask = self._prep_inpaint_mask(context, x)
 
+        b, _c, latent_h, latent_w = x.shape
         img_ids = generate_img_ids(h=latent_h, w=latent_w, batch_size=b, device=x.device, dtype=x.dtype)
 
+        pos_bs, pos_t5_seq_len, _ = pos_t5_embeddings.shape
+        pos_txt_ids = torch.zeros(
+            pos_bs, pos_t5_seq_len, 3, dtype=inference_dtype, device=TorchDevice.choose_torch_device()
+        )
+        neg_txt_ids: torch.Tensor | None = None
+        if neg_t5_embeddings is not None:
+            neg_bs, neg_t5_seq_len, _ = neg_t5_embeddings.shape
+            neg_txt_ids = torch.zeros(
+                neg_bs, neg_t5_seq_len, 3, dtype=inference_dtype, device=TorchDevice.choose_torch_device()
+            )
+
         # Pack all latent tensors.
         init_latents = pack(init_latents) if init_latents is not None else None
         inpaint_mask = pack(inpaint_mask) if inpaint_mask is not None else None
         noise = pack(noise)
         x = pack(x)
 
-        # Now that we have 'packed' the latent tensors, verify that we calculated the image_seq_len, packed_h, and
-        # packed_w correctly.
-        assert packed_h * packed_w == x.shape[1]
+        # Now that we have 'packed' the latent tensors, verify that we calculated the image_seq_len correctly.
+        assert image_seq_len == x.shape[1]
 
         # Prepare inpaint extension.
         inpaint_extension: InpaintExtension | None = None
@@ -335,8 +334,12 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
                 model=transformer,
                 img=x,
                 img_ids=img_ids,
-                pos_regional_prompting_extension=pos_regional_prompting_extension,
-                neg_regional_prompting_extension=neg_regional_prompting_extension,
+                txt=pos_t5_embeddings,
+                txt_ids=pos_txt_ids,
+                vec=pos_clip_embeddings,
+                neg_txt=neg_t5_embeddings,
+                neg_txt_ids=neg_txt_ids,
+                neg_vec=neg_clip_embeddings,
                 timesteps=timesteps,
                 step_callback=self._build_step_callback(context),
                 guidance=self.guidance,
@@ -350,43 +353,6 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         x = unpack(x.float(), self.height, self.width)
         return x
 
-    def _load_text_conditioning(
-        self,
-        context: InvocationContext,
-        cond_field: FluxConditioningField | list[FluxConditioningField],
-        packed_height: int,
-        packed_width: int,
-        dtype: torch.dtype,
-        device: torch.device,
-    ) -> list[FluxTextConditioning]:
-        """Load text conditioning data from a FluxConditioningField or a list of FluxConditioningFields."""
-        # Normalize to a list of FluxConditioningFields.
-        cond_list = [cond_field] if isinstance(cond_field, FluxConditioningField) else cond_field
-
-        text_conditionings: list[FluxTextConditioning] = []
-        for cond_field in cond_list:
-            # Load the text embeddings.
-            cond_data = context.conditioning.load(cond_field.conditioning_name)
-            assert len(cond_data.conditionings) == 1
-            flux_conditioning = cond_data.conditionings[0]
-            assert isinstance(flux_conditioning, FLUXConditioningInfo)
-            flux_conditioning = flux_conditioning.to(dtype=dtype, device=device)
-            t5_embeddings = flux_conditioning.t5_embeds
-            clip_embeddings = flux_conditioning.clip_embeds
-
-            # Load the mask, if provided.
-            mask: Optional[torch.Tensor] = None
-            if cond_field.mask is not None:
-                mask = context.tensors.load(cond_field.mask.tensor_name)
-                mask = mask.to(device=device)
-                mask = RegionalPromptingExtension.preprocess_regional_prompt_mask(
-                    mask, packed_height, packed_width, dtype, device
-                )
-
-            text_conditionings.append(FluxTextConditioning(t5_embeddings, clip_embeddings, mask))
-
-        return text_conditionings
-
     @classmethod
     def prep_cfg_scale(
         cls, cfg_scale: float | list[float], timesteps: list[float], cfg_scale_start_step: int, cfg_scale_end_step: int

invokeai/app/invocations/flux_model_loader.py

@@ -1,89 +0,0 @@
-from typing import Literal
-
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    Classification,
-    invocation,
-    invocation_output,
-)
-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.flux.util import max_seq_lengths
-from invokeai.backend.model_manager.config import (
-    CheckpointConfigBase,
-    SubModelType,
-)
-
-
-@invocation_output("flux_model_loader_output")
-class FluxModelLoaderOutput(BaseInvocationOutput):
-    """Flux base model loader output"""
-
-    transformer: TransformerField = OutputField(description=FieldDescriptions.transformer, title="Transformer")
-    clip: CLIPField = OutputField(description=FieldDescriptions.clip, title="CLIP")
-    t5_encoder: T5EncoderField = OutputField(description=FieldDescriptions.t5_encoder, title="T5 Encoder")
-    vae: VAEField = OutputField(description=FieldDescriptions.vae, title="VAE")
-    max_seq_len: Literal[256, 512] = OutputField(
-        description="The max sequence length to used for the T5 encoder. (256 for schnell transformer, 512 for dev transformer)",
-        title="Max Seq Length",
-    )
-
-
-@invocation(
-    "flux_model_loader",
-    title="Flux Main Model",
-    tags=["model", "flux"],
-    category="model",
-    version="1.0.4",
-    classification=Classification.Prototype,
-)
-class FluxModelLoaderInvocation(BaseInvocation):
-    """Loads a flux base model, outputting its submodels."""
-
-    model: ModelIdentifierField = InputField(
-        description=FieldDescriptions.flux_model,
-        ui_type=UIType.FluxMainModel,
-        input=Input.Direct,
-    )
-
-    t5_encoder_model: ModelIdentifierField = InputField(
-        description=FieldDescriptions.t5_encoder, ui_type=UIType.T5EncoderModel, input=Input.Direct, title="T5 Encoder"
-    )
-
-    clip_embed_model: ModelIdentifierField = InputField(
-        description=FieldDescriptions.clip_embed_model,
-        ui_type=UIType.CLIPEmbedModel,
-        input=Input.Direct,
-        title="CLIP Embed",
-    )
-
-    vae_model: ModelIdentifierField = InputField(
-        description=FieldDescriptions.vae_model, ui_type=UIType.FluxVAEModel, title="VAE"
-    )
-
-    def invoke(self, context: InvocationContext) -> FluxModelLoaderOutput:
-        for key in [self.model.key, self.t5_encoder_model.key, self.clip_embed_model.key, self.vae_model.key]:
-            if not context.models.exists(key):
-                raise ValueError(f"Unknown model: {key}")
-
-        transformer = self.model.model_copy(update={"submodel_type": SubModelType.Transformer})
-        vae = self.vae_model.model_copy(update={"submodel_type": SubModelType.VAE})
-
-        tokenizer = self.clip_embed_model.model_copy(update={"submodel_type": SubModelType.Tokenizer})
-        clip_encoder = self.clip_embed_model.model_copy(update={"submodel_type": SubModelType.TextEncoder})
-
-        tokenizer2 = 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(transformer)
-        assert isinstance(transformer_config, CheckpointConfigBase)
-
-        return FluxModelLoaderOutput(
-            transformer=TransformerField(transformer=transformer, loras=[]),
-            clip=CLIPField(tokenizer=tokenizer, text_encoder=clip_encoder, loras=[], skipped_layers=0),
-            t5_encoder=T5EncoderField(tokenizer=tokenizer2, text_encoder=t5_encoder),
-            vae=VAEField(vae=vae),
-            max_seq_len=max_seq_lengths[transformer_config.config_path],
-        )

invokeai/app/invocations/flux_text_encoder.py

@@ -1,18 +1,11 @@
 from contextlib import ExitStack
-from typing import Iterator, Literal, Optional, Tuple
+from typing import Iterator, Literal, Tuple
 
 import torch
 from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5Tokenizer
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, invocation
-from invokeai.app.invocations.fields import (
-    FieldDescriptions,
-    FluxConditioningField,
-    Input,
-    InputField,
-    TensorField,
-    UIComponent,
-)
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField
 from invokeai.app.invocations.model import CLIPField, T5EncoderField
 from invokeai.app.invocations.primitives import FluxConditioningOutput
 from invokeai.app.services.shared.invocation_context import InvocationContext
@@ -29,7 +22,7 @@ from invokeai.backend.stable_diffusion.diffusion.conditioning_data import Condit
     title="FLUX Text Encoding",
     tags=["prompt", "conditioning", "flux"],
     category="conditioning",
-    version="1.1.1",
+    version="1.1.0",
     classification=Classification.Prototype,
 )
 class FluxTextEncoderInvocation(BaseInvocation):
@@ -48,10 +41,7 @@ class FluxTextEncoderInvocation(BaseInvocation):
     t5_max_seq_len: Literal[256, 512] = InputField(
         description="Max sequence length for the T5 encoder. Expected to be 256 for FLUX schnell models and 512 for FLUX dev models."
     )
-    prompt: str = InputField(description="Text prompt to encode.", ui_component=UIComponent.Textarea)
-    mask: Optional[TensorField] = InputField(
-        default=None, description="A mask defining the region that this conditioning prompt applies to."
-    )
+    prompt: str = InputField(description="Text prompt to encode.")
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> FluxConditioningOutput:
@@ -64,9 +54,7 @@ class FluxTextEncoderInvocation(BaseInvocation):
         )
 
         conditioning_name = context.conditioning.save(conditioning_data)
-        return FluxConditioningOutput(
-            conditioning=FluxConditioningField(conditioning_name=conditioning_name, mask=self.mask)
-        )
+        return FluxConditioningOutput.build(conditioning_name)
 
     def _t5_encode(self, context: InvocationContext) -> torch.Tensor:
         t5_tokenizer_info = context.models.load(self.t5_encoder.tokenizer)
@@ -83,7 +71,6 @@ 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)
@@ -124,7 +111,6 @@ 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

@@ -41,8 +41,7 @@ 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)
-            vae_dtype = next(iter(vae.parameters())).dtype
-            latents = latents.to(device=TorchDevice.choose_torch_device(), dtype=vae_dtype)
+            latents = latents.to(device=TorchDevice.choose_torch_device(), dtype=TorchDevice.choose_torch_dtype())
             img = vae.decode(latents)
 
         img = img.clamp(-1, 1)
@@ -54,7 +53,6 @@ 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

@@ -44,8 +44,9 @@ class FluxVaeEncodeInvocation(BaseInvocation):
         generator = torch.Generator(device=TorchDevice.choose_torch_device()).manual_seed(0)
         with vae_info as vae:
             assert isinstance(vae, AutoEncoder)
-            vae_dtype = next(iter(vae.parameters())).dtype
-            image_tensor = image_tensor.to(device=TorchDevice.choose_torch_device(), dtype=vae_dtype)
+            image_tensor = image_tensor.to(
+                device=TorchDevice.choose_torch_device(), dtype=TorchDevice.choose_torch_dtype()
+            )
             latents = vae.encode(image_tensor, sample=True, generator=generator)
             return latents
 
@@ -59,7 +60,6 @@ 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_panels.py

@@ -1,59 +0,0 @@
-from pydantic import ValidationInfo, field_validator
-
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    Classification,
-    invocation,
-    invocation_output,
-)
-from invokeai.app.invocations.fields import InputField, OutputField
-from invokeai.app.services.shared.invocation_context import InvocationContext
-
-
-@invocation_output("image_panel_coordinate_output")
-class ImagePanelCoordinateOutput(BaseInvocationOutput):
-    x_left: int = OutputField(description="The left x-coordinate of the panel.")
-    y_top: int = OutputField(description="The top y-coordinate of the panel.")
-    width: int = OutputField(description="The width of the panel.")
-    height: int = OutputField(description="The height of the panel.")
-
-
-@invocation(
-    "image_panel_layout",
-    title="Image Panel Layout",
-    tags=["image", "panel", "layout"],
-    category="image",
-    version="1.0.0",
-    classification=Classification.Prototype,
-)
-class ImagePanelLayoutInvocation(BaseInvocation):
-    """Get the coordinates of a single panel in a grid. (If the full image shape cannot be divided evenly into panels,
-    then the grid may not cover the entire image.)
-    """
-
-    width: int = InputField(description="The width of the entire grid.")
-    height: int = InputField(description="The height of the entire grid.")
-    num_cols: int = InputField(ge=1, default=1, description="The number of columns in the grid.")
-    num_rows: int = InputField(ge=1, default=1, description="The number of rows in the grid.")
-    panel_col_idx: int = InputField(ge=0, default=0, description="The column index of the panel to be processed.")
-    panel_row_idx: int = InputField(ge=0, default=0, description="The row index of the panel to be processed.")
-
-    @field_validator("panel_col_idx")
-    def validate_panel_col_idx(cls, v: int, info: ValidationInfo) -> int:
-        if v < 0 or v >= info.data["num_cols"]:
-            raise ValueError(f"panel_col_idx must be between 0 and {info.data['num_cols'] - 1}")
-        return v
-
-    @field_validator("panel_row_idx")
-    def validate_panel_row_idx(cls, v: int, info: ValidationInfo) -> int:
-        if v < 0 or v >= info.data["num_rows"]:
-            raise ValueError(f"panel_row_idx must be between 0 and {info.data['num_rows'] - 1}")
-        return v
-
-    def invoke(self, context: InvocationContext) -> ImagePanelCoordinateOutput:
-        x_left = self.panel_col_idx * (self.width // self.num_cols)
-        y_top = self.panel_row_idx * (self.height // self.num_rows)
-        width = self.width // self.num_cols
-        height = self.height // self.num_rows
-        return ImagePanelCoordinateOutput(x_left=x_left, y_top=y_top, width=width, height=height)

invokeai/app/invocations/image_to_latents.py

@@ -117,7 +117,6 @@ 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

@@ -60,7 +60,6 @@ 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/metadata.py

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

invokeai/app/invocations/model.py

@@ -1,5 +1,5 @@
 import copy
-from typing import List, Optional
+from typing import List, Literal, Optional
 
 from pydantic import BaseModel, Field
 
@@ -13,9 +13,11 @@ from invokeai.app.invocations.baseinvocation import (
 from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.shared.models import FreeUConfig
+from invokeai.backend.flux.util import max_seq_lengths
 from invokeai.backend.model_manager.config import (
     AnyModelConfig,
     BaseModelType,
+    CheckpointConfigBase,
     ModelType,
     SubModelType,
 )
@@ -137,6 +139,78 @@ class ModelIdentifierInvocation(BaseInvocation):
         return ModelIdentifierOutput(model=self.model)
 
 
+@invocation_output("flux_model_loader_output")
+class FluxModelLoaderOutput(BaseInvocationOutput):
+    """Flux base model loader output"""
+
+    transformer: TransformerField = OutputField(description=FieldDescriptions.transformer, title="Transformer")
+    clip: CLIPField = OutputField(description=FieldDescriptions.clip, title="CLIP")
+    t5_encoder: T5EncoderField = OutputField(description=FieldDescriptions.t5_encoder, title="T5 Encoder")
+    vae: VAEField = OutputField(description=FieldDescriptions.vae, title="VAE")
+    max_seq_len: Literal[256, 512] = OutputField(
+        description="The max sequence length to used for the T5 encoder. (256 for schnell transformer, 512 for dev transformer)",
+        title="Max Seq Length",
+    )
+
+
+@invocation(
+    "flux_model_loader",
+    title="Flux Main Model",
+    tags=["model", "flux"],
+    category="model",
+    version="1.0.4",
+    classification=Classification.Prototype,
+)
+class FluxModelLoaderInvocation(BaseInvocation):
+    """Loads a flux base model, outputting its submodels."""
+
+    model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.flux_model,
+        ui_type=UIType.FluxMainModel,
+        input=Input.Direct,
+    )
+
+    t5_encoder_model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.t5_encoder, ui_type=UIType.T5EncoderModel, input=Input.Direct, title="T5 Encoder"
+    )
+
+    clip_embed_model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.clip_embed_model,
+        ui_type=UIType.CLIPEmbedModel,
+        input=Input.Direct,
+        title="CLIP Embed",
+    )
+
+    vae_model: ModelIdentifierField = InputField(
+        description=FieldDescriptions.vae_model, ui_type=UIType.FluxVAEModel, title="VAE"
+    )
+
+    def invoke(self, context: InvocationContext) -> FluxModelLoaderOutput:
+        for key in [self.model.key, self.t5_encoder_model.key, self.clip_embed_model.key, self.vae_model.key]:
+            if not context.models.exists(key):
+                raise ValueError(f"Unknown model: {key}")
+
+        transformer = self.model.model_copy(update={"submodel_type": SubModelType.Transformer})
+        vae = self.vae_model.model_copy(update={"submodel_type": SubModelType.VAE})
+
+        tokenizer = self.clip_embed_model.model_copy(update={"submodel_type": SubModelType.Tokenizer})
+        clip_encoder = self.clip_embed_model.model_copy(update={"submodel_type": SubModelType.TextEncoder})
+
+        tokenizer2 = 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(transformer)
+        assert isinstance(transformer_config, CheckpointConfigBase)
+
+        return FluxModelLoaderOutput(
+            transformer=TransformerField(transformer=transformer, loras=[]),
+            clip=CLIPField(tokenizer=tokenizer, text_encoder=clip_encoder, loras=[], skipped_layers=0),
+            t5_encoder=T5EncoderField(tokenizer=tokenizer2, text_encoder=t5_encoder),
+            vae=VAEField(vae=vae),
+            max_seq_len=max_seq_lengths[transformer_config.config_path],
+        )
+
+
 @invocation(
     "main_model_loader",
     title="Main Model",

invokeai/app/invocations/param_easing.py

@@ -1,4 +1,43 @@
+import io
+from typing import Literal, Optional
+
+import matplotlib.pyplot as plt
 import numpy as np
+import PIL.Image
+from easing_functions import (
+    BackEaseIn,
+    BackEaseInOut,
+    BackEaseOut,
+    BounceEaseIn,
+    BounceEaseInOut,
+    BounceEaseOut,
+    CircularEaseIn,
+    CircularEaseInOut,
+    CircularEaseOut,
+    CubicEaseIn,
+    CubicEaseInOut,
+    CubicEaseOut,
+    ElasticEaseIn,
+    ElasticEaseInOut,
+    ElasticEaseOut,
+    ExponentialEaseIn,
+    ExponentialEaseInOut,
+    ExponentialEaseOut,
+    LinearInOut,
+    QuadEaseIn,
+    QuadEaseInOut,
+    QuadEaseOut,
+    QuarticEaseIn,
+    QuarticEaseInOut,
+    QuarticEaseOut,
+    QuinticEaseIn,
+    QuinticEaseInOut,
+    QuinticEaseOut,
+    SineEaseIn,
+    SineEaseInOut,
+    SineEaseOut,
+)
+from matplotlib.ticker import MaxNLocator
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation, invocation
 from invokeai.app.invocations.fields import InputField
@@ -26,3 +65,191 @@ class FloatLinearRangeInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
         param_list = list(np.linspace(self.start, self.stop, self.steps))
         return FloatCollectionOutput(collection=param_list)
+
+
+EASING_FUNCTIONS_MAP = {
+    "Linear": LinearInOut,
+    "QuadIn": QuadEaseIn,
+    "QuadOut": QuadEaseOut,
+    "QuadInOut": QuadEaseInOut,
+    "CubicIn": CubicEaseIn,
+    "CubicOut": CubicEaseOut,
+    "CubicInOut": CubicEaseInOut,
+    "QuarticIn": QuarticEaseIn,
+    "QuarticOut": QuarticEaseOut,
+    "QuarticInOut": QuarticEaseInOut,
+    "QuinticIn": QuinticEaseIn,
+    "QuinticOut": QuinticEaseOut,
+    "QuinticInOut": QuinticEaseInOut,
+    "SineIn": SineEaseIn,
+    "SineOut": SineEaseOut,
+    "SineInOut": SineEaseInOut,
+    "CircularIn": CircularEaseIn,
+    "CircularOut": CircularEaseOut,
+    "CircularInOut": CircularEaseInOut,
+    "ExponentialIn": ExponentialEaseIn,
+    "ExponentialOut": ExponentialEaseOut,
+    "ExponentialInOut": ExponentialEaseInOut,
+    "ElasticIn": ElasticEaseIn,
+    "ElasticOut": ElasticEaseOut,
+    "ElasticInOut": ElasticEaseInOut,
+    "BackIn": BackEaseIn,
+    "BackOut": BackEaseOut,
+    "BackInOut": BackEaseInOut,
+    "BounceIn": BounceEaseIn,
+    "BounceOut": BounceEaseOut,
+    "BounceInOut": BounceEaseInOut,
+}
+
+EASING_FUNCTION_KEYS = Literal[tuple(EASING_FUNCTIONS_MAP.keys())]
+
+
+# actually I think for now could just use CollectionOutput (which is list[Any]
+@invocation(
+    "step_param_easing",
+    title="Step Param Easing",
+    tags=["step", "easing"],
+    category="step",
+    version="1.0.2",
+)
+class StepParamEasingInvocation(BaseInvocation):
+    """Experimental per-step parameter easing for denoising steps"""
+
+    easing: EASING_FUNCTION_KEYS = InputField(default="Linear", description="The easing function to use")
+    num_steps: int = InputField(default=20, description="number of denoising steps")
+    start_value: float = InputField(default=0.0, description="easing starting value")
+    end_value: float = InputField(default=1.0, description="easing ending value")
+    start_step_percent: float = InputField(default=0.0, description="fraction of steps at which to start easing")
+    end_step_percent: float = InputField(default=1.0, description="fraction of steps after which to end easing")
+    # if None, then start_value is used prior to easing start
+    pre_start_value: Optional[float] = InputField(default=None, description="value before easing start")
+    # if None, then end value is used prior to easing end
+    post_end_value: Optional[float] = InputField(default=None, description="value after easing end")
+    mirror: bool = InputField(default=False, description="include mirror of easing function")
+    # FIXME: add alt_mirror option (alternative to default or mirror), or remove entirely
+    # alt_mirror: bool = InputField(default=False, description="alternative mirroring by dual easing")
+    show_easing_plot: bool = InputField(default=False, description="show easing plot")
+
+    def invoke(self, context: InvocationContext) -> FloatCollectionOutput:
+        log_diagnostics = False
+        # convert from start_step_percent to nearest step <= (steps * start_step_percent)
+        # start_step = int(np.floor(self.num_steps * self.start_step_percent))
+        start_step = int(np.round(self.num_steps * self.start_step_percent))
+        # convert from end_step_percent to nearest step >= (steps * end_step_percent)
+        # end_step = int(np.ceil((self.num_steps - 1) * self.end_step_percent))
+        end_step = int(np.round((self.num_steps - 1) * self.end_step_percent))
+
+        # end_step = int(np.ceil(self.num_steps * self.end_step_percent))
+        num_easing_steps = end_step - start_step + 1
+
+        # num_presteps = max(start_step - 1, 0)
+        num_presteps = start_step
+        num_poststeps = self.num_steps - (num_presteps + num_easing_steps)
+        prelist = list(num_presteps * [self.pre_start_value])
+        postlist = list(num_poststeps * [self.post_end_value])
+
+        if log_diagnostics:
+            context.logger.debug("start_step: " + str(start_step))
+            context.logger.debug("end_step: " + str(end_step))
+            context.logger.debug("num_easing_steps: " + str(num_easing_steps))
+            context.logger.debug("num_presteps: " + str(num_presteps))
+            context.logger.debug("num_poststeps: " + str(num_poststeps))
+            context.logger.debug("prelist size: " + str(len(prelist)))
+            context.logger.debug("postlist size: " + str(len(postlist)))
+            context.logger.debug("prelist: " + str(prelist))
+            context.logger.debug("postlist: " + str(postlist))
+
+        easing_class = EASING_FUNCTIONS_MAP[self.easing]
+        if log_diagnostics:
+            context.logger.debug("easing class: " + str(easing_class))
+        easing_list = []
+        if self.mirror:  # "expected" mirroring
+            # if number of steps is even, squeeze duration down to (number_of_steps)/2
+            # and create reverse copy of list to append
+            # if number of steps is odd, squeeze duration down to ceil(number_of_steps/2)
+            # and create reverse copy of list[1:end-1]
+            # but if even then number_of_steps/2 === ceil(number_of_steps/2), so can just use ceil always
+
+            base_easing_duration = int(np.ceil(num_easing_steps / 2.0))
+            if log_diagnostics:
+                context.logger.debug("base easing duration: " + str(base_easing_duration))
+            even_num_steps = num_easing_steps % 2 == 0  # even number of steps
+            easing_function = easing_class(
+                start=self.start_value,
+                end=self.end_value,
+                duration=base_easing_duration - 1,
+            )
+            base_easing_vals = []
+            for step_index in range(base_easing_duration):
+                easing_val = easing_function.ease(step_index)
+                base_easing_vals.append(easing_val)
+                if log_diagnostics:
+                    context.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(easing_val))
+            if even_num_steps:
+                mirror_easing_vals = list(reversed(base_easing_vals))
+            else:
+                mirror_easing_vals = list(reversed(base_easing_vals[0:-1]))
+            if log_diagnostics:
+                context.logger.debug("base easing vals: " + str(base_easing_vals))
+                context.logger.debug("mirror easing vals: " + str(mirror_easing_vals))
+            easing_list = base_easing_vals + mirror_easing_vals
+
+        # FIXME: add alt_mirror option (alternative to default or mirror), or remove entirely
+        # elif self.alt_mirror:  # function mirroring (unintuitive behavior (at least to me))
+        #     # half_ease_duration = round(num_easing_steps - 1 / 2)
+        #     half_ease_duration = round((num_easing_steps - 1) / 2)
+        #     easing_function = easing_class(start=self.start_value,
+        #                                    end=self.end_value,
+        #                                    duration=half_ease_duration,
+        #                                    )
+        #
+        #     mirror_function = easing_class(start=self.end_value,
+        #                                    end=self.start_value,
+        #                                    duration=half_ease_duration,
+        #                                    )
+        #     for step_index in range(num_easing_steps):
+        #         if step_index <= half_ease_duration:
+        #             step_val = easing_function.ease(step_index)
+        #         else:
+        #             step_val = mirror_function.ease(step_index - half_ease_duration)
+        #         easing_list.append(step_val)
+        #         if log_diagnostics: logger.debug(step_index, step_val)
+        #
+
+        else:  # no mirroring (default)
+            easing_function = easing_class(
+                start=self.start_value,
+                end=self.end_value,
+                duration=num_easing_steps - 1,
+            )
+            for step_index in range(num_easing_steps):
+                step_val = easing_function.ease(step_index)
+                easing_list.append(step_val)
+                if log_diagnostics:
+                    context.logger.debug("step_index: " + str(step_index) + ", easing_val: " + str(step_val))
+
+        if log_diagnostics:
+            context.logger.debug("prelist size: " + str(len(prelist)))
+            context.logger.debug("easing_list size: " + str(len(easing_list)))
+            context.logger.debug("postlist size: " + str(len(postlist)))
+
+        param_list = prelist + easing_list + postlist
+
+        if self.show_easing_plot:
+            plt.figure()
+            plt.xlabel("Step")
+            plt.ylabel("Param Value")
+            plt.title("Per-Step Values Based On Easing: " + self.easing)
+            plt.bar(range(len(param_list)), param_list)
+            # plt.plot(param_list)
+            ax = plt.gca()
+            ax.xaxis.set_major_locator(MaxNLocator(integer=True))
+            buf = io.BytesIO()
+            plt.savefig(buf, format="png")
+            buf.seek(0)
+            im = PIL.Image.open(buf)
+            im.show()
+            buf.close()
+
+        # output array of size steps, each entry list[i] is param value for step i
+        return FloatCollectionOutput(collection=param_list)

invokeai/app/invocations/primitives.py

@@ -4,13 +4,7 @@ from typing import Optional
 
 import torch
 
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    Classification,
-    invocation,
-    invocation_output,
-)
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
 from invokeai.app.invocations.fields import (
     BoundingBoxField,
@@ -24,7 +18,6 @@ from invokeai.app.invocations.fields import (
     InputField,
     LatentsField,
     OutputField,
-    SD3ConditioningField,
     TensorField,
     UIComponent,
 )
@@ -433,17 +426,6 @@ 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"""
@@ -539,23 +521,3 @@ class BoundingBoxInvocation(BaseInvocation):
 
 
 # endregion
-
-
-@invocation(
-    "image_batch",
-    title="Image Batch",
-    tags=["primitives", "image", "batch", "internal"],
-    category="primitives",
-    version="1.0.0",
-    classification=Classification.Special,
-)
-class ImageBatchInvocation(BaseInvocation):
-    """Create a batched generation, where the workflow is executed once for each image in the batch."""
-
-    images: list[ImageField] = InputField(min_length=1, description="The images to batch over", input=Input.Direct)
-
-    def __init__(self):
-        raise NotImplementedError("This class should never be executed or instantiated directly.")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        raise NotImplementedError("This class should never be executed or instantiated directly.")

invokeai/app/invocations/sd3_denoise.py

@@ -1,338 +0,0 @@
-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

@@ -1,65 +0,0 @@
-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

@@ -1,74 +0,0 @@
-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

@@ -1,108 +0,0 @@
-from typing import Optional
-
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    Classification,
-    invocation,
-    invocation_output,
-)
-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 SubModelType
-
-
-@invocation_output("sd3_model_loader_output")
-class Sd3ModelLoaderOutput(BaseInvocationOutput):
-    """SD3 base model loader output."""
-
-    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")
-    vae: VAEField = OutputField(description=FieldDescriptions.vae, title="VAE")
-
-
-@invocation(
-    "sd3_model_loader",
-    title="SD3 Main Model",
-    tags=["model", "sd3"],
-    category="model",
-    version="1.0.0",
-    classification=Classification.Prototype,
-)
-class Sd3ModelLoaderInvocation(BaseInvocation):
-    """Loads a SD3 base model, outputting its submodels."""
-
-    model: ModelIdentifierField = InputField(
-        description=FieldDescriptions.sd3_model,
-        ui_type=UIType.SD3MainModel,
-        input=Input.Direct,
-    )
-
-    t5_encoder_model: Optional[ModelIdentifierField] = InputField(
-        description=FieldDescriptions.t5_encoder,
-        ui_type=UIType.T5EncoderModel,
-        input=Input.Direct,
-        title="T5 Encoder",
-        default=None,
-    )
-
-    clip_l_model: Optional[ModelIdentifierField] = InputField(
-        description=FieldDescriptions.clip_embed_model,
-        ui_type=UIType.CLIPLEmbedModel,
-        input=Input.Direct,
-        title="CLIP L Encoder",
-        default=None,
-    )
-
-    clip_g_model: Optional[ModelIdentifierField] = InputField(
-        description=FieldDescriptions.clip_g_model,
-        ui_type=UIType.CLIPGEmbedModel,
-        input=Input.Direct,
-        title="CLIP G Encoder",
-        default=None,
-    )
-
-    vae_model: Optional[ModelIdentifierField] = InputField(
-        description=FieldDescriptions.vae_model, ui_type=UIType.VAEModel, title="VAE", default=None
-    )
-
-    def invoke(self, context: InvocationContext) -> Sd3ModelLoaderOutput:
-        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(
-            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),
-            vae=VAEField(vae=vae),
-        )

invokeai/app/invocations/sd3_text_encoder.py

@@ -1,201 +0,0 @@
-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
+from pydantic import BaseModel, Field, model_validator
 from transformers import AutoModelForMaskGeneration, AutoProcessor
 from transformers.models.sam import SamModel
 from transformers.models.sam.processing_sam import SamProcessor
@@ -77,14 +77,19 @@ 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/invocation_stats/invocation_stats_default.py

@@ -20,7 +20,7 @@ from invokeai.app.services.invocation_stats.invocation_stats_common import (
     NodeExecutionStatsSummary,
 )
 from invokeai.app.services.invoker import Invoker
-from invokeai.backend.model_manager.load.model_cache.cache_stats import CacheStats
+from invokeai.backend.model_manager.load.model_cache import CacheStats
 
 # Size of 1GB in bytes.
 GB = 2**30

invokeai/app/services/model_load/model_load_base.py

@@ -7,7 +7,7 @@ from typing import Callable, Optional
 
 from invokeai.backend.model_manager import AnyModel, AnyModelConfig, SubModelType
 from invokeai.backend.model_manager.load import LoadedModel, LoadedModelWithoutConfig
-from invokeai.backend.model_manager.load.model_cache.model_cache import ModelCache
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
 
 
 class ModelLoadServiceBase(ABC):
@@ -24,7 +24,7 @@ class ModelLoadServiceBase(ABC):
 
     @property
     @abstractmethod
-    def ram_cache(self) -> ModelCache:
+    def ram_cache(self) -> ModelCacheBase[AnyModel]:
         """Return the RAM cache used by this loader."""
 
     @abstractmethod

invokeai/app/services/model_load/model_load_default.py

@@ -18,7 +18,7 @@ from invokeai.backend.model_manager.load import (
     ModelLoaderRegistry,
     ModelLoaderRegistryBase,
 )
-from invokeai.backend.model_manager.load.model_cache.model_cache import ModelCache
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
 from invokeai.backend.model_manager.load.model_loaders.generic_diffusers import GenericDiffusersLoader
 from invokeai.backend.util.devices import TorchDevice
 from invokeai.backend.util.logging import InvokeAILogger
@@ -30,7 +30,7 @@ class ModelLoadService(ModelLoadServiceBase):
     def __init__(
         self,
         app_config: InvokeAIAppConfig,
-        ram_cache: ModelCache,
+        ram_cache: ModelCacheBase[AnyModel],
         registry: Optional[Type[ModelLoaderRegistryBase]] = ModelLoaderRegistry,
     ):
         """Initialize the model load service."""
@@ -45,7 +45,7 @@ class ModelLoadService(ModelLoadServiceBase):
         self._invoker = invoker
 
     @property
-    def ram_cache(self) -> ModelCache:
+    def ram_cache(self) -> ModelCacheBase[AnyModel]:
         """Return the RAM cache used by this loader."""
         return self._ram_cache
 
@@ -78,14 +78,15 @@ class ModelLoadService(ModelLoadServiceBase):
         self, model_path: Path, loader: Optional[Callable[[Path], AnyModel]] = None
     ) -> LoadedModelWithoutConfig:
         cache_key = str(model_path)
+        ram_cache = self.ram_cache
         try:
-            return LoadedModelWithoutConfig(cache_record=self._ram_cache.get(key=cache_key), cache=self._ram_cache)
+            return LoadedModelWithoutConfig(_locker=ram_cache.get(key=cache_key))
         except IndexError:
             pass
 
         def torch_load_file(checkpoint: Path) -> AnyModel:
             scan_result = scan_file_path(checkpoint)
-            if scan_result.infected_files != 0 or scan_result.scan_err:
+            if scan_result.infected_files != 0:
                 raise Exception("The model at {checkpoint} is potentially infected by malware. Aborting load.")
             result = torch_load(checkpoint, map_location="cpu")
             return result
@@ -108,5 +109,5 @@ class ModelLoadService(ModelLoadServiceBase):
         )
         assert loader is not None
         raw_model = loader(model_path)
-        self._ram_cache.put(key=cache_key, model=raw_model)
-        return LoadedModelWithoutConfig(cache_record=self._ram_cache.get(key=cache_key), cache=self._ram_cache)
+        ram_cache.put(key=cache_key, model=raw_model)
+        return LoadedModelWithoutConfig(_locker=ram_cache.get(key=cache_key))

invokeai/app/services/model_manager/model_manager_default.py

@@ -16,8 +16,7 @@ from invokeai.app.services.model_load.model_load_base import ModelLoadServiceBas
 from invokeai.app.services.model_load.model_load_default import ModelLoadService
 from invokeai.app.services.model_manager.model_manager_base import ModelManagerServiceBase
 from invokeai.app.services.model_records.model_records_base import ModelRecordServiceBase
-from invokeai.backend.model_manager.load.model_cache.model_cache import ModelCache
-from invokeai.backend.model_manager.load.model_loader_registry import ModelLoaderRegistry
+from invokeai.backend.model_manager.load import ModelCache, ModelLoaderRegistry
 from invokeai.backend.util.devices import TorchDevice
 from invokeai.backend.util.logging import InvokeAILogger
 

invokeai/app/services/model_records/model_records_base.py

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

@@ -16,7 +16,6 @@ from pydantic import (
 from pydantic_core import to_jsonable_python
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation
-from invokeai.app.invocations.fields import ImageField
 from invokeai.app.services.shared.graph import Graph, GraphExecutionState, NodeNotFoundError
 from invokeai.app.services.workflow_records.workflow_records_common import (
     WorkflowWithoutID,
@@ -52,7 +51,11 @@ class SessionQueueItemNotFoundError(ValueError):
 
 # region Batch
 
-BatchDataType = Union[StrictStr, float, int, ImageField]
+BatchDataType = Union[
+    StrictStr,
+    float,
+    int,
+]
 
 
 class NodeFieldValue(BaseModel):

invokeai/app/services/shared/invocation_context.py

@@ -160,10 +160,6 @@ 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,
@@ -190,8 +186,6 @@ 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:
@@ -342,10 +336,6 @@ class ConditioningInterface(InvocationContextInterface):
 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.
 
@@ -378,15 +368,11 @@ 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)
-
-        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)
+            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
@@ -411,10 +397,6 @@ 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:
@@ -485,7 +467,6 @@ 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(
@@ -508,8 +489,6 @@ 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(
@@ -535,8 +514,6 @@ 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)
 
 
@@ -730,12 +707,12 @@ 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

@@ -1,382 +0,0 @@
-{
-    "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

@@ -34,25 +34,6 @@ 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],
@@ -129,9 +110,6 @@ 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/flux/custom_block_processor.py

@@ -1,10 +1,9 @@
 import einops
 import torch
 
-from invokeai.backend.flux.extensions.regional_prompting_extension import RegionalPromptingExtension
 from invokeai.backend.flux.extensions.xlabs_ip_adapter_extension import XLabsIPAdapterExtension
 from invokeai.backend.flux.math import attention
-from invokeai.backend.flux.modules.layers import DoubleStreamBlock, SingleStreamBlock
+from invokeai.backend.flux.modules.layers import DoubleStreamBlock
 
 
 class CustomDoubleStreamBlockProcessor:
@@ -14,12 +13,7 @@ class CustomDoubleStreamBlockProcessor:
 
     @staticmethod
     def _double_stream_block_forward(
-        block: DoubleStreamBlock,
-        img: torch.Tensor,
-        txt: torch.Tensor,
-        vec: torch.Tensor,
-        pe: torch.Tensor,
-        attn_mask: torch.Tensor | None = None,
+        block: DoubleStreamBlock, img: torch.Tensor, txt: torch.Tensor, vec: torch.Tensor, pe: torch.Tensor
     ) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
         """This function is a direct copy of DoubleStreamBlock.forward(), but it returns some of the intermediate
         values.
@@ -46,7 +40,7 @@ class CustomDoubleStreamBlockProcessor:
         k = torch.cat((txt_k, img_k), dim=2)
         v = torch.cat((txt_v, img_v), dim=2)
 
-        attn = attention(q, k, v, pe=pe, attn_mask=attn_mask)
+        attn = attention(q, k, v, pe=pe)
         txt_attn, img_attn = attn[:, : txt.shape[1]], attn[:, txt.shape[1] :]
 
         # calculate the img bloks
@@ -69,15 +63,11 @@ class CustomDoubleStreamBlockProcessor:
         vec: torch.Tensor,
         pe: torch.Tensor,
         ip_adapter_extensions: list[XLabsIPAdapterExtension],
-        regional_prompting_extension: RegionalPromptingExtension,
     ) -> tuple[torch.Tensor, torch.Tensor]:
         """A custom implementation of DoubleStreamBlock.forward() with additional features:
         - IP-Adapter support
         """
-        attn_mask = regional_prompting_extension.get_double_stream_attn_mask(block_index)
-        img, txt, img_q = CustomDoubleStreamBlockProcessor._double_stream_block_forward(
-            block, img, txt, vec, pe, attn_mask=attn_mask
-        )
+        img, txt, img_q = CustomDoubleStreamBlockProcessor._double_stream_block_forward(block, img, txt, vec, pe)
 
         # Apply IP-Adapter conditioning.
         for ip_adapter_extension in ip_adapter_extensions:
@@ -91,48 +81,3 @@ class CustomDoubleStreamBlockProcessor:
             )
 
         return img, txt
-
-
-class CustomSingleStreamBlockProcessor:
-    """A class containing a custom implementation of SingleStreamBlock.forward() with additional features (masking,
-    etc.)
-    """
-
-    @staticmethod
-    def _single_stream_block_forward(
-        block: SingleStreamBlock,
-        x: torch.Tensor,
-        vec: torch.Tensor,
-        pe: torch.Tensor,
-        attn_mask: torch.Tensor | None = None,
-    ) -> torch.Tensor:
-        """This function is a direct copy of SingleStreamBlock.forward()."""
-        mod, _ = block.modulation(vec)
-        x_mod = (1 + mod.scale) * block.pre_norm(x) + mod.shift
-        qkv, mlp = torch.split(block.linear1(x_mod), [3 * block.hidden_size, block.mlp_hidden_dim], dim=-1)
-
-        q, k, v = einops.rearrange(qkv, "B L (K H D) -> K B H L D", K=3, H=block.num_heads)
-        q, k = block.norm(q, k, v)
-
-        # compute attention
-        attn = attention(q, k, v, pe=pe, attn_mask=attn_mask)
-        # compute activation in mlp stream, cat again and run second linear layer
-        output = block.linear2(torch.cat((attn, block.mlp_act(mlp)), 2))
-        return x + mod.gate * output
-
-    @staticmethod
-    def custom_single_block_forward(
-        timestep_index: int,
-        total_num_timesteps: int,
-        block_index: int,
-        block: SingleStreamBlock,
-        img: torch.Tensor,
-        vec: torch.Tensor,
-        pe: torch.Tensor,
-        regional_prompting_extension: RegionalPromptingExtension,
-    ) -> torch.Tensor:
-        """A custom implementation of SingleStreamBlock.forward() with additional features:
-        - Masking
-        """
-        attn_mask = regional_prompting_extension.get_single_stream_attn_mask(block_index)
-        return CustomSingleStreamBlockProcessor._single_stream_block_forward(block, img, vec, pe, attn_mask=attn_mask)

invokeai/backend/flux/denoise.py

@@ -7,7 +7,6 @@ from tqdm import tqdm
 from invokeai.backend.flux.controlnet.controlnet_flux_output import ControlNetFluxOutput, sum_controlnet_flux_outputs
 from invokeai.backend.flux.extensions.inpaint_extension import InpaintExtension
 from invokeai.backend.flux.extensions.instantx_controlnet_extension import InstantXControlNetExtension
-from invokeai.backend.flux.extensions.regional_prompting_extension import RegionalPromptingExtension
 from invokeai.backend.flux.extensions.xlabs_controlnet_extension import XLabsControlNetExtension
 from invokeai.backend.flux.extensions.xlabs_ip_adapter_extension import XLabsIPAdapterExtension
 from invokeai.backend.flux.model import Flux
@@ -19,8 +18,14 @@ def denoise(
     # model input
     img: torch.Tensor,
     img_ids: torch.Tensor,
-    pos_regional_prompting_extension: RegionalPromptingExtension,
-    neg_regional_prompting_extension: RegionalPromptingExtension | None,
+    # positive text conditioning
+    txt: torch.Tensor,
+    txt_ids: torch.Tensor,
+    vec: torch.Tensor,
+    # negative text conditioning
+    neg_txt: torch.Tensor | None,
+    neg_txt_ids: torch.Tensor | None,
+    neg_vec: torch.Tensor | None,
     # sampling parameters
     timesteps: list[float],
     step_callback: Callable[[PipelineIntermediateState], None],
@@ -56,9 +61,9 @@ def denoise(
                     total_num_timesteps=total_steps,
                     img=img,
                     img_ids=img_ids,
-                    txt=pos_regional_prompting_extension.regional_text_conditioning.t5_embeddings,
-                    txt_ids=pos_regional_prompting_extension.regional_text_conditioning.t5_txt_ids,
-                    y=pos_regional_prompting_extension.regional_text_conditioning.clip_embeddings,
+                    txt=txt,
+                    txt_ids=txt_ids,
+                    y=vec,
                     timesteps=t_vec,
                     guidance=guidance_vec,
                 )
@@ -73,9 +78,9 @@ def denoise(
         pred = model(
             img=img,
             img_ids=img_ids,
-            txt=pos_regional_prompting_extension.regional_text_conditioning.t5_embeddings,
-            txt_ids=pos_regional_prompting_extension.regional_text_conditioning.t5_txt_ids,
-            y=pos_regional_prompting_extension.regional_text_conditioning.clip_embeddings,
+            txt=txt,
+            txt_ids=txt_ids,
+            y=vec,
             timesteps=t_vec,
             guidance=guidance_vec,
             timestep_index=step_index,
@@ -83,7 +88,6 @@ def denoise(
             controlnet_double_block_residuals=merged_controlnet_residuals.double_block_residuals,
             controlnet_single_block_residuals=merged_controlnet_residuals.single_block_residuals,
             ip_adapter_extensions=pos_ip_adapter_extensions,
-            regional_prompting_extension=pos_regional_prompting_extension,
         )
 
         step_cfg_scale = cfg_scale[step_index]
@@ -93,15 +97,15 @@ def denoise(
             # TODO(ryand): Add option to run positive and negative predictions in a single batch for better performance
             # on systems with sufficient VRAM.
 
-            if neg_regional_prompting_extension is None:
+            if neg_txt is None or neg_txt_ids is None or neg_vec is None:
                 raise ValueError("Negative text conditioning is required when cfg_scale is not 1.0.")
 
             neg_pred = model(
                 img=img,
                 img_ids=img_ids,
-                txt=neg_regional_prompting_extension.regional_text_conditioning.t5_embeddings,
-                txt_ids=neg_regional_prompting_extension.regional_text_conditioning.t5_txt_ids,
-                y=neg_regional_prompting_extension.regional_text_conditioning.clip_embeddings,
+                txt=neg_txt,
+                txt_ids=neg_txt_ids,
+                y=neg_vec,
                 timesteps=t_vec,
                 guidance=guidance_vec,
                 timestep_index=step_index,
@@ -109,7 +113,6 @@ def denoise(
                 controlnet_double_block_residuals=None,
                 controlnet_single_block_residuals=None,
                 ip_adapter_extensions=neg_ip_adapter_extensions,
-                regional_prompting_extension=neg_regional_prompting_extension,
             )
             pred = neg_pred + step_cfg_scale * (pred - neg_pred)
 

invokeai/backend/flux/extensions/regional_prompting_extension.py

@@ -1,276 +0,0 @@
-from typing import Optional
-
-import torch
-import torchvision
-
-from invokeai.backend.flux.text_conditioning import FluxRegionalTextConditioning, FluxTextConditioning
-from invokeai.backend.stable_diffusion.diffusion.conditioning_data import Range
-from invokeai.backend.util.devices import TorchDevice
-from invokeai.backend.util.mask import to_standard_float_mask
-
-
-class RegionalPromptingExtension:
-    """A class for managing regional prompting with FLUX.
-
-    This implementation is inspired by https://arxiv.org/pdf/2411.02395 (though there are significant differences).
-    """
-
-    def __init__(
-        self,
-        regional_text_conditioning: FluxRegionalTextConditioning,
-        restricted_attn_mask: torch.Tensor | None = None,
-    ):
-        self.regional_text_conditioning = regional_text_conditioning
-        self.restricted_attn_mask = restricted_attn_mask
-
-    def get_double_stream_attn_mask(self, block_index: int) -> torch.Tensor | None:
-        order = [self.restricted_attn_mask, None]
-        return order[block_index % len(order)]
-
-    def get_single_stream_attn_mask(self, block_index: int) -> torch.Tensor | None:
-        order = [self.restricted_attn_mask, None]
-        return order[block_index % len(order)]
-
-    @classmethod
-    def from_text_conditioning(cls, text_conditioning: list[FluxTextConditioning], img_seq_len: int):
-        """Create a RegionalPromptingExtension from a list of text conditionings.
-
-        Args:
-            text_conditioning (list[FluxTextConditioning]): The text conditionings to use for regional prompting.
-            img_seq_len (int): The image sequence length (i.e. packed_height * packed_width).
-        """
-        regional_text_conditioning = cls._concat_regional_text_conditioning(text_conditioning)
-        attn_mask_with_restricted_img_self_attn = cls._prepare_restricted_attn_mask(
-            regional_text_conditioning, img_seq_len
-        )
-        return cls(
-            regional_text_conditioning=regional_text_conditioning,
-            restricted_attn_mask=attn_mask_with_restricted_img_self_attn,
-        )
-
-    # Keeping _prepare_unrestricted_attn_mask for reference as an alternative masking strategy:
-    #
-    # @classmethod
-    # def _prepare_unrestricted_attn_mask(
-    #     cls,
-    #     regional_text_conditioning: FluxRegionalTextConditioning,
-    #     img_seq_len: int,
-    # ) -> torch.Tensor:
-    #     """Prepare an 'unrestricted' attention mask. In this context, 'unrestricted' means that:
-    #     - img self-attention is not masked.
-    #     - img regions attend to both txt within their own region and to global prompts.
-    #     """
-    #     device = TorchDevice.choose_torch_device()
-
-    #     # Infer txt_seq_len from the t5_embeddings tensor.
-    #     txt_seq_len = regional_text_conditioning.t5_embeddings.shape[1]
-
-    #     # In the attention blocks, the txt seq and img seq are concatenated and then attention is applied.
-    #     # Concatenation happens in the following order: [txt_seq, img_seq].
-    #     # There are 4 portions of the attention mask to consider as we prepare it:
-    #     # 1. txt attends to itself
-    #     # 2. txt attends to corresponding regional img
-    #     # 3. regional img attends to corresponding txt
-    #     # 4. regional img attends to itself
-
-    #     # Initialize empty attention mask.
-    #     regional_attention_mask = torch.zeros(
-    #         (txt_seq_len + img_seq_len, txt_seq_len + img_seq_len), device=device, dtype=torch.float16
-    #     )
-
-    #     for image_mask, t5_embedding_range in zip(
-    #         regional_text_conditioning.image_masks, regional_text_conditioning.t5_embedding_ranges, strict=True
-    #     ):
-    #         # 1. txt attends to itself
-    #         regional_attention_mask[
-    #             t5_embedding_range.start : t5_embedding_range.end, t5_embedding_range.start : t5_embedding_range.end
-    #         ] = 1.0
-
-    #         # 2. txt attends to corresponding regional img
-    #         # Note that we reshape to (1, img_seq_len) to ensure broadcasting works as desired.
-    #         fill_value = image_mask.view(1, img_seq_len) if image_mask is not None else 1.0
-    #         regional_attention_mask[t5_embedding_range.start : t5_embedding_range.end, txt_seq_len:] = fill_value
-
-    #         # 3. regional img attends to corresponding txt
-    #         # Note that we reshape to (img_seq_len, 1) to ensure broadcasting works as desired.
-    #         fill_value = image_mask.view(img_seq_len, 1) if image_mask is not None else 1.0
-    #         regional_attention_mask[txt_seq_len:, t5_embedding_range.start : t5_embedding_range.end] = fill_value
-
-    #     # 4. regional img attends to itself
-    #     # Allow unrestricted img self attention.
-    #     regional_attention_mask[txt_seq_len:, txt_seq_len:] = 1.0
-
-    #     # Convert attention mask to boolean.
-    #     regional_attention_mask = regional_attention_mask > 0.5
-
-    #     return regional_attention_mask
-
-    @classmethod
-    def _prepare_restricted_attn_mask(
-        cls,
-        regional_text_conditioning: FluxRegionalTextConditioning,
-        img_seq_len: int,
-    ) -> torch.Tensor | None:
-        """Prepare a 'restricted' attention mask. In this context, 'restricted' means that:
-        - img self-attention is only allowed within regions.
-        - img regions only attend to txt within their own region, not to global prompts.
-        """
-        # Identify background region. I.e. the region that is not covered by any region masks.
-        background_region_mask: None | torch.Tensor = None
-        for image_mask in regional_text_conditioning.image_masks:
-            if image_mask is not None:
-                if background_region_mask is None:
-                    background_region_mask = torch.ones_like(image_mask)
-                background_region_mask *= 1 - image_mask
-
-        if background_region_mask is None:
-            # There are no region masks, short-circuit and return None.
-            # TODO(ryand): We could restrict txt-txt attention across multiple global prompts, but this would
-            # is a rare use case and would make the logic here significantly more complicated.
-            return None
-
-        device = TorchDevice.choose_torch_device()
-
-        # Infer txt_seq_len from the t5_embeddings tensor.
-        txt_seq_len = regional_text_conditioning.t5_embeddings.shape[1]
-
-        # In the attention blocks, the txt seq and img seq are concatenated and then attention is applied.
-        # Concatenation happens in the following order: [txt_seq, img_seq].
-        # There are 4 portions of the attention mask to consider as we prepare it:
-        # 1. txt attends to itself
-        # 2. txt attends to corresponding regional img
-        # 3. regional img attends to corresponding txt
-        # 4. regional img attends to itself
-
-        # Initialize empty attention mask.
-        regional_attention_mask = torch.zeros(
-            (txt_seq_len + img_seq_len, txt_seq_len + img_seq_len), device=device, dtype=torch.float16
-        )
-
-        for image_mask, t5_embedding_range in zip(
-            regional_text_conditioning.image_masks, regional_text_conditioning.t5_embedding_ranges, strict=True
-        ):
-            # 1. txt attends to itself
-            regional_attention_mask[
-                t5_embedding_range.start : t5_embedding_range.end, t5_embedding_range.start : t5_embedding_range.end
-            ] = 1.0
-
-            if image_mask is not None:
-                # 2. txt attends to corresponding regional img
-                # Note that we reshape to (1, img_seq_len) to ensure broadcasting works as desired.
-                regional_attention_mask[t5_embedding_range.start : t5_embedding_range.end, txt_seq_len:] = (
-                    image_mask.view(1, img_seq_len)
-                )
-
-                # 3. regional img attends to corresponding txt
-                # Note that we reshape to (img_seq_len, 1) to ensure broadcasting works as desired.
-                regional_attention_mask[txt_seq_len:, t5_embedding_range.start : t5_embedding_range.end] = (
-                    image_mask.view(img_seq_len, 1)
-                )
-
-                # 4. regional img attends to itself
-                image_mask = image_mask.view(img_seq_len, 1)
-                regional_attention_mask[txt_seq_len:, txt_seq_len:] += image_mask @ image_mask.T
-            else:
-                # We don't allow attention between non-background image regions and global prompts. This helps to ensure
-                # that regions focus on their local prompts. We do, however, allow attention between background regions
-                # and global prompts. If we didn't do this, then the background regions would not attend to any txt
-                # embeddings, which we found experimentally to cause artifacts.
-
-                # 2. global txt attends to background region
-                # Note that we reshape to (1, img_seq_len) to ensure broadcasting works as desired.
-                regional_attention_mask[t5_embedding_range.start : t5_embedding_range.end, txt_seq_len:] = (
-                    background_region_mask.view(1, img_seq_len)
-                )
-
-                # 3. background region attends to global txt
-                # Note that we reshape to (img_seq_len, 1) to ensure broadcasting works as desired.
-                regional_attention_mask[txt_seq_len:, t5_embedding_range.start : t5_embedding_range.end] = (
-                    background_region_mask.view(img_seq_len, 1)
-                )
-
-        # Allow background regions to attend to themselves.
-        regional_attention_mask[txt_seq_len:, txt_seq_len:] += background_region_mask.view(img_seq_len, 1)
-        regional_attention_mask[txt_seq_len:, txt_seq_len:] += background_region_mask.view(1, img_seq_len)
-
-        # Convert attention mask to boolean.
-        regional_attention_mask = regional_attention_mask > 0.5
-
-        return regional_attention_mask
-
-    @classmethod
-    def _concat_regional_text_conditioning(
-        cls,
-        text_conditionings: list[FluxTextConditioning],
-    ) -> FluxRegionalTextConditioning:
-        """Concatenate regional text conditioning data into a single conditioning tensor (with associated masks)."""
-        concat_t5_embeddings: list[torch.Tensor] = []
-        concat_t5_embedding_ranges: list[Range] = []
-        image_masks: list[torch.Tensor | None] = []
-
-        # Choose global CLIP embedding.
-        # Use the first global prompt's CLIP embedding as the global CLIP embedding. If there is no global prompt, use
-        # the first prompt's CLIP embedding.
-        global_clip_embedding: torch.Tensor = text_conditionings[0].clip_embeddings
-        for text_conditioning in text_conditionings:
-            if text_conditioning.mask is None:
-                global_clip_embedding = text_conditioning.clip_embeddings
-                break
-
-        cur_t5_embedding_len = 0
-        for text_conditioning in text_conditionings:
-            concat_t5_embeddings.append(text_conditioning.t5_embeddings)
-
-            concat_t5_embedding_ranges.append(
-                Range(start=cur_t5_embedding_len, end=cur_t5_embedding_len + text_conditioning.t5_embeddings.shape[1])
-            )
-
-            image_masks.append(text_conditioning.mask)
-
-            cur_t5_embedding_len += text_conditioning.t5_embeddings.shape[1]
-
-        t5_embeddings = torch.cat(concat_t5_embeddings, dim=1)
-
-        # Initialize the txt_ids tensor.
-        pos_bs, pos_t5_seq_len, _ = t5_embeddings.shape
-        t5_txt_ids = torch.zeros(
-            pos_bs, pos_t5_seq_len, 3, dtype=t5_embeddings.dtype, device=TorchDevice.choose_torch_device()
-        )
-
-        return FluxRegionalTextConditioning(
-            t5_embeddings=t5_embeddings,
-            clip_embeddings=global_clip_embedding,
-            t5_txt_ids=t5_txt_ids,
-            image_masks=image_masks,
-            t5_embedding_ranges=concat_t5_embedding_ranges,
-        )
-
-    @staticmethod
-    def preprocess_regional_prompt_mask(
-        mask: Optional[torch.Tensor], packed_height: int, packed_width: int, dtype: torch.dtype, device: torch.device
-    ) -> torch.Tensor:
-        """Preprocess a regional prompt mask to match the target height and width.
-        If mask is None, returns a mask of all ones with the target height and width.
-        If mask is not None, resizes the mask to the target height and width using 'nearest' interpolation.
-
-        packed_height and packed_width are the target height and width of the mask in the 'packed' latent space.
-
-        Returns:
-            torch.Tensor: The processed mask. shape: (1, 1, packed_height * packed_width).
-        """
-
-        if mask is None:
-            return torch.ones((1, 1, packed_height * packed_width), dtype=dtype, device=device)
-
-        mask = to_standard_float_mask(mask, out_dtype=dtype)
-
-        tf = torchvision.transforms.Resize(
-            (packed_height, packed_width), interpolation=torchvision.transforms.InterpolationMode.NEAREST
-        )
-
-        # Add a batch dimension to the mask, because torchvision expects shape (batch, channels, h, w).
-        mask = mask.unsqueeze(0)  # Shape: (1, h, w) -> (1, 1, h, w)
-        resized_mask = tf(mask)
-
-        # Flatten the height and width dimensions into a single image_seq_len dimension.
-        return resized_mask.flatten(start_dim=2)

invokeai/backend/flux/ip_adapter/state_dict_utils.py

@@ -41,12 +41,10 @@ def infer_xlabs_ip_adapter_params_from_state_dict(state_dict: dict[str, torch.Te
     hidden_dim = state_dict["double_blocks.0.processor.ip_adapter_double_stream_k_proj.weight"].shape[0]
     context_dim = state_dict["double_blocks.0.processor.ip_adapter_double_stream_k_proj.weight"].shape[1]
     clip_embeddings_dim = state_dict["ip_adapter_proj_model.proj.weight"].shape[1]
-    clip_extra_context_tokens = state_dict["ip_adapter_proj_model.proj.weight"].shape[0] // context_dim
 
     return XlabsIpAdapterParams(
         num_double_blocks=num_double_blocks,
         context_dim=context_dim,
         hidden_dim=hidden_dim,
         clip_embeddings_dim=clip_embeddings_dim,
-        clip_extra_context_tokens=clip_extra_context_tokens,
     )

invokeai/backend/flux/ip_adapter/xlabs_ip_adapter_flux.py

@@ -31,16 +31,13 @@ class XlabsIpAdapterParams:
     hidden_dim: int
 
     clip_embeddings_dim: int
-    clip_extra_context_tokens: int
 
 
 class XlabsIpAdapterFlux(torch.nn.Module):
     def __init__(self, params: XlabsIpAdapterParams):
         super().__init__()
         self.image_proj = ImageProjModel(
-            cross_attention_dim=params.context_dim,
-            clip_embeddings_dim=params.clip_embeddings_dim,
-            clip_extra_context_tokens=params.clip_extra_context_tokens,
+            cross_attention_dim=params.context_dim, clip_embeddings_dim=params.clip_embeddings_dim
         )
         self.ip_adapter_double_blocks = IPAdapterDoubleBlocks(
             num_double_blocks=params.num_double_blocks, context_dim=params.context_dim, hidden_dim=params.hidden_dim

invokeai/backend/flux/math.py

@@ -5,10 +5,10 @@ from einops import rearrange
 from torch import Tensor
 
 
-def attention(q: Tensor, k: Tensor, v: Tensor, pe: Tensor, attn_mask: Tensor | None = None) -> Tensor:
+def attention(q: Tensor, k: Tensor, v: Tensor, pe: Tensor) -> Tensor:
     q, k = apply_rope(q, k, pe)
 
-    x = torch.nn.functional.scaled_dot_product_attention(q, k, v, attn_mask=attn_mask)
+    x = torch.nn.functional.scaled_dot_product_attention(q, k, v)
     x = rearrange(x, "B H L D -> B L (H D)")
 
     return x
@@ -24,12 +24,12 @@ def rope(pos: Tensor, dim: int, theta: int) -> Tensor:
     out = torch.einsum("...n,d->...nd", pos, omega)
     out = torch.stack([torch.cos(out), -torch.sin(out), torch.sin(out), torch.cos(out)], dim=-1)
     out = rearrange(out, "b n d (i j) -> b n d i j", i=2, j=2)
-    return out.to(dtype=pos.dtype, device=pos.device)
+    return out.float()
 
 
 def apply_rope(xq: Tensor, xk: Tensor, freqs_cis: Tensor) -> tuple[Tensor, Tensor]:
-    xq_ = xq.view(*xq.shape[:-1], -1, 1, 2)
-    xk_ = xk.view(*xk.shape[:-1], -1, 1, 2)
+    xq_ = xq.float().reshape(*xq.shape[:-1], -1, 1, 2)
+    xk_ = xk.float().reshape(*xk.shape[:-1], -1, 1, 2)
     xq_out = freqs_cis[..., 0] * xq_[..., 0] + freqs_cis[..., 1] * xq_[..., 1]
     xk_out = freqs_cis[..., 0] * xk_[..., 0] + freqs_cis[..., 1] * xk_[..., 1]
-    return xq_out.view(*xq.shape), xk_out.view(*xk.shape)
+    return xq_out.reshape(*xq.shape).type_as(xq), xk_out.reshape(*xk.shape).type_as(xk)

invokeai/backend/flux/model.py

@@ -5,11 +5,7 @@ from dataclasses import dataclass
 import torch
 from torch import Tensor, nn
 
-from invokeai.backend.flux.custom_block_processor import (
-    CustomDoubleStreamBlockProcessor,
-    CustomSingleStreamBlockProcessor,
-)
-from invokeai.backend.flux.extensions.regional_prompting_extension import RegionalPromptingExtension
+from invokeai.backend.flux.custom_block_processor import CustomDoubleStreamBlockProcessor
 from invokeai.backend.flux.extensions.xlabs_ip_adapter_extension import XLabsIPAdapterExtension
 from invokeai.backend.flux.modules.layers import (
     DoubleStreamBlock,
@@ -99,7 +95,6 @@ class Flux(nn.Module):
         controlnet_double_block_residuals: list[Tensor] | None,
         controlnet_single_block_residuals: list[Tensor] | None,
         ip_adapter_extensions: list[XLabsIPAdapterExtension],
-        regional_prompting_extension: RegionalPromptingExtension,
     ) -> Tensor:
         if img.ndim != 3 or txt.ndim != 3:
             raise ValueError("Input img and txt tensors must have 3 dimensions.")
@@ -122,6 +117,7 @@ class Flux(nn.Module):
             assert len(controlnet_double_block_residuals) == len(self.double_blocks)
         for block_index, block in enumerate(self.double_blocks):
             assert isinstance(block, DoubleStreamBlock)
+
             img, txt = CustomDoubleStreamBlockProcessor.custom_double_block_forward(
                 timestep_index=timestep_index,
                 total_num_timesteps=total_num_timesteps,
@@ -132,7 +128,6 @@ class Flux(nn.Module):
                 vec=vec,
                 pe=pe,
                 ip_adapter_extensions=ip_adapter_extensions,
-                regional_prompting_extension=regional_prompting_extension,
             )
 
             if controlnet_double_block_residuals is not None:
@@ -145,17 +140,7 @@ class Flux(nn.Module):
             assert len(controlnet_single_block_residuals) == len(self.single_blocks)
 
         for block_index, block in enumerate(self.single_blocks):
-            assert isinstance(block, SingleStreamBlock)
-            img = CustomSingleStreamBlockProcessor.custom_single_block_forward(
-                timestep_index=timestep_index,
-                total_num_timesteps=total_num_timesteps,
-                block_index=block_index,
-                block=block,
-                img=img,
-                vec=vec,
-                pe=pe,
-                regional_prompting_extension=regional_prompting_extension,
-            )
+            img = block(img, vec=vec, pe=pe)
 
             if controlnet_single_block_residuals is not None:
                 img[:, txt.shape[1] :, ...] += controlnet_single_block_residuals[block_index]

invokeai/backend/flux/modules/layers.py

@@ -66,7 +66,10 @@ class RMSNorm(torch.nn.Module):
         self.scale = nn.Parameter(torch.ones(dim))
 
     def forward(self, x: Tensor):
-        return torch.nn.functional.rms_norm(x, self.scale.shape, self.scale, eps=1e-6)
+        x_dtype = x.dtype
+        x = x.float()
+        rrms = torch.rsqrt(torch.mean(x**2, dim=-1, keepdim=True) + 1e-6)
+        return (x * rrms).to(dtype=x_dtype) * self.scale
 
 
 class QKNorm(torch.nn.Module):

invokeai/backend/flux/text_conditioning.py

@@ -1,36 +0,0 @@
-from dataclasses import dataclass
-
-import torch
-
-from invokeai.backend.stable_diffusion.diffusion.conditioning_data import Range
-
-
-@dataclass
-class FluxTextConditioning:
-    t5_embeddings: torch.Tensor
-    clip_embeddings: torch.Tensor
-    # If mask is None, the prompt is a global prompt.
-    mask: torch.Tensor | None
-
-
-@dataclass
-class FluxRegionalTextConditioning:
-    # Concatenated text embeddings.
-    # Shape: (1, concatenated_txt_seq_len, 4096)
-    t5_embeddings: torch.Tensor
-    # Shape: (1, concatenated_txt_seq_len, 3)
-    t5_txt_ids: torch.Tensor
-
-    # Global CLIP embeddings.
-    # Shape: (1, 768)
-    clip_embeddings: torch.Tensor
-
-    # A binary mask indicating the regions of the image that the prompt should be applied to. If None, the prompt is a
-    # global prompt.
-    # image_masks[i] is the mask for the ith prompt.
-    # image_masks[i] has shape (1, image_seq_len) and dtype torch.bool.
-    image_masks: list[torch.Tensor | None]
-
-    # List of ranges that represent the embedding ranges for each mask.
-    # t5_embedding_ranges[i] contains the range of the t5 embeddings that correspond to image_masks[i].
-    t5_embedding_ranges: list[Range]

invokeai/backend/lora/conversions/flux_diffusers_lora_conversion_utils.py

@@ -45,9 +45,8 @@ 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
-    hidden_size = 3072
-    mlp_ratio = 4.0
-    mlp_hidden_dim = int(hidden_size * mlp_ratio)
+    # inner_dim = 3072
+    # mlp_ratio = 4.0
 
     layers: dict[str, AnyLoRALayer] = {}
 
@@ -63,43 +62,30 @@ 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],
-        src_weight_shapes: list[tuple[int, int]],
-        dst_qkv_key: str,
-        allow_missing_keys: bool = False,
-    ) -> None:
+    def add_qkv_lora_layer_if_present(src_keys: list[str], dst_qkv_key: str) -> 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.
         """
-        # If none of the keys are present, return early.
+        # 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.
         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_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)
+        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)
 
     # time_text_embed.timestep_embedder -> time_in.
     add_lora_layer_if_present("time_text_embed.timestep_embedder.linear_1", "time_in.in_layer")
@@ -132,7 +118,6 @@ 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(
@@ -141,7 +126,6 @@ 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",
         )
 
@@ -191,14 +175,7 @@ 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

@@ -53,7 +53,6 @@ class BaseModelType(str, Enum):
     Any = "any"
     StableDiffusion1 = "sd-1"
     StableDiffusion2 = "sd-2"
-    StableDiffusion3 = "sd-3"
     StableDiffusionXL = "sdxl"
     StableDiffusionXLRefiner = "sdxl-refiner"
     Flux = "flux"
@@ -84,10 +83,8 @@ 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"
@@ -95,13 +92,6 @@ class SubModelType(str, Enum):
     SafetyChecker = "safety_checker"
 
 
-class ClipVariantType(str, Enum):
-    """Variant type."""
-
-    L = "large"
-    G = "gigantic"
-
-
 class ModelVariantType(str, Enum):
     """Variant type."""
 
@@ -157,17 +147,6 @@ 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")
@@ -214,9 +193,6 @@ 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):
@@ -359,7 +335,7 @@ class MainConfigBase(ModelConfigBase):
     default_settings: Optional[MainModelDefaultSettings] = Field(
         description="Default settings for this model", default=None
     )
-    variant: AnyVariant = ModelVariantType.Normal
+    variant: ModelVariantType = ModelVariantType.Normal
 
 
 class MainCheckpointConfig(CheckpointConfigBase, MainConfigBase):
@@ -443,33 +419,12 @@ 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."""
 
@@ -546,8 +501,6 @@ 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/__init__.py

@@ -8,7 +8,7 @@ from pathlib import Path
 
 from invokeai.backend.model_manager.load.load_base import LoadedModel, LoadedModelWithoutConfig, ModelLoaderBase
 from invokeai.backend.model_manager.load.load_default import ModelLoader
-from invokeai.backend.model_manager.load.model_cache.model_cache import ModelCache
+from invokeai.backend.model_manager.load.model_cache.model_cache_default import ModelCache
 from invokeai.backend.model_manager.load.model_loader_registry import ModelLoaderRegistry, ModelLoaderRegistryBase
 
 # This registers the subclasses that implement loaders of specific model types

invokeai/backend/model_manager/load/load_base.py

@@ -5,6 +5,7 @@ Base class for model loading in InvokeAI.
 
 from abc import ABC, abstractmethod
 from contextlib import contextmanager
+from dataclasses import dataclass
 from logging import Logger
 from pathlib import Path
 from typing import Any, Dict, Generator, Optional, Tuple
@@ -17,17 +18,19 @@ from invokeai.backend.model_manager.config import (
     AnyModelConfig,
     SubModelType,
 )
-from invokeai.backend.model_manager.load.model_cache.cache_record import CacheRecord
-from invokeai.backend.model_manager.load.model_cache.model_cache import ModelCache
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase, ModelLockerBase
 
 
+@dataclass
 class LoadedModelWithoutConfig:
-    """Context manager object that mediates transfer from RAM<->VRAM.
+    """
+    Context manager object that mediates transfer from RAM<->VRAM.
 
     This is a context manager object that has two distinct APIs:
 
     1. Older API (deprecated):
-    Use the LoadedModel object directly as a context manager.  It will move the model into VRAM (on CUDA devices), and
+    Use the LoadedModel object directly as a context manager.
+    It will move the model into VRAM (on CUDA devices), and
     return the model in a form suitable for passing to torch.
     Example:
     ```
@@ -37,9 +40,13 @@ class LoadedModelWithoutConfig:
     ```
 
     2. Newer API (recommended):
-    Call the LoadedModel's `model_on_device()` method in a context. It returns a tuple consisting of a copy of the
-    model's state dict in CPU RAM followed by a copy of the model in VRAM. The state dict is provided to allow LoRAs and
-    other model patchers to return the model to its unpatched state without expensive copy and restore operations.
+    Call the LoadedModel's `model_on_device()` method in a
+    context. It returns a tuple consisting of a copy of
+    the model's state dict in CPU RAM followed by a copy
+    of the model in VRAM. The state dict is provided to allow
+    LoRAs and other model patchers to return the model to
+    its unpatched state without expensive copy and restore
+    operations.
 
     Example:
     ```
@@ -48,42 +55,43 @@ class LoadedModelWithoutConfig:
         image = vae.decode(latents)[0]
     ```
 
-    The state_dict should be treated as a read-only object and never modified. Also be aware that some loadable models
-    do not have a state_dict, in which case this value will be None.
+    The state_dict should be treated as a read-only object and
+    never modified. Also be aware that some loadable models do
+    not have a state_dict, in which case this value will be None.
     """
 
-    def __init__(self, cache_record: CacheRecord, cache: ModelCache):
-        self._cache_record = cache_record
-        self._cache = cache
+    _locker: ModelLockerBase
 
     def __enter__(self) -> AnyModel:
-        self._cache.lock(self._cache_record.key)
+        """Context entry."""
+        self._locker.lock()
         return self.model
 
     def __exit__(self, *args: Any, **kwargs: Any) -> None:
-        self._cache.unlock(self._cache_record.key)
+        """Context exit."""
+        self._locker.unlock()
 
     @contextmanager
     def model_on_device(self) -> Generator[Tuple[Optional[Dict[str, torch.Tensor]], AnyModel], None, None]:
         """Return a tuple consisting of the model's state dict (if it exists) and the locked model on execution device."""
-        self._cache.lock(self._cache_record.key)
+        locked_model = self._locker.lock()
         try:
-            yield (self._cache_record.cached_model.get_cpu_state_dict(), self._cache_record.cached_model.model)
+            state_dict = self._locker.get_state_dict()
+            yield (state_dict, locked_model)
         finally:
-            self._cache.unlock(self._cache_record.key)
+            self._locker.unlock()
 
     @property
     def model(self) -> AnyModel:
         """Return the model without locking it."""
-        return self._cache_record.cached_model.model
+        return self._locker.model
 
 
+@dataclass
 class LoadedModel(LoadedModelWithoutConfig):
     """Context manager object that mediates transfer from RAM<->VRAM."""
 
-    def __init__(self, config: Optional[AnyModelConfig], cache_record: CacheRecord, cache: ModelCache):
-        super().__init__(cache_record=cache_record, cache=cache)
-        self.config = config
+    config: Optional[AnyModelConfig] = None
 
 
 # TODO(MM2):
@@ -102,7 +110,7 @@ class ModelLoaderBase(ABC):
         self,
         app_config: InvokeAIAppConfig,
         logger: Logger,
-        ram_cache: ModelCache,
+        ram_cache: ModelCacheBase[AnyModel],
     ):
         """Initialize the loader."""
         pass
@@ -130,6 +138,6 @@ class ModelLoaderBase(ABC):
 
     @property
     @abstractmethod
-    def ram_cache(self) -> ModelCache:
+    def ram_cache(self) -> ModelCacheBase[AnyModel]:
         """Return the ram cache associated with this loader."""
         pass

invokeai/backend/model_manager/load/load_default.py

@@ -14,8 +14,7 @@ from invokeai.backend.model_manager import (
 )
 from invokeai.backend.model_manager.config import DiffusersConfigBase
 from invokeai.backend.model_manager.load.load_base import LoadedModel, ModelLoaderBase
-from invokeai.backend.model_manager.load.model_cache.cache_record import CacheRecord
-from invokeai.backend.model_manager.load.model_cache.model_cache import ModelCache, get_model_cache_key
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase, ModelLockerBase
 from invokeai.backend.model_manager.load.model_util import calc_model_size_by_fs
 from invokeai.backend.model_manager.load.optimizations import skip_torch_weight_init
 from invokeai.backend.util.devices import TorchDevice
@@ -29,14 +28,13 @@ class ModelLoader(ModelLoaderBase):
         self,
         app_config: InvokeAIAppConfig,
         logger: Logger,
-        ram_cache: ModelCache,
+        ram_cache: ModelCacheBase[AnyModel],
     ):
         """Initialize the loader."""
         self._app_config = app_config
         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:
         """
@@ -55,11 +53,11 @@ class ModelLoader(ModelLoaderBase):
             raise InvalidModelConfigException(f"Files for model '{model_config.name}' not found at {model_path}")
 
         with skip_torch_weight_init():
-            cache_record = self._load_and_cache(model_config, submodel_type)
-        return LoadedModel(config=model_config, cache_record=cache_record, cache=self._ram_cache)
+            locker = self._load_and_cache(model_config, submodel_type)
+        return LoadedModel(config=model_config, _locker=locker)
 
     @property
-    def ram_cache(self) -> ModelCache:
+    def ram_cache(self) -> ModelCacheBase[AnyModel]:
         """Return the ram cache associated with this loader."""
         return self._ram_cache
 
@@ -67,10 +65,10 @@ class ModelLoader(ModelLoaderBase):
         model_base = self._app_config.models_path
         return (model_base / config.path).resolve()
 
-    def _load_and_cache(self, config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> CacheRecord:
+    def _load_and_cache(self, config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> ModelLockerBase:
         stats_name = ":".join([config.base, config.type, config.name, (submodel_type or "")])
         try:
-            return self._ram_cache.get(key=get_model_cache_key(config.key, submodel_type), stats_name=stats_name)
+            return self._ram_cache.get(config.key, submodel_type, stats_name=stats_name)
         except IndexError:
             pass
 
@@ -79,11 +77,16 @@ class ModelLoader(ModelLoaderBase):
         loaded_model = self._load_model(config, submodel_type)
 
         self._ram_cache.put(
-            get_model_cache_key(config.key, submodel_type),
+            config.key,
+            submodel_type=submodel_type,
             model=loaded_model,
         )
 
-        return self._ram_cache.get(key=get_model_cache_key(config.key, submodel_type), stats_name=stats_name)
+        return self._ram_cache.get(
+            key=config.key,
+            submodel_type=submodel_type,
+            stats_name=stats_name,
+        )
 
     def get_size_fs(
         self, config: AnyModelConfig, model_path: Path, submodel_type: Optional[SubModelType] = None

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

@@ -0,0 +1,6 @@
+"""Init file for ModelCache."""
+
+from .model_cache_base import ModelCacheBase, CacheStats  # noqa F401
+from .model_cache_default import ModelCache  # noqa F401
+
+_all__ = ["ModelCacheBase", "ModelCache", "CacheStats"]

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

@@ -1,31 +0,0 @@
-from dataclasses import dataclass
-
-from invokeai.backend.model_manager.load.model_cache.cached_model.cached_model_only_full_load import (
-    CachedModelOnlyFullLoad,
-)
-from invokeai.backend.model_manager.load.model_cache.cached_model.cached_model_with_partial_load import (
-    CachedModelWithPartialLoad,
-)
-
-
-@dataclass
-class CacheRecord:
-    """A class that represents a model in the model cache."""
-
-    # Cache key.
-    key: str
-    # Model in memory.
-    cached_model: CachedModelWithPartialLoad | CachedModelOnlyFullLoad
-    # If locks > 0, the model is actively being used, so we should do our best to keep it on the compute device.
-    _locks: int = 0
-
-    def lock(self) -> None:
-        self._locks += 1
-
-    def unlock(self) -> None:
-        self._locks -= 1
-        assert self._locks >= 0
-
-    @property
-    def is_locked(self) -> bool:
-        return self._locks > 0

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

@@ -1,15 +0,0 @@
-from dataclasses import dataclass, field
-from typing import Dict
-
-
-@dataclass
-class CacheStats(object):
-    """Collect statistics on cache performance."""
-
-    hits: int = 0  # cache hits
-    misses: int = 0  # cache misses
-    high_watermark: int = 0  # amount of cache used
-    in_cache: int = 0  # number of models in cache
-    cleared: int = 0  # number of models cleared to make space
-    cache_size: int = 0  # total size of cache
-    loaded_model_sizes: Dict[str, int] = field(default_factory=dict)

invokeai/backend/model_manager/load/model_cache/cached_model/cached_model_only_full_load.py

@@ -1,81 +0,0 @@
-from typing import Any
-
-import torch
-
-
-class CachedModelOnlyFullLoad:
-    """A wrapper around a PyTorch model to handle full loads and unloads between the CPU and the compute device.
-
-    Note: "VRAM" is used throughout this class to refer to the memory on the compute device. It could be CUDA memory,
-    MPS memory, etc.
-    """
-
-    def __init__(self, model: torch.nn.Module | Any, compute_device: torch.device, total_bytes: int):
-        """Initialize a CachedModelOnlyFullLoad.
-
-        Args:
-            model (torch.nn.Module | Any): The model to wrap. Should be on the CPU.
-            compute_device (torch.device): The compute device to move the model to.
-            total_bytes (int): The total size (in bytes) of all the weights in the model.
-        """
-        # model is often a torch.nn.Module, but could be any model type. Throughout this class, we handle both cases.
-        self._model = model
-        self._compute_device = compute_device
-        self._total_bytes = total_bytes
-        self._is_in_vram = False
-
-    @property
-    def model(self) -> torch.nn.Module:
-        return self._model
-
-    def get_cpu_state_dict(self) -> dict[str, torch.Tensor] | None:
-        """Get a read-only copy of the model's state dict in RAM."""
-        # TODO(ryand): Document this better and implement it.
-        return None
-
-    def total_bytes(self) -> int:
-        """Get the total size (in bytes) of all the weights in the model."""
-        return self._total_bytes
-
-    def cur_vram_bytes(self) -> int:
-        """Get the size (in bytes) of the weights that are currently in VRAM."""
-        if self._is_in_vram:
-            return self._total_bytes
-        else:
-            return 0
-
-    def is_in_vram(self) -> bool:
-        """Return true if the model is currently in VRAM."""
-        return self._is_in_vram
-
-    def full_load_to_vram(self) -> int:
-        """Load all weights into VRAM (if supported by the model).
-
-        Returns:
-            The number of bytes loaded into VRAM.
-        """
-        if self._is_in_vram:
-            # Already in VRAM.
-            return 0
-
-        if not hasattr(self._model, "to"):
-            # Model doesn't support moving to a device.
-            return 0
-
-        self._model.to(self._compute_device)
-        self._is_in_vram = True
-        return self._total_bytes
-
-    def full_unload_from_vram(self) -> int:
-        """Unload all weights from VRAM.
-
-        Returns:
-            The number of bytes unloaded from VRAM.
-        """
-        if not self._is_in_vram:
-            # Already in RAM.
-            return 0
-
-        self._model.to("cpu")
-        self._is_in_vram = False
-        return self._total_bytes

invokeai/backend/model_manager/load/model_cache/cached_model/cached_model_with_partial_load.py

@@ -1,139 +0,0 @@
-import torch
-
-from invokeai.backend.model_manager.load.model_cache.torch_function_autocast_context import (
-    add_autocast_to_module_forward,
-)
-from invokeai.backend.util.calc_tensor_size import calc_tensor_size
-
-
-def set_nested_attr(obj: object, attr: str, value: object):
-    """A helper function that extends setattr() to support nested attributes.
-
-    Example:
-        set_nested_attr(model, "module.encoder.conv1.weight", new_conv1_weight)
-    """
-    attrs = attr.split(".")
-    for attr in attrs[:-1]:
-        obj = getattr(obj, attr)
-    setattr(obj, attrs[-1], value)
-
-
-class CachedModelWithPartialLoad:
-    """A wrapper around a PyTorch model to handle partial loads and unloads between the CPU and the compute device.
-
-    Note: "VRAM" is used throughout this class to refer to the memory on the compute device. It could be CUDA memory,
-    MPS memory, etc.
-    """
-
-    def __init__(self, model: torch.nn.Module, compute_device: torch.device):
-        self._model = model
-        self._compute_device = compute_device
-
-        # A CPU read-only copy of the model's state dict.
-        self._cpu_state_dict: dict[str, torch.Tensor] = model.state_dict()
-
-        # Monkey-patch the model to add autocasting to the model's forward method.
-        add_autocast_to_module_forward(model, compute_device)
-
-        # TODO(ryand): Manage a read-only CPU copy of the model state dict.
-        # TODO(ryand): Add memoization for total_bytes and cur_vram_bytes?
-
-        self._total_bytes = sum(calc_tensor_size(p) for p in self._model.parameters())
-        self._cur_vram_bytes: int | None = None
-
-    @property
-    def model(self) -> torch.nn.Module:
-        return self._model
-
-    def get_cpu_state_dict(self) -> dict[str, torch.Tensor] | None:
-        """Get a read-only copy of the model's state dict in RAM."""
-        # TODO(ryand): Document this better.
-        return self._cpu_state_dict
-
-    def total_bytes(self) -> int:
-        """Get the total size (in bytes) of all the weights in the model."""
-        return self._total_bytes
-
-    def cur_vram_bytes(self) -> int:
-        """Get the size (in bytes) of the weights that are currently in VRAM."""
-        if self._cur_vram_bytes is None:
-            self._cur_vram_bytes = sum(
-                calc_tensor_size(p) for p in self._model.parameters() if p.device.type == self._compute_device.type
-            )
-        return self._cur_vram_bytes
-
-    def full_load_to_vram(self) -> int:
-        """Load all weights into VRAM."""
-        return self.partial_load_to_vram(self.total_bytes())
-
-    def full_unload_from_vram(self) -> int:
-        """Unload all weights from VRAM."""
-        return self.partial_unload_from_vram(self.total_bytes())
-
-    @torch.no_grad()
-    def partial_load_to_vram(self, vram_bytes_to_load: int) -> int:
-        """Load more weights into VRAM without exceeding vram_bytes_to_load.
-
-        Returns:
-            The number of bytes loaded into VRAM.
-        """
-        vram_bytes_loaded = 0
-
-        # TODO(ryand): Iterate over buffers too?
-        for key, param in self._model.named_parameters():
-            # Skip parameters that are already on the compute device.
-            if param.device.type == self._compute_device.type:
-                continue
-
-            # Check the size of the parameter.
-            param_size = calc_tensor_size(param)
-            if vram_bytes_loaded + param_size > vram_bytes_to_load:
-                # TODO(ryand): Should we just break here? If we couldn't fit this parameter into VRAM, is it really
-                # worth continuing to search for a smaller parameter that would fit?
-                continue
-
-            # Copy the parameter to the compute device.
-            # We use the 'overwrite' strategy from torch.nn.Module._apply().
-            # TODO(ryand): For some edge cases (e.g. quantized models?), we may need to support other strategies (e.g.
-            # swap).
-            assert isinstance(param, torch.nn.Parameter)
-            assert param.is_leaf
-            out_param = torch.nn.Parameter(param.to(self._compute_device, copy=True), requires_grad=param.requires_grad)
-            set_nested_attr(self._model, key, out_param)
-            # We did not port the param.grad handling from torch.nn.Module._apply(), because we do not expect to be
-            # handling gradients. We assert that this assumption is true.
-            assert param.grad is None
-
-            vram_bytes_loaded += param_size
-
-        if self._cur_vram_bytes is not None:
-            self._cur_vram_bytes += vram_bytes_loaded
-
-        return vram_bytes_loaded
-
-    @torch.no_grad()
-    def partial_unload_from_vram(self, vram_bytes_to_free: int) -> int:
-        """Unload weights from VRAM until vram_bytes_to_free bytes are freed. Or the entire model is unloaded.
-
-        Returns:
-            The number of bytes unloaded from VRAM.
-        """
-        vram_bytes_freed = 0
-
-        # TODO(ryand): Iterate over buffers too?
-        for key, param in self._model.named_parameters():
-            if vram_bytes_freed >= vram_bytes_to_free:
-                break
-
-            if param.device.type != self._compute_device.type:
-                continue
-
-            # Create a new parameter, but inject the existing CPU tensor into it.
-            out_param = torch.nn.Parameter(self._cpu_state_dict[key], requires_grad=param.requires_grad)
-            set_nested_attr(self._model, key, out_param)
-            vram_bytes_freed += calc_tensor_size(param)
-
-        if self._cur_vram_bytes is not None:
-            self._cur_vram_bytes -= vram_bytes_freed
-
-        return vram_bytes_freed

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

@@ -1,534 +0,0 @@
-import gc
-from logging import Logger
-from typing import Dict, List, Optional
-
-import torch
-
-from invokeai.backend.model_manager import AnyModel, SubModelType
-from invokeai.backend.model_manager.load.memory_snapshot import MemorySnapshot
-from invokeai.backend.model_manager.load.model_cache.cache_record import CacheRecord
-from invokeai.backend.model_manager.load.model_cache.cache_stats import CacheStats
-from invokeai.backend.model_manager.load.model_cache.cached_model.cached_model_only_full_load import (
-    CachedModelOnlyFullLoad,
-)
-from invokeai.backend.model_manager.load.model_cache.cached_model.cached_model_with_partial_load import (
-    CachedModelWithPartialLoad,
-)
-from invokeai.backend.model_manager.load.model_util import calc_model_size_by_data
-from invokeai.backend.util.devices import TorchDevice
-from invokeai.backend.util.logging import InvokeAILogger
-from invokeai.backend.util.prefix_logger_adapter import PrefixedLoggerAdapter
-
-# Size of a GB in bytes.
-GB = 2**30
-
-# Size of a MB in bytes.
-MB = 2**20
-
-
-# TODO(ryand): Where should this go? The ModelCache shouldn't be concerned with submodels.
-def get_model_cache_key(model_key: str, submodel_type: Optional[SubModelType] = None) -> str:
-    """Get the cache key for a model based on the optional submodel type."""
-    if submodel_type:
-        return f"{model_key}:{submodel_type.value}"
-    else:
-        return model_key
-
-
-class ModelCache:
-    """A cache for managing models in memory.
-
-    The cache is based on two levels of model storage:
-    - execution_device: The device where most models are executed (typically "cuda", "mps", or "cpu").
-    - storage_device: The device where models are offloaded when not in active use (typically "cpu").
-
-    The model cache is based on the following assumptions:
-    - storage_device_mem_size > execution_device_mem_size
-    - disk_to_storage_device_transfer_time >> storage_device_to_execution_device_transfer_time
-
-    A copy of all models in the cache is always kept on the storage_device. A subset of the models also have a copy on
-    the execution_device.
-
-    Models are moved between the storage_device and the execution_device as necessary. Cache size limits are enforced
-    on both the storage_device and the execution_device. The execution_device cache uses a smallest-first offload
-    policy. The storage_device cache uses a least-recently-used (LRU) offload policy.
-
-    Note: Neither of these offload policies has really been compared against alternatives. It's likely that different
-    policies would be better, although the optimal policies are likely heavily dependent on usage patterns and HW
-    configuration.
-
-    The cache returns context manager generators designed to load the model into the execution device (often GPU) within
-    the context, and unload outside the context.
-
-    Example usage:
-    ```
-    cache = ModelCache(max_cache_size=7.5, max_vram_cache_size=6.0)
-    with cache.get_model('runwayml/stable-diffusion-1-5') as SD1:
-        do_something_on_gpu(SD1)
-    ```
-    """
-
-    def __init__(
-        self,
-        max_cache_size: float,
-        max_vram_cache_size: float,
-        execution_device: torch.device = torch.device("cuda"),
-        storage_device: torch.device = torch.device("cpu"),
-        lazy_offloading: bool = True,
-        log_memory_usage: bool = False,
-        logger: Optional[Logger] = None,
-    ):
-        """
-        Initialize the model RAM cache.
-
-        :param max_cache_size: Maximum size of the storage_device cache in GBs.
-        :param max_vram_cache_size: Maximum size of the execution_device cache in GBs.
-        :param execution_device: Torch device to load active model into [torch.device('cuda')]
-        :param storage_device: Torch device to save inactive model in [torch.device('cpu')]
-        :param lazy_offloading: Keep model in VRAM until another model needs to be loaded
-        :param log_memory_usage: If True, a memory snapshot will be captured before and after every model cache
-            operation, and the result will be logged (at debug level). There is a time cost to capturing the memory
-            snapshots, so it is recommended to disable this feature unless you are actively inspecting the model cache's
-            behaviour.
-        :param logger: InvokeAILogger to use (otherwise creates one)
-        """
-        # allow lazy offloading only when vram cache enabled
-        # TODO(ryand): Think about what lazy_offloading should mean in the new model cache.
-        self._lazy_offloading = lazy_offloading and max_vram_cache_size > 0
-        self._max_cache_size: float = max_cache_size
-        self._max_vram_cache_size: float = max_vram_cache_size
-        self._execution_device: torch.device = execution_device
-        self._storage_device: torch.device = storage_device
-        self._logger = PrefixedLoggerAdapter(
-            logger or InvokeAILogger.get_logger(self.__class__.__name__), "MODEL CACHE"
-        )
-        self._log_memory_usage = log_memory_usage
-        self._stats: Optional[CacheStats] = None
-
-        self._cached_models: Dict[str, CacheRecord] = {}
-        self._cache_stack: List[str] = []
-
-    @property
-    def max_cache_size(self) -> float:
-        """Return the cap on cache size."""
-        return self._max_cache_size
-
-    @max_cache_size.setter
-    def max_cache_size(self, value: float) -> None:
-        """Set the cap on cache size."""
-        self._max_cache_size = value
-
-    @property
-    def max_vram_cache_size(self) -> float:
-        """Return the cap on vram cache size."""
-        return self._max_vram_cache_size
-
-    @max_vram_cache_size.setter
-    def max_vram_cache_size(self, value: float) -> None:
-        """Set the cap on vram cache size."""
-        self._max_vram_cache_size = value
-
-    @property
-    def stats(self) -> Optional[CacheStats]:
-        """Return collected CacheStats object."""
-        return self._stats
-
-    @stats.setter
-    def stats(self, stats: CacheStats) -> None:
-        """Set the CacheStats object for collecting cache statistics."""
-        self._stats = stats
-
-    def put(self, key: str, model: AnyModel) -> None:
-        """Add a model to the cache."""
-        if key in self._cached_models:
-            self._logger.debug(
-                f"Attempted to add model {key} ({model.__class__.__name__}), but it already exists in the cache. No action necessary."
-            )
-            return
-
-        size = calc_model_size_by_data(self._logger, model)
-        self.make_room(size)
-
-        # Wrap model.
-        if isinstance(model, torch.nn.Module):
-            wrapped_model = CachedModelWithPartialLoad(model, self._execution_device)
-        else:
-            wrapped_model = CachedModelOnlyFullLoad(model, self._execution_device, size)
-
-        # running_on_cpu = self._execution_device == torch.device("cpu")
-        # state_dict = model.state_dict() if isinstance(model, torch.nn.Module) and not running_on_cpu else None
-        cache_record = CacheRecord(key=key, cached_model=wrapped_model)
-        self._cached_models[key] = cache_record
-        self._cache_stack.append(key)
-        self._logger.debug(
-            f"Added model {key} (Type: {model.__class__.__name__}, Wrap mode: {wrapped_model.__class__.__name__}, Model size: {size/MB:.2f}MB)"
-        )
-
-    def get(self, key: str, stats_name: Optional[str] = None) -> CacheRecord:
-        """Retrieve a model from the cache.
-
-        :param key: Model key
-        :param stats_name: A human-readable id for the model for the purposes of stats reporting.
-
-        Raises IndexError if the model is not in the cache.
-        """
-        if key in self._cached_models:
-            if self.stats:
-                self.stats.hits += 1
-        else:
-            if self.stats:
-                self.stats.misses += 1
-            self._logger.debug(f"Cache miss: {key}")
-            raise IndexError(f"The model with key {key} is not in the cache.")
-
-        cache_entry = self._cached_models[key]
-
-        # more stats
-        if self.stats:
-            stats_name = stats_name or key
-            self.stats.cache_size = int(self._max_cache_size * GB)
-            self.stats.high_watermark = max(self.stats.high_watermark, self._get_ram_in_use())
-            self.stats.in_cache = len(self._cached_models)
-            self.stats.loaded_model_sizes[stats_name] = max(
-                self.stats.loaded_model_sizes.get(stats_name, 0), cache_entry.cached_model.total_bytes()
-            )
-
-        # this moves the entry to the top (right end) of the stack
-        self._cache_stack = [k for k in self._cache_stack if k != key]
-        self._cache_stack.append(key)
-
-        self._logger.debug(f"Cache hit: {key} (Type: {cache_entry.cached_model.model.__class__.__name__})")
-
-        return cache_entry
-
-    def lock(self, key: str) -> None:
-        """Lock a model for use and move it into VRAM."""
-        cache_entry = self._cached_models[key]
-        cache_entry.lock()
-
-        self._logger.debug(f"Locking model {key} (Type: {cache_entry.cached_model.model.__class__.__name__})")
-
-        try:
-            self._load_locked_model(cache_entry)
-            self._logger.debug(
-                f"Finished locking model {key} (Type: {cache_entry.cached_model.model.__class__.__name__})"
-            )
-        except torch.cuda.OutOfMemoryError:
-            self._logger.warning("Insufficient GPU memory to load model. Aborting")
-            cache_entry.unlock()
-            raise
-        except Exception:
-            cache_entry.unlock()
-            raise
-
-        self._log_cache_state()
-
-    def unlock(self, key: str) -> None:
-        """Unlock a model."""
-        cache_entry = self._cached_models[key]
-        cache_entry.unlock()
-        self._logger.debug(f"Unlocked model {key} (Type: {cache_entry.cached_model.model.__class__.__name__})")
-
-    def _load_locked_model(self, cache_entry: CacheRecord) -> None:
-        """Helper function for self.lock(). Loads a locked model into VRAM."""
-        vram_available = self._get_vram_available()
-
-        # The amount of additional VRAM that will be used if we fully load the model into VRAM.
-        model_cur_vram_bytes = cache_entry.cached_model.cur_vram_bytes()
-        model_total_bytes = cache_entry.cached_model.total_bytes()
-        model_vram_needed = model_total_bytes - model_cur_vram_bytes
-
-        self._logger.debug(
-            f"Before unloading: {self._get_vram_state_str(model_cur_vram_bytes, model_total_bytes, vram_available)}"
-        )
-
-        # Make room for the model in VRAM.
-        # 1. If the model can fit entirely in VRAM, then make enough room for it to be loaded fully.
-        # 2. If the model can't fit fully into VRAM, then unload all other models and load as much of the model as
-        #    possible.
-        vram_bytes_freed = self._offload_unlocked_models(model_vram_needed)
-        self._logger.debug(f"Unloaded models (if necessary): vram_bytes_freed={(vram_bytes_freed/MB):.2f}MB")
-
-        # Check the updated vram_available after offloading.
-        vram_available = self._get_vram_available()
-        self._logger.debug(
-            f"After unloading: {self._get_vram_state_str(model_cur_vram_bytes, model_total_bytes, vram_available)}"
-        )
-
-        # Move as much of the model as possible into VRAM.
-        model_bytes_loaded = 0
-        if isinstance(cache_entry.cached_model, CachedModelWithPartialLoad):
-            model_bytes_loaded = cache_entry.cached_model.partial_load_to_vram(vram_available)
-        elif isinstance(cache_entry.cached_model, CachedModelOnlyFullLoad):  # type: ignore
-            # Partial load is not supported, so we have not choice but to try and fit it all into VRAM.
-            model_bytes_loaded = cache_entry.cached_model.full_load_to_vram()
-        else:
-            raise ValueError(f"Unsupported cached model type: {type(cache_entry.cached_model)}")
-
-        model_cur_vram_bytes = cache_entry.cached_model.cur_vram_bytes()
-        vram_available = self._get_vram_available()
-        self._logger.debug(f"Loaded model onto execution device: model_bytes_loaded={(model_bytes_loaded/MB):.2f}MB, ")
-        self._logger.debug(
-            f"After loading: {self._get_vram_state_str(model_cur_vram_bytes, model_total_bytes, vram_available)}"
-        )
-
-    def _get_vram_available(self) -> int:
-        """Get the amount of VRAM available in the cache."""
-        return int(self._max_vram_cache_size * GB) - self._get_vram_in_use()
-
-    def _get_vram_in_use(self) -> int:
-        """Get the amount of VRAM currently in use."""
-        return sum(ce.cached_model.cur_vram_bytes() for ce in self._cached_models.values())
-
-    def _get_ram_available(self) -> int:
-        """Get the amount of RAM available in the cache."""
-        return int(self._max_cache_size * GB) - self._get_ram_in_use()
-
-    def _get_ram_in_use(self) -> int:
-        """Get the amount of RAM currently in use."""
-        return sum(ce.cached_model.total_bytes() for ce in self._cached_models.values())
-
-    def _capture_memory_snapshot(self) -> Optional[MemorySnapshot]:
-        if self._log_memory_usage:
-            return MemorySnapshot.capture()
-        return None
-
-    def _get_vram_state_str(self, model_cur_vram_bytes: int, model_total_bytes: int, vram_available: int) -> str:
-        """Helper function for preparing a VRAM state log string."""
-        model_cur_vram_bytes_percent = model_cur_vram_bytes / model_total_bytes if model_total_bytes > 0 else 0
-        return (
-            f"model_total={model_total_bytes/MB:.0f} MB, "
-            + f"model_vram={model_cur_vram_bytes/MB:.0f} MB ({model_cur_vram_bytes_percent:.1%} %), "
-            + f"vram_total={int(self._max_vram_cache_size * GB)/MB:.0f} MB, "
-            + f"vram_available={(vram_available/MB):.0f} MB, "
-        )
-
-    def _offload_unlocked_models(self, vram_bytes_to_free: int) -> int:
-        """Offload models from the execution_device until vram_bytes_to_free bytes are freed, or all models are
-        offloaded. Of course, locked models are not offloaded.
-
-        Returns:
-            int: The number of bytes freed.
-        """
-        self._logger.debug(f"Offloading unlocked models with goal of freeing {vram_bytes_to_free/MB:.2f}MB of VRAM.")
-        vram_bytes_freed = 0
-        # TODO(ryand): Give more thought to the offloading policy used here.
-        cache_entries_increasing_size = sorted(self._cached_models.values(), key=lambda x: x.cached_model.total_bytes())
-        for cache_entry in cache_entries_increasing_size:
-            if vram_bytes_freed >= vram_bytes_to_free:
-                break
-            if cache_entry.is_locked:
-                continue
-
-            if isinstance(cache_entry.cached_model, CachedModelWithPartialLoad):
-                cache_entry_bytes_freed = cache_entry.cached_model.partial_unload_from_vram(
-                    vram_bytes_to_free - vram_bytes_freed
-                )
-            elif isinstance(cache_entry.cached_model, CachedModelOnlyFullLoad):  # type: ignore
-                cache_entry_bytes_freed = cache_entry.cached_model.full_unload_from_vram()
-            else:
-                raise ValueError(f"Unsupported cached model type: {type(cache_entry.cached_model)}")
-            if cache_entry_bytes_freed > 0:
-                self._logger.debug(
-                    f"Unloaded {cache_entry.key} from VRAM to free {(cache_entry_bytes_freed/MB):.0f} MB."
-                )
-            vram_bytes_freed += cache_entry_bytes_freed
-
-        TorchDevice.empty_cache()
-        return vram_bytes_freed
-
-    # def _move_model_to_device(self, cache_entry: CacheRecord, target_device: torch.device) -> None:
-    #     """Move model into the indicated device.
-
-    #     :param cache_entry: The CacheRecord for the model
-    #     :param target_device: The torch.device to move the model into
-
-    #     May raise a torch.cuda.OutOfMemoryError
-    #     """
-    #     self._logger.debug(f"Called to move {cache_entry.key} to {target_device}")
-    #     source_device = cache_entry.device
-
-    #     # Note: We compare device types only so that 'cuda' == 'cuda:0'.
-    #     # This would need to be revised to support multi-GPU.
-    #     if torch.device(source_device).type == torch.device(target_device).type:
-    #         return
-
-    #     # Some models don't have a `to` method, in which case they run in RAM/CPU.
-    #     if not hasattr(cache_entry.model, "to"):
-    #         return
-
-    #     # This roundabout method for moving the model around is done to avoid
-    #     # the cost of moving the model from RAM to VRAM and then back from VRAM to RAM.
-    #     # When moving to VRAM, we copy (not move) each element of the state dict from
-    #     # RAM to a new state dict in VRAM, and then inject it into the model.
-    #     # This operation is slightly faster than running `to()` on the whole model.
-    #     #
-    #     # When the model needs to be removed from VRAM we simply delete the copy
-    #     # of the state dict in VRAM, and reinject the state dict that is cached
-    #     # in RAM into the model. So this operation is very fast.
-    #     start_model_to_time = time.time()
-    #     snapshot_before = self._capture_memory_snapshot()
-
-    #     try:
-    #         if cache_entry.state_dict is not None:
-    #             assert hasattr(cache_entry.model, "load_state_dict")
-    #             if target_device == self._storage_device:
-    #                 cache_entry.model.load_state_dict(cache_entry.state_dict, assign=True)
-    #             else:
-    #                 new_dict: Dict[str, torch.Tensor] = {}
-    #                 for k, v in cache_entry.state_dict.items():
-    #                     new_dict[k] = v.to(target_device, copy=True)
-    #                 cache_entry.model.load_state_dict(new_dict, assign=True)
-    #         cache_entry.model.to(target_device)
-    #         cache_entry.device = target_device
-    #     except Exception as e:  # blow away cache entry
-    #         self._delete_cache_entry(cache_entry)
-    #         raise e
-
-    #     snapshot_after = self._capture_memory_snapshot()
-    #     end_model_to_time = time.time()
-    #     self._logger.debug(
-    #         f"Moved model '{cache_entry.key}' from {source_device} to"
-    #         f" {target_device} in {(end_model_to_time-start_model_to_time):.2f}s."
-    #         f"Estimated model size: {(cache_entry.size/GB):.3f} GB."
-    #         f"{get_pretty_snapshot_diff(snapshot_before, snapshot_after)}"
-    #     )
-
-    #     if (
-    #         snapshot_before is not None
-    #         and snapshot_after is not None
-    #         and snapshot_before.vram is not None
-    #         and snapshot_after.vram is not None
-    #     ):
-    #         vram_change = abs(snapshot_before.vram - snapshot_after.vram)
-
-    #         # If the estimated model size does not match the change in VRAM, log a warning.
-    #         if not math.isclose(
-    #             vram_change,
-    #             cache_entry.size,
-    #             rel_tol=0.1,
-    #             abs_tol=10 * MB,
-    #         ):
-    #             self._logger.debug(
-    #                 f"Moving model '{cache_entry.key}' from {source_device} to"
-    #                 f" {target_device} caused an unexpected change in VRAM usage. The model's"
-    #                 " estimated size may be incorrect. Estimated model size:"
-    #                 f" {(cache_entry.size/GB):.3f} GB.\n"
-    #                 f"{get_pretty_snapshot_diff(snapshot_before, snapshot_after)}"
-    #             )
-
-    def _log_cache_state(self, title: str = "Model cache state:", include_entry_details: bool = True):
-        ram_size_bytes = self._max_cache_size * GB
-        ram_in_use_bytes = self._get_ram_in_use()
-        ram_in_use_bytes_percent = ram_in_use_bytes / ram_size_bytes if ram_size_bytes > 0 else 0
-        ram_available_bytes = self._get_ram_available()
-        ram_available_bytes_percent = ram_available_bytes / ram_size_bytes if ram_size_bytes > 0 else 0
-
-        vram_size_bytes = self._max_vram_cache_size * GB
-        vram_in_use_bytes = self._get_vram_in_use()
-        vram_in_use_bytes_percent = vram_in_use_bytes / vram_size_bytes if vram_size_bytes > 0 else 0
-        vram_available_bytes = self._get_vram_available()
-        vram_available_bytes_percent = vram_available_bytes / vram_size_bytes if vram_size_bytes > 0 else 0
-
-        log = f"{title}\n"
-
-        log_format = "  {:<30} Limit: {:>7.1f} MB, Used: {:>7.1f} MB ({:>5.1%}), Available: {:>7.1f} MB ({:>5.1%})\n"
-        log += log_format.format(
-            f"Storage Device ({self._storage_device.type})",
-            ram_size_bytes / MB,
-            ram_in_use_bytes / MB,
-            ram_in_use_bytes_percent,
-            ram_available_bytes / MB,
-            ram_available_bytes_percent,
-        )
-        log += log_format.format(
-            f"Compute Device ({self._execution_device.type})",
-            vram_size_bytes / MB,
-            vram_in_use_bytes / MB,
-            vram_in_use_bytes_percent,
-            vram_available_bytes / MB,
-            vram_available_bytes_percent,
-        )
-
-        if torch.cuda.is_available():
-            log += "  {:<30} {} MB\n".format("CUDA Memory Allocated:", torch.cuda.memory_allocated() / MB)
-        log += "  {:<30} {}\n".format("Total models:", len(self._cached_models))
-
-        if include_entry_details and len(self._cached_models) > 0:
-            log += "  Models:\n"
-            log_format = (
-                "    {:<80} total={:>7.1f} MB, vram={:>7.1f} MB ({:>5.1%}), ram={:>7.1f} MB ({:>5.1%}), locked={}\n"
-            )
-            for cache_record in self._cached_models.values():
-                total_bytes = cache_record.cached_model.total_bytes()
-                cur_vram_bytes = cache_record.cached_model.cur_vram_bytes()
-                cur_vram_bytes_percent = cur_vram_bytes / total_bytes if total_bytes > 0 else 0
-                cur_ram_bytes = total_bytes - cur_vram_bytes
-                cur_ram_bytes_percent = cur_ram_bytes / total_bytes if total_bytes > 0 else 0
-
-                log += log_format.format(
-                    f"{cache_record.key} ({cache_record.cached_model.model.__class__.__name__}):",
-                    total_bytes / MB,
-                    cur_vram_bytes / MB,
-                    cur_vram_bytes_percent,
-                    cur_ram_bytes / MB,
-                    cur_ram_bytes_percent,
-                    cache_record.is_locked,
-                )
-
-        self._logger.debug(log)
-
-    def make_room(self, bytes_needed: int) -> None:
-        """Make enough room in the cache to accommodate a new model of indicated size.
-
-        Note: This function deletes all of the cache's internal references to a model in order to free it. If there are
-        external references to the model, there's nothing that the cache can do about it, and those models will not be
-        garbage-collected.
-        """
-        self._logger.debug(f"Making room for {bytes_needed/MB:.2f}MB of RAM.")
-        self._log_cache_state(title="Before dropping models:")
-
-        ram_bytes_available = self._get_ram_available()
-        ram_bytes_to_free = max(0, bytes_needed - ram_bytes_available)
-
-        ram_bytes_freed = 0
-        pos = 0
-        models_cleared = 0
-        while ram_bytes_freed < ram_bytes_to_free and pos < len(self._cache_stack):
-            model_key = self._cache_stack[pos]
-            cache_entry = self._cached_models[model_key]
-
-            if not cache_entry.is_locked:
-                ram_bytes_freed += cache_entry.cached_model.total_bytes()
-                self._logger.debug(
-                    f"Dropping {model_key} from RAM cache to free {(cache_entry.cached_model.total_bytes()/MB):.2f}MB."
-                )
-                self._delete_cache_entry(cache_entry)
-                del cache_entry
-                models_cleared += 1
-            else:
-                pos += 1
-
-        if models_cleared > 0:
-            # There would likely be some 'garbage' to be collected regardless of whether a model was cleared or not, but
-            # there is a significant time cost to calling `gc.collect()`, so we want to use it sparingly. (The time cost
-            # is high even if no garbage gets collected.)
-            #
-            # Calling gc.collect(...) when a model is cleared seems like a good middle-ground:
-            # - If models had to be cleared, it's a signal that we are close to our memory limit.
-            # - If models were cleared, there's a good chance that there's a significant amount of garbage to be
-            #   collected.
-            #
-            # Keep in mind that gc is only responsible for handling reference cycles. Most objects should be cleaned up
-            # immediately when their reference count hits 0.
-            if self.stats:
-                self.stats.cleared = models_cleared
-            gc.collect()
-
-        TorchDevice.empty_cache()
-        self._logger.debug(f"Dropped {models_cleared} models to free {ram_bytes_freed/MB:.2f}MB of RAM.")
-        self._log_cache_state(title="After dropping models:")
-
-    def _delete_cache_entry(self, cache_entry: CacheRecord) -> None:
-        self._cache_stack.remove(cache_entry.key)
-        del self._cached_models[cache_entry.key]

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

@@ -0,0 +1,221 @@
+# Copyright (c) 2024 Lincoln D. Stein and the InvokeAI Development team
+# TODO: Add Stalker's proper name to copyright
+"""
+Manage a RAM cache of diffusion/transformer models for fast switching.
+They are moved between GPU VRAM and CPU RAM as necessary. If the cache
+grows larger than a preset maximum, then the least recently used
+model will be cleared and (re)loaded from disk when next needed.
+"""
+
+from abc import ABC, abstractmethod
+from dataclasses import dataclass, field
+from logging import Logger
+from typing import Dict, Generic, Optional, TypeVar
+
+import torch
+
+from invokeai.backend.model_manager.config import AnyModel, SubModelType
+
+
+class ModelLockerBase(ABC):
+    """Base class for the model locker used by the loader."""
+
+    @abstractmethod
+    def lock(self) -> AnyModel:
+        """Lock the contained model and move it into VRAM."""
+        pass
+
+    @abstractmethod
+    def unlock(self) -> None:
+        """Unlock the contained model, and remove it from VRAM."""
+        pass
+
+    @abstractmethod
+    def get_state_dict(self) -> Optional[Dict[str, torch.Tensor]]:
+        """Return the state dict (if any) for the cached model."""
+        pass
+
+    @property
+    @abstractmethod
+    def model(self) -> AnyModel:
+        """Return the model."""
+        pass
+
+
+T = TypeVar("T")
+
+
+@dataclass
+class CacheRecord(Generic[T]):
+    """
+    Elements of the cache:
+
+    key: Unique key for each model, same as used in the models database.
+    model: Model in memory.
+    state_dict: A read-only copy of the model's state dict in RAM. It will be
+                used as a template for creating a copy in the VRAM.
+    size: Size of the model
+    loaded: True if the model's state dict is currently in VRAM
+
+    Before a model is executed, the state_dict template is copied into VRAM,
+    and then injected into the model. When the model is finished, the VRAM
+    copy of the state dict is deleted, and the RAM version is reinjected
+    into the model.
+
+    The state_dict should be treated as a read-only attribute. Do not attempt
+    to patch or otherwise modify it. Instead, patch the copy of the state_dict
+    after it is loaded into the execution device (e.g. CUDA) using the `LoadedModel`
+    context manager call `model_on_device()`.
+    """
+
+    key: str
+    model: T
+    device: torch.device
+    state_dict: Optional[Dict[str, torch.Tensor]]
+    size: int
+    loaded: bool = False
+    _locks: int = 0
+
+    def lock(self) -> None:
+        """Lock this record."""
+        self._locks += 1
+
+    def unlock(self) -> None:
+        """Unlock this record."""
+        self._locks -= 1
+        assert self._locks >= 0
+
+    @property
+    def locked(self) -> bool:
+        """Return true if record is locked."""
+        return self._locks > 0
+
+
+@dataclass
+class CacheStats(object):
+    """Collect statistics on cache performance."""
+
+    hits: int = 0  # cache hits
+    misses: int = 0  # cache misses
+    high_watermark: int = 0  # amount of cache used
+    in_cache: int = 0  # number of models in cache
+    cleared: int = 0  # number of models cleared to make space
+    cache_size: int = 0  # total size of cache
+    loaded_model_sizes: Dict[str, int] = field(default_factory=dict)
+
+
+class ModelCacheBase(ABC, Generic[T]):
+    """Virtual base class for RAM model cache."""
+
+    @property
+    @abstractmethod
+    def storage_device(self) -> torch.device:
+        """Return the storage device (e.g. "CPU" for RAM)."""
+        pass
+
+    @property
+    @abstractmethod
+    def execution_device(self) -> torch.device:
+        """Return the exection device (e.g. "cuda" for VRAM)."""
+        pass
+
+    @property
+    @abstractmethod
+    def lazy_offloading(self) -> bool:
+        """Return true if the cache is configured to lazily offload models in VRAM."""
+        pass
+
+    @property
+    @abstractmethod
+    def max_cache_size(self) -> float:
+        """Return the maximum size the RAM cache can grow to."""
+        pass
+
+    @max_cache_size.setter
+    @abstractmethod
+    def max_cache_size(self, value: float) -> None:
+        """Set the cap on vram cache size."""
+
+    @property
+    @abstractmethod
+    def max_vram_cache_size(self) -> float:
+        """Return the maximum size the VRAM cache can grow to."""
+        pass
+
+    @max_vram_cache_size.setter
+    @abstractmethod
+    def max_vram_cache_size(self, value: float) -> float:
+        """Set the maximum size the VRAM cache can grow to."""
+        pass
+
+    @abstractmethod
+    def offload_unlocked_models(self, size_required: int) -> None:
+        """Offload from VRAM any models not actively in use."""
+        pass
+
+    @abstractmethod
+    def move_model_to_device(self, cache_entry: CacheRecord[AnyModel], target_device: torch.device) -> None:
+        """Move model into the indicated device."""
+        pass
+
+    @property
+    @abstractmethod
+    def stats(self) -> Optional[CacheStats]:
+        """Return collected CacheStats object."""
+        pass
+
+    @stats.setter
+    @abstractmethod
+    def stats(self, stats: CacheStats) -> None:
+        """Set the CacheStats object for collectin cache statistics."""
+        pass
+
+    @property
+    @abstractmethod
+    def logger(self) -> Logger:
+        """Return the logger used by the cache."""
+        pass
+
+    @abstractmethod
+    def make_room(self, size: int) -> None:
+        """Make enough room in the cache to accommodate a new model of indicated size."""
+        pass
+
+    @abstractmethod
+    def put(
+        self,
+        key: str,
+        model: T,
+        submodel_type: Optional[SubModelType] = None,
+    ) -> None:
+        """Store model under key and optional submodel_type."""
+        pass
+
+    @abstractmethod
+    def get(
+        self,
+        key: str,
+        submodel_type: Optional[SubModelType] = None,
+        stats_name: Optional[str] = None,
+    ) -> ModelLockerBase:
+        """
+        Retrieve model using key and optional submodel_type.
+
+        :param key: Opaque model key
+        :param submodel_type: Type of the submodel to fetch
+        :param stats_name: A human-readable id for the model for the purposes of
+        stats reporting.
+
+        This may raise an IndexError if the model is not in the cache.
+        """
+        pass
+
+    @abstractmethod
+    def cache_size(self) -> int:
+        """Get the total size of the models currently cached."""
+        pass
+
+    @abstractmethod
+    def print_cuda_stats(self) -> None:
+        """Log debugging information on CUDA usage."""
+        pass

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

@@ -0,0 +1,426 @@
+# Copyright (c) 2024 Lincoln D. Stein and the InvokeAI Development team
+# TODO: Add Stalker's proper name to copyright
+""" """
+
+import gc
+import math
+import time
+from contextlib import suppress
+from logging import Logger
+from typing import Dict, List, Optional
+
+import torch
+
+from invokeai.backend.model_manager import AnyModel, SubModelType
+from invokeai.backend.model_manager.load.memory_snapshot import MemorySnapshot, get_pretty_snapshot_diff
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import (
+    CacheRecord,
+    CacheStats,
+    ModelCacheBase,
+    ModelLockerBase,
+)
+from invokeai.backend.model_manager.load.model_cache.model_locker import ModelLocker
+from invokeai.backend.model_manager.load.model_util import calc_model_size_by_data
+from invokeai.backend.util.devices import TorchDevice
+from invokeai.backend.util.logging import InvokeAILogger
+
+# Size of a GB in bytes.
+GB = 2**30
+
+# Size of a MB in bytes.
+MB = 2**20
+
+
+class ModelCache(ModelCacheBase[AnyModel]):
+    """A cache for managing models in memory.
+
+    The cache is based on two levels of model storage:
+    - execution_device: The device where most models are executed (typically "cuda", "mps", or "cpu").
+    - storage_device: The device where models are offloaded when not in active use (typically "cpu").
+
+    The model cache is based on the following assumptions:
+    - storage_device_mem_size > execution_device_mem_size
+    - disk_to_storage_device_transfer_time >> storage_device_to_execution_device_transfer_time
+
+    A copy of all models in the cache is always kept on the storage_device. A subset of the models also have a copy on
+    the execution_device.
+
+    Models are moved between the storage_device and the execution_device as necessary. Cache size limits are enforced
+    on both the storage_device and the execution_device. The execution_device cache uses a smallest-first offload
+    policy. The storage_device cache uses a least-recently-used (LRU) offload policy.
+
+    Note: Neither of these offload policies has really been compared against alternatives. It's likely that different
+    policies would be better, although the optimal policies are likely heavily dependent on usage patterns and HW
+    configuration.
+
+    The cache returns context manager generators designed to load the model into the execution device (often GPU) within
+    the context, and unload outside the context.
+
+    Example usage:
+    ```
+    cache = ModelCache(max_cache_size=7.5, max_vram_cache_size=6.0)
+    with cache.get_model('runwayml/stable-diffusion-1-5') as SD1:
+        do_something_on_gpu(SD1)
+    ```
+    """
+
+    def __init__(
+        self,
+        max_cache_size: float,
+        max_vram_cache_size: float,
+        execution_device: torch.device = torch.device("cuda"),
+        storage_device: torch.device = torch.device("cpu"),
+        precision: torch.dtype = torch.float16,
+        lazy_offloading: bool = True,
+        log_memory_usage: bool = False,
+        logger: Optional[Logger] = None,
+    ):
+        """
+        Initialize the model RAM cache.
+
+        :param max_cache_size: Maximum size of the storage_device cache in GBs.
+        :param max_vram_cache_size: Maximum size of the execution_device cache in GBs.
+        :param execution_device: Torch device to load active model into [torch.device('cuda')]
+        :param storage_device: Torch device to save inactive model in [torch.device('cpu')]
+        :param precision: Precision for loaded models [torch.float16]
+        :param lazy_offloading: Keep model in VRAM until another model needs to be loaded
+        :param log_memory_usage: If True, a memory snapshot will be captured before and after every model cache
+            operation, and the result will be logged (at debug level). There is a time cost to capturing the memory
+            snapshots, so it is recommended to disable this feature unless you are actively inspecting the model cache's
+            behaviour.
+        :param logger: InvokeAILogger to use (otherwise creates one)
+        """
+        # allow lazy offloading only when vram cache enabled
+        self._lazy_offloading = lazy_offloading and max_vram_cache_size > 0
+        self._max_cache_size: float = max_cache_size
+        self._max_vram_cache_size: float = max_vram_cache_size
+        self._execution_device: torch.device = execution_device
+        self._storage_device: torch.device = storage_device
+        self._logger = logger or InvokeAILogger.get_logger(self.__class__.__name__)
+        self._log_memory_usage = log_memory_usage
+        self._stats: Optional[CacheStats] = None
+
+        self._cached_models: Dict[str, CacheRecord[AnyModel]] = {}
+        self._cache_stack: List[str] = []
+
+    @property
+    def logger(self) -> Logger:
+        """Return the logger used by the cache."""
+        return self._logger
+
+    @property
+    def lazy_offloading(self) -> bool:
+        """Return true if the cache is configured to lazily offload models in VRAM."""
+        return self._lazy_offloading
+
+    @property
+    def storage_device(self) -> torch.device:
+        """Return the storage device (e.g. "CPU" for RAM)."""
+        return self._storage_device
+
+    @property
+    def execution_device(self) -> torch.device:
+        """Return the exection device (e.g. "cuda" for VRAM)."""
+        return self._execution_device
+
+    @property
+    def max_cache_size(self) -> float:
+        """Return the cap on cache size."""
+        return self._max_cache_size
+
+    @max_cache_size.setter
+    def max_cache_size(self, value: float) -> None:
+        """Set the cap on cache size."""
+        self._max_cache_size = value
+
+    @property
+    def max_vram_cache_size(self) -> float:
+        """Return the cap on vram cache size."""
+        return self._max_vram_cache_size
+
+    @max_vram_cache_size.setter
+    def max_vram_cache_size(self, value: float) -> None:
+        """Set the cap on vram cache size."""
+        self._max_vram_cache_size = value
+
+    @property
+    def stats(self) -> Optional[CacheStats]:
+        """Return collected CacheStats object."""
+        return self._stats
+
+    @stats.setter
+    def stats(self, stats: CacheStats) -> None:
+        """Set the CacheStats object for collectin cache statistics."""
+        self._stats = stats
+
+    def cache_size(self) -> int:
+        """Get the total size of the models currently cached."""
+        total = 0
+        for cache_record in self._cached_models.values():
+            total += cache_record.size
+        return total
+
+    def put(
+        self,
+        key: str,
+        model: AnyModel,
+        submodel_type: Optional[SubModelType] = None,
+    ) -> None:
+        """Store model under key and optional submodel_type."""
+        key = self._make_cache_key(key, submodel_type)
+        if key in self._cached_models:
+            return
+        size = calc_model_size_by_data(self.logger, model)
+        self.make_room(size)
+
+        running_on_cpu = self.execution_device == torch.device("cpu")
+        state_dict = model.state_dict() if isinstance(model, torch.nn.Module) and not running_on_cpu else None
+        cache_record = CacheRecord(key=key, model=model, device=self.storage_device, state_dict=state_dict, size=size)
+        self._cached_models[key] = cache_record
+        self._cache_stack.append(key)
+
+    def get(
+        self,
+        key: str,
+        submodel_type: Optional[SubModelType] = None,
+        stats_name: Optional[str] = None,
+    ) -> ModelLockerBase:
+        """
+        Retrieve model using key and optional submodel_type.
+
+        :param key: Opaque model key
+        :param submodel_type: Type of the submodel to fetch
+        :param stats_name: A human-readable id for the model for the purposes of
+        stats reporting.
+
+        This may raise an IndexError if the model is not in the cache.
+        """
+        key = self._make_cache_key(key, submodel_type)
+        if key in self._cached_models:
+            if self.stats:
+                self.stats.hits += 1
+        else:
+            if self.stats:
+                self.stats.misses += 1
+            raise IndexError(f"The model with key {key} is not in the cache.")
+
+        cache_entry = self._cached_models[key]
+
+        # more stats
+        if self.stats:
+            stats_name = stats_name or key
+            self.stats.cache_size = int(self._max_cache_size * GB)
+            self.stats.high_watermark = max(self.stats.high_watermark, self.cache_size())
+            self.stats.in_cache = len(self._cached_models)
+            self.stats.loaded_model_sizes[stats_name] = max(
+                self.stats.loaded_model_sizes.get(stats_name, 0), cache_entry.size
+            )
+
+        # this moves the entry to the top (right end) of the stack
+        with suppress(Exception):
+            self._cache_stack.remove(key)
+        self._cache_stack.append(key)
+        return ModelLocker(
+            cache=self,
+            cache_entry=cache_entry,
+        )
+
+    def _capture_memory_snapshot(self) -> Optional[MemorySnapshot]:
+        if self._log_memory_usage:
+            return MemorySnapshot.capture()
+        return None
+
+    def _make_cache_key(self, model_key: str, submodel_type: Optional[SubModelType] = None) -> str:
+        if submodel_type:
+            return f"{model_key}:{submodel_type.value}"
+        else:
+            return model_key
+
+    def offload_unlocked_models(self, size_required: int) -> None:
+        """Offload models from the execution_device to make room for size_required.
+
+        :param size_required: The amount of space to clear in the execution_device cache, in bytes.
+        """
+        reserved = self._max_vram_cache_size * GB
+        vram_in_use = torch.cuda.memory_allocated() + size_required
+        self.logger.debug(f"{(vram_in_use/GB):.2f}GB VRAM needed for models; max allowed={(reserved/GB):.2f}GB")
+        for _, cache_entry in sorted(self._cached_models.items(), key=lambda x: x[1].size):
+            if vram_in_use <= reserved:
+                break
+            if not cache_entry.loaded:
+                continue
+            if not cache_entry.locked:
+                self.move_model_to_device(cache_entry, self.storage_device)
+                cache_entry.loaded = False
+                vram_in_use = torch.cuda.memory_allocated() + size_required
+                self.logger.debug(
+                    f"Removing {cache_entry.key} from VRAM to free {(cache_entry.size/GB):.2f}GB; vram free = {(torch.cuda.memory_allocated()/GB):.2f}GB"
+                )
+
+        TorchDevice.empty_cache()
+
+    def move_model_to_device(self, cache_entry: CacheRecord[AnyModel], target_device: torch.device) -> None:
+        """Move model into the indicated device.
+
+        :param cache_entry: The CacheRecord for the model
+        :param target_device: The torch.device to move the model into
+
+        May raise a torch.cuda.OutOfMemoryError
+        """
+        self.logger.debug(f"Called to move {cache_entry.key} to {target_device}")
+        source_device = cache_entry.device
+
+        # Note: We compare device types only so that 'cuda' == 'cuda:0'.
+        # This would need to be revised to support multi-GPU.
+        if torch.device(source_device).type == torch.device(target_device).type:
+            return
+
+        # Some models don't have a `to` method, in which case they run in RAM/CPU.
+        if not hasattr(cache_entry.model, "to"):
+            return
+
+        # This roundabout method for moving the model around is done to avoid
+        # the cost of moving the model from RAM to VRAM and then back from VRAM to RAM.
+        # When moving to VRAM, we copy (not move) each element of the state dict from
+        # RAM to a new state dict in VRAM, and then inject it into the model.
+        # This operation is slightly faster than running `to()` on the whole model.
+        #
+        # When the model needs to be removed from VRAM we simply delete the copy
+        # of the state dict in VRAM, and reinject the state dict that is cached
+        # in RAM into the model. So this operation is very fast.
+        start_model_to_time = time.time()
+        snapshot_before = self._capture_memory_snapshot()
+
+        try:
+            if cache_entry.state_dict is not None:
+                assert hasattr(cache_entry.model, "load_state_dict")
+                if target_device == self.storage_device:
+                    cache_entry.model.load_state_dict(cache_entry.state_dict, assign=True)
+                else:
+                    new_dict: Dict[str, torch.Tensor] = {}
+                    for k, v in cache_entry.state_dict.items():
+                        new_dict[k] = v.to(target_device, copy=True)
+                    cache_entry.model.load_state_dict(new_dict, assign=True)
+            cache_entry.model.to(target_device)
+            cache_entry.device = target_device
+        except Exception as e:  # blow away cache entry
+            self._delete_cache_entry(cache_entry)
+            raise e
+
+        snapshot_after = self._capture_memory_snapshot()
+        end_model_to_time = time.time()
+        self.logger.debug(
+            f"Moved model '{cache_entry.key}' from {source_device} to"
+            f" {target_device} in {(end_model_to_time-start_model_to_time):.2f}s."
+            f"Estimated model size: {(cache_entry.size/GB):.3f} GB."
+            f"{get_pretty_snapshot_diff(snapshot_before, snapshot_after)}"
+        )
+
+        if (
+            snapshot_before is not None
+            and snapshot_after is not None
+            and snapshot_before.vram is not None
+            and snapshot_after.vram is not None
+        ):
+            vram_change = abs(snapshot_before.vram - snapshot_after.vram)
+
+            # If the estimated model size does not match the change in VRAM, log a warning.
+            if not math.isclose(
+                vram_change,
+                cache_entry.size,
+                rel_tol=0.1,
+                abs_tol=10 * MB,
+            ):
+                self.logger.debug(
+                    f"Moving model '{cache_entry.key}' from {source_device} to"
+                    f" {target_device} caused an unexpected change in VRAM usage. The model's"
+                    " estimated size may be incorrect. Estimated model size:"
+                    f" {(cache_entry.size/GB):.3f} GB.\n"
+                    f"{get_pretty_snapshot_diff(snapshot_before, snapshot_after)}"
+                )
+
+    def print_cuda_stats(self) -> None:
+        """Log CUDA diagnostics."""
+        vram = "%4.2fG" % (torch.cuda.memory_allocated() / GB)
+        ram = "%4.2fG" % (self.cache_size() / GB)
+
+        in_ram_models = 0
+        in_vram_models = 0
+        locked_in_vram_models = 0
+        for cache_record in self._cached_models.values():
+            if hasattr(cache_record.model, "device"):
+                if cache_record.model.device == self.storage_device:
+                    in_ram_models += 1
+                else:
+                    in_vram_models += 1
+                if cache_record.locked:
+                    locked_in_vram_models += 1
+
+                self.logger.debug(
+                    f"Current VRAM/RAM usage: {vram}/{ram}; models_in_ram/models_in_vram(locked) ="
+                    f" {in_ram_models}/{in_vram_models}({locked_in_vram_models})"
+                )
+
+    def make_room(self, size: int) -> None:
+        """Make enough room in the cache to accommodate a new model of indicated size.
+
+        Note: This function deletes all of the cache's internal references to a model in order to free it. If there are
+        external references to the model, there's nothing that the cache can do about it, and those models will not be
+        garbage-collected.
+        """
+        bytes_needed = size
+        maximum_size = self.max_cache_size * GB  # stored in GB, convert to bytes
+        current_size = self.cache_size()
+
+        if current_size + bytes_needed > maximum_size:
+            self.logger.debug(
+                f"Max cache size exceeded: {(current_size/GB):.2f}/{self.max_cache_size:.2f} GB, need an additional"
+                f" {(bytes_needed/GB):.2f} GB"
+            )
+
+        self.logger.debug(f"Before making_room: cached_models={len(self._cached_models)}")
+
+        pos = 0
+        models_cleared = 0
+        while current_size + bytes_needed > maximum_size and pos < len(self._cache_stack):
+            model_key = self._cache_stack[pos]
+            cache_entry = self._cached_models[model_key]
+            device = cache_entry.model.device if hasattr(cache_entry.model, "device") else None
+            self.logger.debug(
+                f"Model: {model_key}, locks: {cache_entry._locks}, device: {device}, loaded: {cache_entry.loaded}"
+            )
+
+            if not cache_entry.locked:
+                self.logger.debug(
+                    f"Removing {model_key} from RAM cache to free at least {(size/GB):.2f} GB (-{(cache_entry.size/GB):.2f} GB)"
+                )
+                current_size -= cache_entry.size
+                models_cleared += 1
+                self._delete_cache_entry(cache_entry)
+                del cache_entry
+
+            else:
+                pos += 1
+
+        if models_cleared > 0:
+            # There would likely be some 'garbage' to be collected regardless of whether a model was cleared or not, but
+            # there is a significant time cost to calling `gc.collect()`, so we want to use it sparingly. (The time cost
+            # is high even if no garbage gets collected.)
+            #
+            # Calling gc.collect(...) when a model is cleared seems like a good middle-ground:
+            # - If models had to be cleared, it's a signal that we are close to our memory limit.
+            # - If models were cleared, there's a good chance that there's a significant amount of garbage to be
+            #   collected.
+            #
+            # Keep in mind that gc is only responsible for handling reference cycles. Most objects should be cleaned up
+            # immediately when their reference count hits 0.
+            if self.stats:
+                self.stats.cleared = models_cleared
+            gc.collect()
+
+        TorchDevice.empty_cache()
+        self.logger.debug(f"After making room: cached_models={len(self._cached_models)}")
+
+    def _delete_cache_entry(self, cache_entry: CacheRecord[AnyModel]) -> None:
+        self._cache_stack.remove(cache_entry.key)
+        del self._cached_models[cache_entry.key]

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

@@ -0,0 +1,64 @@
+"""
+Base class and implementation of a class that moves models in and out of VRAM.
+"""
+
+from typing import Dict, Optional
+
+import torch
+
+from invokeai.backend.model_manager import AnyModel
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import (
+    CacheRecord,
+    ModelCacheBase,
+    ModelLockerBase,
+)
+
+
+class ModelLocker(ModelLockerBase):
+    """Internal class that mediates movement in and out of GPU."""
+
+    def __init__(self, cache: ModelCacheBase[AnyModel], cache_entry: CacheRecord[AnyModel]):
+        """
+        Initialize the model locker.
+
+        :param cache: The ModelCache object
+        :param cache_entry: The entry in the model cache
+        """
+        self._cache = cache
+        self._cache_entry = cache_entry
+
+    @property
+    def model(self) -> AnyModel:
+        """Return the model without moving it around."""
+        return self._cache_entry.model
+
+    def get_state_dict(self) -> Optional[Dict[str, torch.Tensor]]:
+        """Return the state dict (if any) for the cached model."""
+        return self._cache_entry.state_dict
+
+    def lock(self) -> AnyModel:
+        """Move the model into the execution device (GPU) and lock it."""
+        self._cache_entry.lock()
+        try:
+            if self._cache.lazy_offloading:
+                self._cache.offload_unlocked_models(self._cache_entry.size)
+            self._cache.move_model_to_device(self._cache_entry, self._cache.execution_device)
+            self._cache_entry.loaded = True
+            self._cache.logger.debug(f"Locking {self._cache_entry.key} in {self._cache.execution_device}")
+            self._cache.print_cuda_stats()
+        except torch.cuda.OutOfMemoryError:
+            self._cache.logger.warning("Insufficient GPU memory to load model. Aborting")
+            self._cache_entry.unlock()
+            raise
+        except Exception:
+            self._cache_entry.unlock()
+            raise
+
+        return self.model
+
+    def unlock(self) -> None:
+        """Call upon exit from context."""
+        self._cache_entry.unlock()
+        if not self._cache.lazy_offloading:
+            self._cache.offload_unlocked_models(0)
+            self._cache.print_cuda_stats()

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

@@ -1,33 +0,0 @@
-from typing import Any, Callable
-
-import torch
-from torch.overrides import TorchFunctionMode
-
-
-def add_autocast_to_module_forward(m: torch.nn.Module, to_device: torch.device):
-    """Monkey-patch m.forward(...) with a new forward(...) method that activates device autocasting for its duration."""
-    old_forward = m.forward
-
-    def new_forward(*args: Any, **kwargs: Any):
-        with TorchFunctionAutocastDeviceContext(to_device):
-            return old_forward(*args, **kwargs)
-
-    m.forward = new_forward
-
-
-def _cast_to_device_and_run(
-    func: Callable[..., Any], args: tuple[Any, ...], kwargs: dict[str, Any], to_device: torch.device
-):
-    args_on_device = [a.to(to_device) if isinstance(a, torch.Tensor) else a for a in args]
-    kwargs_on_device = {k: v.to(to_device) if isinstance(v, torch.Tensor) else v for k, v in kwargs.items()}
-    return func(*args_on_device, **kwargs_on_device)
-
-
-class TorchFunctionAutocastDeviceContext(TorchFunctionMode):
-    def __init__(self, to_device: torch.device):
-        self._to_device = to_device
-
-    def __torch_function__(
-        self, func: Callable[..., Any], types, args: tuple[Any, ...] = (), kwargs: dict[str, Any] | None = None
-    ):
-        return _cast_to_device_and_run(func, args, kwargs or {}, self._to_device)

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

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

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

@@ -26,7 +26,7 @@ from invokeai.backend.model_manager import (
     SubModelType,
 )
 from invokeai.backend.model_manager.load.load_default import ModelLoader
-from invokeai.backend.model_manager.load.model_cache.model_cache import ModelCache
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
 from invokeai.backend.model_manager.load.model_loader_registry import ModelLoaderRegistry
 
 
@@ -40,7 +40,7 @@ class LoRALoader(ModelLoader):
         self,
         app_config: InvokeAIAppConfig,
         logger: Logger,
-        ram_cache: ModelCache,
+        ram_cache: ModelCacheBase[AnyModel],
     ):
         """Initialize the loader."""
         super().__init__(app_config, logger, ram_cache)

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

@@ -25,7 +25,6 @@ from invokeai.backend.model_manager.config import (
     DiffusersConfigBase,
     MainCheckpointConfig,
 )
-from invokeai.backend.model_manager.load.model_cache.model_cache import get_model_cache_key
 from invokeai.backend.model_manager.load.model_loader_registry import ModelLoaderRegistry
 from invokeai.backend.model_manager.load.model_loaders.generic_diffusers import GenericDiffusersLoader
 from invokeai.backend.util.silence_warnings import SilenceWarnings
@@ -43,7 +42,6 @@ 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)
@@ -53,6 +51,13 @@ 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,
@@ -133,5 +138,5 @@ class StableDiffusionDiffusersModel(GenericDiffusersLoader):
             if subtype == submodel_type:
                 continue
             if submodel := getattr(pipeline, subtype.value, None):
-                self._ram_cache.put(get_model_cache_key(config.key, subtype), model=submodel)
+                self._ram_cache.put(config.key, submodel_type=subtype, model=submodel)
         return getattr(pipeline, submodel_type.value)

invokeai/backend/model_manager/probe.py

@@ -1,7 +1,7 @@
 import json
 import re
 from pathlib import Path
-from typing import Any, Callable, Dict, Literal, Optional, Union
+from typing import Any, Dict, Literal, Optional, Union
 
 import safetensors.torch
 import spandrel
@@ -22,7 +22,6 @@ 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,
@@ -34,15 +33,8 @@ 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.spandrel_image_to_image_model import SpandrelImageToImageModel
@@ -120,7 +112,6 @@ class ModelProbe(object):
         "StableDiffusionXLPipeline": ModelType.Main,
         "StableDiffusionXLImg2ImgPipeline": ModelType.Main,
         "StableDiffusionXLInpaintPipeline": ModelType.Main,
-        "StableDiffusion3Pipeline": ModelType.Main,
         "LatentConsistencyModelPipeline": ModelType.Main,
         "AutoencoderKL": ModelType.VAE,
         "AutoencoderTiny": ModelType.VAE,
@@ -131,12 +122,8 @@ class ModelProbe(object):
         "CLIPTextModel": 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]
@@ -183,10 +170,7 @@ 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()
-        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["variant"] = fields.get("variant") 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)
@@ -233,10 +217,6 @@ 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
 
@@ -469,7 +449,7 @@ class ModelProbe(object):
         """
         # scan model
         scan_result = scan_file_path(checkpoint)
-        if scan_result.infected_files != 0 or scan_result.scan_err:
+        if scan_result.infected_files != 0:
             raise Exception("The model {model_name} is potentially infected by malware. Aborting import.")
 
 
@@ -485,7 +465,6 @@ MODEL_NAME_TO_PREPROCESSOR = {
     "lineart anime": "lineart_anime_image_processor",
     "lineart_anime": "lineart_anime_image_processor",
     "lineart": "lineart_image_processor",
-    "soft": "hed_image_processor",
     "softedge": "hed_image_processor",
     "hed": "hed_image_processor",
     "shuffle": "content_shuffle_image_processor",
@@ -768,33 +747,18 @@ class FolderProbeBase(ProbeBase):
 
 class PipelineFolderProbe(FolderProbeBase):
     def get_base_type(self) -> BaseModelType:
-        # 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}")
+        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}")
 
     def get_scheduler_prediction_type(self) -> SchedulerPredictionType:
         with open(self.model_path / "scheduler" / "scheduler_config.json", "r") as file:
@@ -806,23 +770,6 @@ 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

@@ -140,22 +140,6 @@ 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,
@@ -298,12 +282,13 @@ ip_adapter_sdxl = StarterModel(
     previous_names=["IP Adapter SDXL"],
 )
 ip_adapter_flux = StarterModel(
-    name="Standard Reference (XLabs FLUX IP-Adapter v2)",
+    name="Standard Reference (XLabs FLUX IP-Adapter)",
     base=BaseModelType.Flux,
-    source="https://huggingface.co/XLabs-AI/flux-ip-adapter-v2/resolve/main/ip_adapter.safetensors",
+    source="https://huggingface.co/XLabs-AI/flux-ip-adapter/resolve/main/flux-ip-adapter.safetensors",
     description="References images with a more generalized/looser degree of precision.",
     type=ModelType.IPAdapter,
     dependencies=[clip_vit_l_image_encoder],
+    previous_names=["XLabs FLUX IP-Adapter"],
 )
 # endregion
 # region ControlNet
@@ -585,8 +570,6 @@ STARTER_MODELS: list[StarterModel] = [
     flux_dev_quantized,
     flux_schnell,
     flux_dev,
-    sd35_medium,
-    sd35_large,
     cyberrealistic_sd1,
     rev_animated_sd1,
     dreamshaper_8_sd1,

invokeai/backend/model_manager/util/model_util.py

@@ -8,7 +8,6 @@ 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
 
 
@@ -44,7 +43,7 @@ def _fast_safetensors_reader(path: str) -> Dict[str, torch.Tensor]:
     return checkpoint
 
 
-def read_checkpoint_meta(path: Union[str, Path], scan: bool = True) -> Dict[str, torch.Tensor]:
+def read_checkpoint_meta(path: Union[str, Path], scan: bool = False) -> Dict[str, torch.Tensor]:
     if str(path).endswith(".safetensors"):
         try:
             path_str = path.as_posix() if isinstance(path, Path) else path
@@ -55,7 +54,7 @@ def read_checkpoint_meta(path: Union[str, Path], scan: bool = True) -> Dict[str,
     else:
         if scan:
             scan_result = scan_file_path(path)
-            if scan_result.infected_files != 0 or scan_result.scan_err:
+            if scan_result.infected_files != 0:
                 raise Exception(f'The model file "{path}" is potentially infected by malware. Aborting import.')
         if str(path).endswith(".gguf"):
             # The GGUF reader used here uses numpy memmap, so these tensors are not loaded into memory during this function
@@ -166,25 +165,3 @@ 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

@@ -85,7 +85,6 @@ 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:
@@ -120,27 +119,19 @@ 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 (
-                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]):
+            if candidate_variant_label == f".{variant}" or (
+                not candidate_variant_label and variant in [ModelRepoVariant.FP32, ModelRepoVariant.Default]
+            ):
                 score += 1
 
             if parent not in subfolder_weights:
@@ -155,7 +146,7 @@ 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].startswith(".fp16"):
+            if len(candidate.path.suffixes) == 2 and candidate.path.suffixes[0] == ".fp16":
                 at_least_one_fp16 = True
                 break
 
@@ -171,16 +162,7 @@ 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:
-            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)
+            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

@@ -1,58 +0,0 @@
-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/stable_diffusion/diffusers_pipeline.py

@@ -499,22 +499,6 @@ 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

@@ -49,32 +49,9 @@ 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]
-        | List[SD3ConditioningInfo]
-    )
+    conditionings: List[BasicConditioningInfo] | List[SDXLConditioningInfo] | List[FLUXConditioningInfo]
 
 
 @dataclass

invokeai/backend/util/prefix_logger_adapter.py

@@ -1,12 +0,0 @@
-import logging
-from typing import Any, MutableMapping
-
-
-# Issue with type hints related to LoggerAdapter: https://github.com/python/typeshed/issues/7855
-class PrefixedLoggerAdapter(logging.LoggerAdapter):  # type: ignore
-    def __init__(self, logger: logging.Logger, prefix: str):
-        super().__init__(logger, {})
-        self.prefix = prefix
-
-    def process(self, msg: str, kwargs: MutableMapping[str, Any]) -> tuple[str, MutableMapping[str, Any]]:
-        return f"[{self.prefix}] {msg}", kwargs

invokeai/frontend/web/knip.ts

@@ -9,7 +9,6 @@ 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": "^0.0.44",
+    "@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: ^0.0.44
-    version: 0.0.44(@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)
@@ -319,28 +319,6 @@ 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'}
@@ -515,8 +493,8 @@ packages:
     resolution: {integrity: sha512-MV6D4VLRIHr4PkW4zMyqfrNS1mPlCTiCXwvYGtDFQYr+xHFfonhAuf9WjsSc0nyp2m0OdkSLnzmVKkZFLo25Tg==}
     dev: false
 
-  /@chakra-ui/anatomy@2.3.5:
-    resolution: {integrity: sha512-3im33cUOxCbISjaBlINE2u8BOwJSCdzpjCX0H+0JxK2xz26UaVA5xeI3NYHUoxDnr/QIrgfrllGxS0szYwOcyg==}
+  /@chakra-ui/anatomy@2.3.4:
+    resolution: {integrity: sha512-fFIYN7L276gw0Q7/ikMMlZxP7mvnjRaWJ7f3Jsf9VtDOi6eAYIBRrhQe6+SZ0PGmoOkRaBc7gSE5oeIbgFFyrw==}
     dev: false
 
   /@chakra-ui/breakpoint-utils@2.0.8:
@@ -573,12 +551,12 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/hooks@2.4.3(react@18.3.1):
-    resolution: {integrity: sha512-Sr2zsoTZw3p7HbrUy4aLpTIkE2XXUelAUgg3NGwMzrmx75bE0qVyiuuTFOuyEzGxYVV2Fe8QtcKKilm6RwzTGg==}
+  /@chakra-ui/hooks@2.4.2(react@18.3.1):
+    resolution: {integrity: sha512-LRKiVE1oA7afT5tbbSKAy7Uas2xFHE6IkrQdbhWCHmkHBUtPvjQQDgwtnd4IRZPmoEfNGwoJ/MQpwOM/NRTTwA==}
     peerDependencies:
       react: '>=18'
     dependencies:
-      '@chakra-ui/utils': 2.2.3(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
       '@zag-js/element-size': 0.31.1
       copy-to-clipboard: 3.3.3
       framesync: 6.1.2
@@ -596,13 +574,13 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/icons@2.2.4(@chakra-ui/react@2.10.4)(react@18.3.1):
+  /@chakra-ui/icons@2.2.4(@chakra-ui/react@2.10.2)(react@18.3.1):
     resolution: {integrity: sha512-l5QdBgwrAg3Sc2BRqtNkJpfuLw/pWRDwwT58J6c4PqQT6wzXxyNa8Q0PForu1ltB5qEiFb1kxr/F/HO1EwNa6g==}
     peerDependencies:
       '@chakra-ui/react': '>=2.0.0'
       react: '>=18'
     dependencies:
-      '@chakra-ui/react': 2.10.4(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1)
+      '@chakra-ui/react': 2.10.2(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1)
       react: 18.3.1
     dev: false
 
@@ -825,8 +803,8 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/react@2.10.4(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1):
-    resolution: {integrity: sha512-XyRWnuZ1Uw7Mlj5pKUGO5/WhnIHP/EOrpy6lGZC1yWlkd0eIfIpYMZ1ALTZx4KPEdbBaes48dgiMT2ROCqLhkA==}
+  /@chakra-ui/react@2.10.2(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1):
+    resolution: {integrity: sha512-TfIHTqTlxTHYJZBtpiR5EZasPUrLYKJxdbHkdOJb5G1OQ+2c5kKl5XA7c2pMtsEptzb7KxAAIB62t3hxdfWp1w==}
     peerDependencies:
       '@emotion/react': '>=11'
       '@emotion/styled': '>=11'
@@ -834,10 +812,10 @@ packages:
       react: '>=18'
       react-dom: '>=18'
     dependencies:
-      '@chakra-ui/hooks': 2.4.3(react@18.3.1)
-      '@chakra-ui/styled-system': 2.12.1(react@18.3.1)
-      '@chakra-ui/theme': 3.4.7(@chakra-ui/styled-system@2.12.1)(react@18.3.1)
-      '@chakra-ui/utils': 2.2.3(react@18.3.1)
+      '@chakra-ui/hooks': 2.4.2(react@18.3.1)
+      '@chakra-ui/styled-system': 2.11.2(react@18.3.1)
+      '@chakra-ui/theme': 3.4.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
       '@emotion/react': 11.13.3(@types/react@18.3.11)(react@18.3.1)
       '@emotion/styled': 11.13.0(@emotion/react@11.13.3)(@types/react@18.3.11)(react@18.3.1)
       '@popperjs/core': 2.11.8
@@ -868,10 +846,10 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/styled-system@2.12.1(react@18.3.1):
-    resolution: {integrity: sha512-DQph1nDiCPtgze7nDe0a36530ByXb5VpPosKGyWMvKocVeZJcDtYG6XM0+V5a0wKuFBXsViBBRIFUTiUesJAcg==}
+  /@chakra-ui/styled-system@2.11.2(react@18.3.1):
+    resolution: {integrity: sha512-y++z2Uop+hjfZX9mbH88F1ikazPv32asD2er56zMJBemUAzweXnHTpiCQbluEDSUDhqmghVZAdb+5L4XLbsRxA==}
     dependencies:
-      '@chakra-ui/utils': 2.2.3(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
       csstype: 3.1.3
     transitivePeerDependencies:
       - react
@@ -915,14 +893,14 @@ packages:
       color2k: 2.0.3
     dev: false
 
-  /@chakra-ui/theme-tools@2.2.7(@chakra-ui/styled-system@2.12.1)(react@18.3.1):
-    resolution: {integrity: sha512-K/VJd0QcnKik7m+qZTkggqNLep6+MPUu8IP5TUpHsnSM5R/RVjsJIR7gO8IZVAIMIGLLTIhGshHxeMekqv6LcQ==}
+  /@chakra-ui/theme-tools@2.2.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1):
+    resolution: {integrity: sha512-3UhKPyzKbV3l/bg1iQN9PBvffYp+EBOoYMUaeTUdieQRPFzo2jbYR0lNCxqv8h5aGM/k54nCHU2M/GStyi9F2A==}
     peerDependencies:
       '@chakra-ui/styled-system': '>=2.0.0'
     dependencies:
-      '@chakra-ui/anatomy': 2.3.5
-      '@chakra-ui/styled-system': 2.12.1(react@18.3.1)
-      '@chakra-ui/utils': 2.2.3(react@18.3.1)
+      '@chakra-ui/anatomy': 2.3.4
+      '@chakra-ui/styled-system': 2.11.2(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
       color2k: 2.0.3
     transitivePeerDependencies:
       - react
@@ -948,15 +926,15 @@ packages:
       '@chakra-ui/theme-tools': 2.1.2(@chakra-ui/styled-system@2.9.2)
     dev: false
 
-  /@chakra-ui/theme@3.4.7(@chakra-ui/styled-system@2.12.1)(react@18.3.1):
-    resolution: {integrity: sha512-pfewthgZTFNUYeUwGvhPQO/FTIyf375cFV1AT8N1y0aJiw4KDe7YTGm7p0aFy4AwAjH2ydMgeEx/lua4tx8qyQ==}
+  /@chakra-ui/theme@3.4.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1):
+    resolution: {integrity: sha512-ZwFBLfiMC3URwaO31ONXoKH9k0TX0OW3UjdPF3EQkQpYyrk/fm36GkkzajjtdpWEd7rzDLRsQjPmvwNaSoNDtg==}
     peerDependencies:
       '@chakra-ui/styled-system': '>=2.8.0'
     dependencies:
-      '@chakra-ui/anatomy': 2.3.5
-      '@chakra-ui/styled-system': 2.12.1(react@18.3.1)
-      '@chakra-ui/theme-tools': 2.2.7(@chakra-ui/styled-system@2.12.1)(react@18.3.1)
-      '@chakra-ui/utils': 2.2.3(react@18.3.1)
+      '@chakra-ui/anatomy': 2.3.4
+      '@chakra-ui/styled-system': 2.11.2(react@18.3.1)
+      '@chakra-ui/theme-tools': 2.2.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
     transitivePeerDependencies:
       - react
     dev: false
@@ -981,8 +959,8 @@ packages:
       lodash.mergewith: 4.6.2
     dev: false
 
-  /@chakra-ui/utils@2.2.3(react@18.3.1):
-    resolution: {integrity: sha512-cldoCQuexZ6e07/9hWHKD4l1QXXlM1Nax9tuQOBvVf/EgwNZt3nZu8zZRDFlhAOKCTQDkmpLTTu+eXXjChNQOw==}
+  /@chakra-ui/utils@2.2.2(react@18.3.1):
+    resolution: {integrity: sha512-jUPLT0JzRMWxpdzH6c+t0YMJYrvc5CLericgITV3zDSXblkfx3DsYXqU11DJTSGZI9dUKzM1Wd0Wswn4eJwvFQ==}
     peerDependencies:
       react: '>=16.8.0'
     dependencies:
@@ -1002,6 +980,49 @@ 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:
@@ -1675,20 +1696,20 @@ packages:
       prettier: 3.3.3
     dev: true
 
-  /@invoke-ai/ui-library@0.0.44(@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-PDseHmdr8oi8cmrpx3UwIYHn4NduAJX2R0pM0pyM54xrCMPMgYiCbC/eOs8Gt4fBc2ziiPZ9UGoW4evnE3YJsg==}
+  /@invoke-ai/ui-library@0.0.43(@chakra-ui/form-control@2.2.0)(@chakra-ui/icon@3.2.0)(@chakra-ui/media-query@3.3.0)(@chakra-ui/menu@2.2.1)(@chakra-ui/spinner@2.1.0)(@chakra-ui/system@2.6.2)(@fontsource-variable/inter@5.1.0)(@types/react@18.3.11)(i18next@23.15.1)(react-dom@18.3.1)(react@18.3.1):
+    resolution: {integrity: sha512-t3fPYyks07ue3dEBPJuTHbeDLnDckDCOrtvc07mMDbLOnlPEZ0StaeiNGH+oO8qLzAuMAlSTdswgHfzTc2MmPw==}
     peerDependencies:
       '@fontsource-variable/inter': ^5.0.16
       react: ^18.2.0
       react-dom: ^18.2.0
     dependencies:
-      '@chakra-ui/anatomy': 2.2.2
-      '@chakra-ui/icons': 2.2.4(@chakra-ui/react@2.10.4)(react@18.3.1)
+      '@chakra-ui/anatomy': 2.3.4
+      '@chakra-ui/icons': 2.2.4(@chakra-ui/react@2.10.2)(react@18.3.1)
       '@chakra-ui/layout': 2.3.1(@chakra-ui/system@2.6.2)(react@18.3.1)
       '@chakra-ui/portal': 2.1.0(react-dom@18.3.1)(react@18.3.1)
-      '@chakra-ui/react': 2.10.4(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1)
-      '@chakra-ui/styled-system': 2.9.2
-      '@chakra-ui/theme-tools': 2.1.2(@chakra-ui/styled-system@2.9.2)
+      '@chakra-ui/react': 2.10.2(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1)
+      '@chakra-ui/styled-system': 2.11.2(react@18.3.1)
+      '@chakra-ui/theme-tools': 2.2.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1)
       '@emotion/react': 11.13.3(@types/react@18.3.11)(react@18.3.1)
       '@emotion/styled': 11.13.0(@emotion/react@11.13.3)(@types/react@18.3.11)(react@18.3.1)
       '@fontsource-variable/inter': 5.1.0
@@ -4292,10 +4313,6 @@ 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:
@@ -7540,10 +7557,6 @@ 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

@@ -95,10 +95,7 @@
         "none": "Keine",
         "new": "Neu",
         "ok": "OK",
-        "close": "Schließen",
-        "clipboard": "Zwischenablage",
-        "generating": "Generieren",
-        "loadingModel": "Lade Modell"
+        "close": "Schließen"
     },
     "gallery": {
         "galleryImageSize": "Bildgröße",
@@ -538,12 +535,14 @@
         "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",
@@ -593,15 +592,7 @@
         "loraTriggerPhrases": "LoRA-Auslösephrasen",
         "installingBundle": "Bündel wird installiert",
         "triggerPhrases": "Auslösephrasen",
-        "mainModelTriggerPhrases": "Hauptmodell-Auslösephrasen",
-        "noDefaultSettings": "Für dieses Modell sind keine Standardeinstellungen konfiguriert. Besuchen Sie den Modell-Manager, um Standardeinstellungen hinzuzufügen.",
-        "defaultSettingsOutOfSync": "Einige Einstellungen stimmen nicht mit den Standardeinstellungen des Modells überein:",
-        "clipLEmbed": "CLIP-L einbetten",
-        "clipGEmbed": "CLIP-G einbetten",
-        "hfTokenLabel": "HuggingFace-Token (für einige Modelle erforderlich)",
-        "hfTokenHelperText": "Für die Nutzung einiger Modelle ist ein HF-Token erforderlich. Klicken Sie hier, um Ihr Token zu erstellen oder zu erhalten.",
-        "hfForbidden": "Sie haben keinen Zugriff auf dieses HF-Modell",
-        "hfTokenInvalid": "Ungültiges oder fehlendes HF-Token"
+        "mainModelTriggerPhrases": "Hauptmodell-Auslösephrasen"
     },
     "parameters": {
         "images": "Bilder",
@@ -687,41 +678,10 @@
     "toast": {
         "uploadFailed": "Hochladen fehlgeschlagen",
         "imageCopied": "Bild kopiert",
-        "parametersNotSet": "Parameter nicht zurückgerufen",
+        "parametersNotSet": "Parameter nicht festgelegt",
         "addedToBoard": "Dem Board hinzugefügt",
         "loadedWithWarnings": "Workflow mit Warnungen geladen",
-        "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"
+        "imageSaved": "Bild gespeichert"
     },
     "accessibility": {
         "uploadImage": "Bild hochladen",
@@ -778,8 +738,7 @@
         "deletedPrivateBoardsCannotbeRestored": "Gelöschte Boards können nicht wiederhergestellt werden. Wenn Sie „Nur Board löschen“ wählen, werden die Bilder in einen privaten, nicht kategorisierten Status für den Ersteller des Bildes versetzt.",
         "assetsWithCount_one": "{{count}} in der Sammlung",
         "assetsWithCount_other": "{{count}} in der Sammlung",
-        "deletedBoardsCannotbeRestored": "Gelöschte Ordner können nicht wiederhergestellt werden. Die Auswahl von \"Nur Ordner löschen\" verschiebt Bilder in einen unkategorisierten Zustand.",
-        "updateBoardError": "Fehler beim Aktualisieren des Ordners"
+        "deletedBoardsCannotbeRestored": "Gelöschte Ordner können nicht wiederhergestellt werden. Die Auswahl von \"Nur Ordner löschen\" verschiebt Bilder in einen unkategorisierten Zustand."
     },
     "queue": {
         "status": "Status",
@@ -851,8 +810,7 @@
         "upscaling": "Hochskalierung",
         "canvas": "Leinwand",
         "prompts_one": "Prompt",
-        "prompts_other": "Prompts",
-        "batchSize": "Stapelgröße"
+        "prompts_other": "Prompts"
     },
     "metadata": {
         "negativePrompt": "Negativ Beschreibung",
@@ -867,6 +825,7 @@
         "width": "Breite",
         "createdBy": "Erstellt von",
         "steps": "Schritte",
+        "seamless": "Nahtlos",
         "positivePrompt": "Positiver Prompt",
         "generationMode": "Generierungsmodus",
         "Threshold": "Rauschen-Schwelle",
@@ -883,9 +842,7 @@
         "recallParameter": "{{label}} Abrufen",
         "parsingFailed": "Parsing Fehlgeschlagen",
         "canvasV2Metadata": "Leinwand",
-        "guidance": "Führung",
-        "seamlessXAxis": "Nahtlose X Achse",
-        "seamlessYAxis": "Nahtlose Y Achse"
+        "guidance": "Führung"
     },
     "popovers": {
         "noiseUseCPU": {
@@ -1092,21 +1049,6 @@
         },
         "patchmatchDownScaleSize": {
             "heading": "Herunterskalieren"
-        },
-        "paramHeight": {
-            "heading": "Höhe",
-            "paragraphs": [
-                "Höhe des generierten Bildes. Muss ein Vielfaches von 8 sein."
-            ]
-        },
-        "paramUpscaleMethod": {
-            "heading": "Vergrößerungsmethode",
-            "paragraphs": [
-                "Methode zum Hochskalieren des Bildes für High Resolution Fix."
-            ]
-        },
-        "paramHrf": {
-            "heading": "High Resolution Fix aktivieren"
         }
     },
     "invocationCache": {
@@ -1228,19 +1170,7 @@
         "workflowVersion": "Version",
         "saveToGallery": "In Galerie speichern",
         "noWorkflows": "Keine 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"
+        "noMatchingWorkflows": "Keine passenden Arbeitsabläufe"
     },
     "hrf": {
         "enableHrf": "Korrektur für hohe Auflösungen",
@@ -1370,7 +1300,15 @@
         "enableLogging": "Protokollierung aktivieren"
     },
     "whatsNew": {
-        "whatsNewInInvoke": "Was gibt's Neues"
+        "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"
+        }
     },
     "stylePresets": {
         "name": "Name",
@@ -1421,13 +1359,7 @@
         "pullBboxIntoLayerOk": "Bbox in die Ebene gezogen",
         "saveBboxToGallery": "Bbox in Galerie speichern",
         "tool": {
-            "bbox": "Bbox",
-            "brush": "Pinsel",
-            "eraser": "Radiergummi",
-            "colorPicker": "Farbwähler",
-            "view": "Ansicht",
-            "rectangle": "Rechteck",
-            "move": "Verschieben"
+            "bbox": "Bbox"
         },
         "transform": {
             "fitToBbox": "An Bbox anpassen",
@@ -1469,6 +1401,7 @@
         "deleteReferenceImage": "Referenzbild löschen",
         "referenceImage": "Referenzbild",
         "opacity": "Opazität",
+        "resetCanvas": "Leinwand zurücksetzen",
         "removeBookmark": "Lesezeichen entfernen",
         "rasterLayer": "Raster-Ebene",
         "rasterLayers_withCount_visible": "Raster-Ebenen ({{count}})",
@@ -1545,30 +1478,7 @@
         "layer_one": "Ebene",
         "layer_other": "Ebenen",
         "layer_withCount_one": "Ebene ({{count}})",
-        "layer_withCount_other": "Ebenen ({{count}})",
-        "fill": {
-            "fillStyle": "Füllstil",
-            "diagonal": "Diagonal",
-            "vertical": "Vertikal",
-            "fillColor": "Füllfarbe",
-            "grid": "Raster",
-            "solid": "Solide",
-            "crosshatch": "Kreuzschraffur",
-            "horizontal": "Horizontal"
-        },
-        "filter": {
-            "apply": "Anwenden",
-            "reset": "Zurücksetzen",
-            "cancel": "Abbrechen",
-            "spandrel_filter": {
-                "label": "Bild-zu-Bild Modell",
-                "description": "Ein Bild-zu-Bild Modell auf der ausgewählten Ebene ausführen.",
-                "model": "Modell"
-            },
-            "filters": "Filter",
-            "filterType": "Filtertyp",
-            "filter": "Filter"
-        }
+        "layer_withCount_other": "Ebenen ({{count}})"
     },
     "upsell": {
         "shareAccess": "Zugang teilen",

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

@@ -122,7 +122,6 @@
         "goTo": "Go to",
         "hotkeysLabel": "Hotkeys",
         "loadingImage": "Loading Image",
-        "loadingModel": "Loading Model",
         "imageFailedToLoad": "Unable to Load Image",
         "img2img": "Image To Image",
         "inpaint": "inpaint",
@@ -175,9 +174,7 @@
         "placeholderSelectAModel": "Select a model",
         "reset": "Reset",
         "none": "None",
-        "new": "New",
-        "generating": "Generating",
-        "warnings": "Warnings"
+        "new": "New"
     },
     "hrf": {
         "hrf": "High Resolution Fix",
@@ -264,8 +261,7 @@
         "iterations_one": "Iteration",
         "iterations_other": "Iterations",
         "generations_one": "Generation",
-        "generations_other": "Generations",
-        "batchSize": "Batch Size"
+        "generations_other": "Generations"
     },
     "invocationCache": {
         "invocationCache": "Invocation Cache",
@@ -708,8 +704,6 @@
         "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.",
@@ -739,17 +733,7 @@
         "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.",
-        "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",
+        "hfToken": "HuggingFace Token",
         "imageEncoderModelId": "Image Encoder Model ID",
         "includesNModels": "Includes {{n}} models and their dependencies",
         "installQueue": "Install Queue",
@@ -979,8 +963,6 @@
         "zoomOutNodes": "Zoom Out",
         "betaDesc": "This invocation is in beta. Until it is stable, it may have breaking changes during app updates. We plan to support this invocation long-term.",
         "prototypeDesc": "This invocation is a prototype. It may have breaking changes during app updates and may be removed at any time.",
-        "internalDesc": "This invocation is used internally by Invoke. It may have breaking changes during app updates and may be removed at any time.",
-        "specialDesc": "This invocation some special handling in the app. For example, Batch nodes are used to queue multiple graphs from a single workflow.",
         "imageAccessError": "Unable to find image {{image_name}}, resetting to default",
         "boardAccessError": "Unable to find board {{board_id}}, resetting to default",
         "modelAccessError": "Unable to find model {{key}}, resetting to default",
@@ -1005,7 +987,6 @@
         "controlNetControlMode": "Control Mode",
         "copyImage": "Copy Image",
         "denoisingStrength": "Denoising Strength",
-        "disabledNoRasterContent": "Disabled (No Raster Content)",
         "downloadImage": "Download Image",
         "general": "General",
         "guidance": "Guidance",
@@ -1019,11 +1000,8 @@
             "addingImagesTo": "Adding images to",
             "invoke": "Invoke",
             "missingFieldTemplate": "Missing field template",
-            "missingInputForField": "{{nodeLabel}} -> {{fieldLabel}}: missing input",
+            "missingInputForField": "{{nodeLabel}} -> {{fieldLabel}} missing input",
             "missingNodeTemplate": "Missing node template",
-            "collectionEmpty": "{{nodeLabel}} -> {{fieldLabel}} empty collection",
-            "collectionTooFewItems": "{{nodeLabel}} -> {{fieldLabel}}: too few items, minimum {{minItems}}",
-            "collectionTooManyItems": "{{nodeLabel}} -> {{fieldLabel}}: too many items, maximum {{maxItems}}",
             "noModelSelected": "No model selected",
             "noT5EncoderModelSelected": "No T5 Encoder model selected for FLUX generation",
             "noFLUXVAEModelSelected": "No VAE model selected for FLUX generation",
@@ -1032,14 +1010,26 @@
             "fluxModelIncompatibleBboxHeight": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16), bbox height is {{height}}",
             "fluxModelIncompatibleScaledBboxWidth": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16), scaled bbox width is {{width}}",
             "fluxModelIncompatibleScaledBboxHeight": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16), scaled bbox height is {{height}}",
-            "canvasIsFiltering": "Canvas is busy (filtering)",
-            "canvasIsTransforming": "Canvas is busy (transforming)",
-            "canvasIsRasterizing": "Canvas is busy (rasterizing)",
-            "canvasIsCompositing": "Canvas is busy (compositing)",
-            "canvasIsSelectingObject": "Canvas is busy (selecting object)",
+            "canvasIsFiltering": "Canvas is filtering",
+            "canvasIsTransforming": "Canvas is transforming",
+            "canvasIsRasterizing": "Canvas is rasterizing",
+            "canvasIsCompositing": "Canvas is compositing",
             "noPrompts": "No prompts generated",
             "noNodesInGraph": "No nodes in graph",
-            "systemDisconnected": "System disconnected"
+            "systemDisconnected": "System disconnected",
+            "layer": {
+                "controlAdapterNoModelSelected": "no Control Adapter model selected",
+                "controlAdapterIncompatibleBaseModel": "incompatible Control Adapter base model",
+                "t2iAdapterIncompatibleBboxWidth": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, bbox width is {{width}}",
+                "t2iAdapterIncompatibleBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, bbox height is {{height}}",
+                "t2iAdapterIncompatibleScaledBboxWidth": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, scaled bbox width is {{width}}",
+                "t2iAdapterIncompatibleScaledBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, scaled bbox height is {{height}}",
+                "ipAdapterNoModelSelected": "no IP adapter selected",
+                "ipAdapterIncompatibleBaseModel": "incompatible IP Adapter base model",
+                "ipAdapterNoImageSelected": "no IP Adapter image selected",
+                "rgNoPromptsOrIPAdapters": "no text prompts or IP Adapters",
+                "rgNoRegion": "no region selected"
+            }
         },
         "maskBlur": "Mask Blur",
         "negativePromptPlaceholder": "Negative Prompt",
@@ -1047,7 +1037,6 @@
         "patchmatchDownScaleSize": "Downscale",
         "perlinNoise": "Perlin Noise",
         "positivePromptPlaceholder": "Positive Prompt",
-        "recallMetadata": "Recall Metadata",
         "iterations": "Iterations",
         "scale": "Scale",
         "scaleBeforeProcessing": "Scale Before Processing",
@@ -1136,7 +1125,6 @@
         "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",
@@ -1307,9 +1295,8 @@
         "controlNetBeginEnd": {
             "heading": "Begin / End Step Percentage",
             "paragraphs": [
-                "This setting determines which portion of the denoising (generation) process incorporates the guidance from this layer.",
-                "• Start Step (%): Specifies when to begin applying the guidance from this layer during the generation process.",
-                "• End Step (%): Specifies when to stop applying this layer's guidance and revert general guidance from the model and other settings."
+                "The part of the of the denoising process that will have the Control Adapter applied.",
+                "Generally, Control Adapters applied at the start of the process guide composition, and Control Adapters applied at the end guide details."
             ]
         },
         "controlNetControlMode": {
@@ -1319,7 +1306,7 @@
         "controlNetProcessor": {
             "heading": "Processor",
             "paragraphs": [
-                "Method of processing the input image to guide the generation process. Different processors will provide different effects or styles in your generated images."
+                "Method of processing the input image to guide the generation process. Different processors will providedifferent effects or styles in your generated images."
             ]
         },
         "controlNetResizeMode": {
@@ -1327,15 +1314,13 @@
             "paragraphs": ["Method to fit Control Adapter's input image size to the output generation size."]
         },
         "ipAdapterMethod": {
-            "heading": "Mode",
-            "paragraphs": ["The mode defines how the reference image will guide the generation process."]
+            "heading": "Method",
+            "paragraphs": ["Method by which to apply the current IP Adapter."]
         },
         "controlNetWeight": {
             "heading": "Weight",
             "paragraphs": [
-                "Adjusts how strongly the layer influences the generation process",
-                "• Higher Weight (.75-2): Creates a more significant impact on the final result.",
-                "• Lower Weight (0-.75): Creates a smaller impact on the final result."
+                "Weight of the Control Adapter. Higher weight will lead to larger impacts on the final image."
             ]
         },
         "dynamicPrompts": {
@@ -1416,9 +1401,8 @@
         "paramDenoisingStrength": {
             "heading": "Denoising Strength",
             "paragraphs": [
-                "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."
+                "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."
             ]
         },
         "paramHeight": {
@@ -1663,17 +1647,15 @@
         "pullBboxIntoReferenceImageError": "Problem Pulling BBox Into ReferenceImage",
         "regionIsEmpty": "Selected region is empty",
         "mergeVisible": "Merge Visible",
-        "mergeDown": "Merge Down",
-        "mergeVisibleOk": "Merged layers",
-        "mergeVisibleError": "Error merging layers",
-        "mergingLayers": "Merging layers",
+        "mergeVisibleOk": "Merged visible layers",
+        "mergeVisibleError": "Error merging visible layers",
         "clearHistory": "Clear History",
         "bboxOverlay": "Show Bbox Overlay",
-        "newSession": "New Session",
+        "resetCanvas": "Reset Canvas",
         "clearCaches": "Clear Caches",
         "recalculateRects": "Recalculate Rects",
         "clipToBbox": "Clip Strokes to Bbox",
-        "outputOnlyMaskedRegions": "Output Only Generated Regions",
+        "outputOnlyMaskedRegions": "Output Only Masked Regions",
         "addLayer": "Add Layer",
         "duplicate": "Duplicate",
         "moveToFront": "Move to Front",
@@ -1701,12 +1683,8 @@
         "controlLayer": "Control Layer",
         "inpaintMask": "Inpaint Mask",
         "regionalGuidance": "Regional Guidance",
-        "referenceImageRegional": "Reference Image (Regional)",
-        "referenceImageGlobal": "Reference Image (Global)",
-        "asRasterLayer": "As $t(controlLayers.rasterLayer)",
-        "asRasterLayerResize": "As $t(controlLayers.rasterLayer) (Resize)",
-        "asControlLayer": "As $t(controlLayers.controlLayer)",
-        "asControlLayerResize": "As $t(controlLayers.controlLayer) (Resize)",
+        "canvasAsRasterLayer": "$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",
@@ -1774,7 +1752,6 @@
         "pullBboxIntoLayer": "Pull Bbox into Layer",
         "pullBboxIntoReferenceImage": "Pull Bbox into Reference Image",
         "showProgressOnCanvas": "Show Progress on Canvas",
-        "useImage": "Use Image",
         "prompt": "Prompt",
         "negativePrompt": "Negative Prompt",
         "beginEndStepPercentShort": "Begin/End %",
@@ -1783,41 +1760,19 @@
         "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.",
-        "resetCanvasLayers": "Reset Canvas Layers",
-        "resetGenerationSettings": "Reset Generation Settings",
         "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.",
-        "referenceImageEmptyState": "<UploadButton>Upload an image</UploadButton> or drag an image from the <GalleryButton>gallery</GalleryButton> onto this layer to get started.",
-        "warnings": {
-            "problemsFound": "Problems found",
-            "unsupportedModel": "layer not supported for selected base model",
-            "controlAdapterNoModelSelected": "no Control Layer model selected",
-            "controlAdapterIncompatibleBaseModel": "incompatible Control Layer base model",
-            "controlAdapterNoControl": "no control selected/drawn",
-            "ipAdapterNoModelSelected": "no Reference Image model selected",
-            "ipAdapterIncompatibleBaseModel": "incompatible Reference Image base model",
-            "ipAdapterNoImageSelected": "no Reference Image image selected",
-            "rgNoPromptsOrIPAdapters": "no text prompts or Reference Images",
-            "rgNegativePromptNotSupported": "Negative Prompt not supported for selected base model",
-            "rgReferenceImagesNotSupported": "regional Reference Images not supported for selected base model",
-            "rgAutoNegativeNotSupported": "Auto-Negative not supported for selected base model",
-            "rgNoRegion": "no region drawn"
-        },
         "controlMode": {
             "controlMode": "Control Mode",
-            "balanced": "Balanced (recommended)",
+            "balanced": "Balanced",
             "prompt": "Prompt",
             "control": "Control",
             "megaControl": "Mega Control"
         },
         "ipAdapterMethod": {
-            "ipAdapterMethod": "Mode",
-            "full": "Style and Composition",
-            "fullDesc": "Applies visual style (colors, textures) & composition (layout, structure).",
+            "ipAdapterMethod": "IP Adapter Method",
+            "full": "Full",
             "style": "Style Only",
-            "styleDesc": "Applies visual style (colors, textures) without considering its layout.",
-            "composition": "Composition Only",
-            "compositionDesc": "Replicates layout & structure while ignoring the reference's style."
+            "composition": "Composition Only"
         },
         "fill": {
             "fillColor": "Fill Color",
@@ -1847,9 +1802,6 @@
             "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.",
@@ -2027,9 +1979,7 @@
         "upscaleModelDesc": "Upscale (image to image) model",
         "missingUpscaleInitialImage": "Missing initial image for upscaling",
         "missingUpscaleModel": "Missing upscale model",
-        "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."
+        "missingTileControlNetModel": "No valid tile ControlNet models installed"
     },
     "stylePresets": {
         "active": "Active",
@@ -2132,74 +2082,11 @@
     },
     "whatsNew": {
         "whatsNewInInvoke": "What's New in Invoke",
-        "items": [
-            "<StrongComponent>Workflows</StrongComponent>: Run a workflow for a collection of images using the new <StrongComponent>Image Batch</StrongComponent> node.",
-            "<StrongComponent>FLUX</StrongComponent>: Support for XLabs IP Adapter v2."
-        ],
+        "line1": "<ItalicComponent>Select Object</ItalicComponent> tool for precise object selection and editing",
+        "line2": "Expanded Flux support, now with Global Reference Images",
+        "line3": "Improved tooltips and context menus",
         "readReleaseNotes": "Read Release Notes",
         "watchRecentReleaseVideos": "Watch Recent Release Videos",
         "watchUiUpdatesOverview": "Watch UI Updates Overview"
-    },
-    "supportVideos": {
-        "supportVideos": "Support Videos",
-        "gettingStarted": "Getting Started",
-        "controlCanvas": "Control Canvas",
-        "watch": "Watch",
-        "studioSessionsDesc1": "Check out the <StudioSessionsPlaylistLink /> for Invoke deep dives.",
-        "studioSessionsDesc2": "Join our <DiscordLink /> to participate in the live sessions and ask questions. Sessions are uploaded to the playlist the following week.",
-        "videos": {
-            "creatingYourFirstImage": {
-                "title": "Creating Your First Image",
-                "description": "Introduction to creating an image from scratch using Invoke's tools."
-            },
-            "usingControlLayersAndReferenceGuides": {
-                "title": "Using Control Layers and Reference Guides",
-                "description": "Learn how to guide your image creation with control layers and reference images."
-            },
-            "understandingImageToImageAndDenoising": {
-                "title": "Understanding Image-to-Image and Denoising",
-                "description": "Overview of image-to-image transformations and denoising in Invoke."
-            },
-            "exploringAIModelsAndConceptAdapters": {
-                "title": "Exploring AI Models and Concept Adapters",
-                "description": "Dive into AI models and how to use concept adapters for creative control."
-            },
-            "creatingAndComposingOnInvokesControlCanvas": {
-                "title": "Creating and Composing on Invoke's Control Canvas",
-                "description": "Learn to compose images using Invoke's control canvas."
-            },
-            "upscaling": {
-                "title": "Upscaling",
-                "description": "How to upscale images with Invoke's tools to enhance resolution."
-            },
-            "howDoIGenerateAndSaveToTheGallery": {
-                "title": "How Do I Generate and Save to the Gallery?",
-                "description": "Steps to generate and save images to the gallery."
-            },
-            "howDoIEditOnTheCanvas": {
-                "title": "How Do I Edit on the Canvas?",
-                "description": "Guide to editing images directly on the canvas."
-            },
-            "howDoIDoImageToImageTransformation": {
-                "title": "How Do I Do Image-to-Image Transformation?",
-                "description": "Tutorial on performing image-to-image transformations in Invoke."
-            },
-            "howDoIUseControlNetsAndControlLayers": {
-                "title": "How Do I Use Control Nets and Control Layers?",
-                "description": "Learn to apply control layers and controlnets to your images."
-            },
-            "howDoIUseGlobalIPAdaptersAndReferenceImages": {
-                "title": "How Do I Use Global IP Adapters and Reference Images?",
-                "description": "Introduction to adding reference images and global IP adapters."
-            },
-            "howDoIUseInpaintMasks": {
-                "title": "How Do I Use Inpaint Masks?",
-                "description": "How to apply inpaint masks for image correction and variation."
-            },
-            "howDoIOutpaint": {
-                "title": "How Do I Outpaint?",
-                "description": "Guide to outpainting beyond the original image borders."
-            }
-        }
     }
 }

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

@@ -13,7 +13,7 @@
         "discordLabel": "Discord",
         "back": "Atrás",
         "loading": "Cargando",
-        "postprocessing": "Postprocesamiento",
+        "postprocessing": "Postprocesado",
         "txt2img": "De texto a imagen",
         "accept": "Aceptar",
         "cancel": "Cancelar",
@@ -64,7 +64,7 @@
         "prevPage": "Página Anterior",
         "red": "Rojo",
         "alpha": "Transparencia",
-        "outputs": "Resultados",
+        "outputs": "Salidas",
         "learnMore": "Aprende más",
         "enabled": "Activado",
         "disabled": "Desactivado",
@@ -73,32 +73,7 @@
         "created": "Creado",
         "save": "Guardar",
         "unknownError": "Error Desconocido",
-        "blue": "Azul",
-        "clipboard": "Portapapeles",
-        "loadingImage": "Cargando la imagen",
-        "inpaint": "inpaint",
-        "ipAdapter": "Adaptador IP",
-        "t2iAdapter": "Adaptador T2I",
-        "apply": "Aplicar",
-        "openInViewer": "Abrir en el visor",
-        "off": "Apagar",
-        "generating": "Generando",
-        "ok": "De acuerdo",
-        "placeholderSelectAModel": "Seleccionar un modelo",
-        "reset": "Restablecer",
-        "none": "Ninguno",
-        "new": "Nuevo",
-        "dontShowMeThese": "No mostrar estos",
-        "loadingModel": "Cargando el modelo",
-        "view": "Ver",
-        "edit": "Editar",
-        "safetensors": "Safetensors",
-        "toResolve": "Para resolver",
-        "localSystem": "Sistema local",
-        "notInstalled": "No $t(common.installed)",
-        "outpaint": "outpaint",
-        "simple": "Sencillo",
-        "close": "Cerrar"
+        "blue": "Azul"
     },
     "gallery": {
         "galleryImageSize": "Tamaño de la imagen",
@@ -110,63 +85,7 @@
         "deleteImage_other": "Eliminar {{count}} Imágenes",
         "deleteImagePermanent": "Las imágenes eliminadas no se pueden restaurar.",
         "assets": "Activos",
-        "autoAssignBoardOnClick": "Asignar automática tableros al hacer clic",
-        "gallery": "Galería",
-        "noImageSelected": "Sin imágenes seleccionadas",
-        "bulkDownloadRequestFailed": "Error al preparar la descarga",
-        "oldestFirst": "La más antigua primero",
-        "sideBySide": "conjuntamente",
-        "selectForCompare": "Seleccionar para comparar",
-        "alwaysShowImageSizeBadge": "Mostrar siempre las dimensiones de la imagen",
-        "currentlyInUse": "Esta imagen se utiliza actualmente con las siguientes funciones:",
-        "unableToLoad": "No se puede cargar la galería",
-        "selectAllOnPage": "Seleccionar todo en la página",
-        "selectAnImageToCompare": "Seleccione una imagen para comparar",
-        "bulkDownloadFailed": "Error en la descarga",
-        "compareHelp2": "Presione <Kbd> M </Kbd> para recorrer los modos de comparación.",
-        "move": "Mover",
-        "copy": "Copiar",
-        "drop": "Gota",
-        "displayBoardSearch": "Tablero de búsqueda",
-        "deleteSelection": "Borrar selección",
-        "downloadSelection": "Descargar selección",
-        "openInViewer": "Abrir en el visor",
-        "searchImages": "Búsqueda por metadatos",
-        "swapImages": "Intercambiar imágenes",
-        "sortDirection": "Orden de clasificación",
-        "showStarredImagesFirst": "Mostrar imágenes destacadas primero",
-        "go": "Ir",
-        "bulkDownloadRequested": "Preparando la descarga",
-        "image": "imagen",
-        "compareHelp4": "Presione <Kbd> Z </Kbd> o <Kbd> Esc </Kbd> para salir.",
-        "viewerImage": "Ver imagen",
-        "dropOrUpload": "$t(gallery.drop) o cargar",
-        "displaySearch": "Buscar imagen",
-        "download": "Descargar",
-        "exitBoardSearch": "Finalizar búsqueda",
-        "exitSearch": "Salir de la búsqueda de imágenes",
-        "featuresWillReset": "Si elimina esta imagen, dichas funciones se restablecerán inmediatamente.",
-        "jump": "Omitir",
-        "loading": "Cargando",
-        "newestFirst": "La más nueva primero",
-        "unstarImage": "Dejar de ser favorita",
-        "bulkDownloadRequestedDesc": "Su solicitud de descarga se está preparando. Esto puede tardar unos minutos.",
-        "hover": "Desplazar",
-        "compareHelp1": "Mantenga presionada la tecla <Kbd> Alt </Kbd> mientras hace clic en una imagen de la galería o utiliza las teclas de flecha para cambiar la imagen de comparación.",
-        "stretchToFit": "Estirar para encajar",
-        "exitCompare": "Salir de la comparación",
-        "starImage": "Imágenes favoritas",
-        "dropToUpload": "$t(gallery.drop) para cargar",
-        "slider": "Deslizador",
-        "assetsTab": "Archivos que has cargado para utilizarlos en tus proyectos.",
-        "imagesTab": "Imágenes que ha creado y guardado en Invoke.",
-        "compareImage": "Comparar imagen",
-        "boardsSettings": "Ajustes de los tableros",
-        "imagesSettings": "Configuración de imágenes de la galería",
-        "compareHelp3": "Presione <Kbd> C </Kbd> para intercambiar las imágenes comparadas.",
-        "showArchivedBoards": "Mostrar paneles archivados",
-        "closeViewer": "Cerrar visor",
-        "openViewer": "Abrir visor"
+        "autoAssignBoardOnClick": "Asignación automática de tableros al hacer clic"
     },
     "modelManager": {
         "modelManager": "Gestor de Modelos",
@@ -212,13 +131,7 @@
         "modelDeleted": "Modelo eliminado",
         "modelDeleteFailed": "Error al borrar el modelo",
         "settings": "Ajustes",
-        "syncModels": "Sincronizar las plantillas",
-        "clipEmbed": "Incrustar CLIP",
-        "addModels": "Añadir modelos",
-        "advanced": "Avanzado",
-        "clipGEmbed": "Incrustar CLIP-G",
-        "cancel": "Cancelar",
-        "clipLEmbed": "Incrustar CLIP-L"
+        "syncModels": "Sincronizar las plantillas"
     },
     "parameters": {
         "images": "Imágenes",
@@ -245,19 +158,19 @@
         "useSeed": "Usar Semilla",
         "useAll": "Usar Todo",
         "info": "Información",
-        "showOptionsPanel": "Mostrar panel lateral (O o T)",
+        "showOptionsPanel": "Mostrar panel de opciones",
         "symmetry": "Simetría",
         "copyImage": "Copiar la imagen",
         "general": "General",
         "denoisingStrength": "Intensidad de la eliminación del ruido",
-        "seamlessXAxis": "Eje X sin juntas",
-        "seamlessYAxis": "Eje Y sin juntas",
+        "seamlessXAxis": "Eje x",
+        "seamlessYAxis": "Eje y",
         "scheduler": "Programador",
         "positivePromptPlaceholder": "Prompt Positivo",
         "negativePromptPlaceholder": "Prompt Negativo",
         "controlNetControlMode": "Modo de control",
         "clipSkip": "Omitir el CLIP",
-        "maskBlur": "Desenfoque de máscara",
+        "maskBlur": "Difuminar",
         "patchmatchDownScaleSize": "Reducir a escala",
         "coherenceMode": "Modo"
     },
@@ -289,19 +202,16 @@
         "serverError": "Error en el servidor",
         "canceled": "Procesando la cancelación",
         "connected": "Conectado al servidor",
-        "uploadFailedInvalidUploadDesc": "Deben ser imágenes PNG o JPEG.",
-        "parameterSet": "Parámetro recuperado",
-        "parameterNotSet": "Parámetro no recuperado",
+        "uploadFailedInvalidUploadDesc": "Debe ser una sola imagen PNG o JPEG",
+        "parameterSet": "Conjunto de parámetros",
+        "parameterNotSet": "Parámetro no configurado",
         "problemCopyingImage": "No se puede copiar la imagen",
         "errorCopied": "Error al copiar",
         "baseModelChanged": "Modelo base cambiado",
-        "addedToBoard": "Se agregó a los activos del panel {{name}}",
+        "addedToBoard": "Añadido al tablero",
         "baseModelChangedCleared_one": "Borrado o desactivado {{count}} submodelo incompatible",
         "baseModelChangedCleared_many": "Borrados o desactivados {{count}} submodelos incompatibles",
-        "baseModelChangedCleared_other": "Borrados o desactivados {{count}} submodelos incompatibles",
-        "addedToUncategorized": "Añadido a los activos del tablero $t(boards.uncategorized)",
-        "imagesWillBeAddedTo": "Las imágenes subidas se añadirán a los activos del panel {{boardName}}.",
-        "layerCopiedToClipboard": "Capa copiada en el portapapeles"
+        "baseModelChangedCleared_other": "Borrados o desactivados {{count}} submodelos incompatibles"
     },
     "accessibility": {
         "invokeProgressBar": "Activar la barra de progreso",
@@ -316,8 +226,7 @@
         "mode": "Modo",
         "submitSupportTicket": "Enviar Ticket de Soporte",
         "toggleRightPanel": "Activar o desactivar el panel derecho (G)",
-        "toggleLeftPanel": "Activar o desactivar el panel izquierdo (T)",
-        "uploadImages": "Cargar imagen(es)"
+        "toggleLeftPanel": "Activar o desactivar el panel izquierdo (T)"
     },
     "nodes": {
         "zoomInNodes": "Acercar",
@@ -329,8 +238,7 @@
         "showMinimapnodes": "Mostrar el minimapa",
         "reloadNodeTemplates": "Recargar las plantillas de nodos",
         "loadWorkflow": "Cargar el flujo de trabajo",
-        "downloadWorkflow": "Descargar el flujo de trabajo en un archivo JSON",
-        "boardAccessError": "No se puede encontrar el panel {{board_id}}, se está restableciendo al valor predeterminado"
+        "downloadWorkflow": "Descargar el flujo de trabajo en un archivo JSON"
     },
     "boards": {
         "autoAddBoard": "Agregar panel automáticamente",
@@ -347,7 +255,7 @@
         "bottomMessage": "Al eliminar este panel y las imágenes que contiene, se restablecerán las funciones que los estén utilizando actualmente.",
         "deleteBoardAndImages": "Borrar el panel y las imágenes",
         "loading": "Cargando...",
-        "deletedBoardsCannotbeRestored": "Los paneles eliminados no se pueden restaurar. Al Seleccionar 'Borrar solo el panel' transferirá las imágenes a un estado sin categorizar.",
+        "deletedBoardsCannotbeRestored": "Los paneles eliminados no se pueden restaurar. Al Seleccionar 'Borrar Solo el Panel' transferirá las imágenes a un estado sin categorizar.",
         "move": "Mover",
         "menuItemAutoAdd": "Agregar automáticamente a este panel",
         "searchBoard": "Buscando paneles…",
@@ -355,33 +263,29 @@
         "downloadBoard": "Descargar panel",
         "deleteBoardOnly": "Borrar solo el panel",
         "myBoard": "Mi panel",
-        "noMatching": "Sin paneles coincidentes",
+        "noMatching": "No hay paneles que coincidan",
         "imagesWithCount_one": "{{count}} imagen",
         "imagesWithCount_many": "{{count}} imágenes",
         "imagesWithCount_other": "{{count}} imágenes",
         "assetsWithCount_one": "{{count}} activo",
         "assetsWithCount_many": "{{count}} activos",
         "assetsWithCount_other": "{{count}} activos",
-        "hideBoards": "Ocultar paneles",
-        "addPrivateBoard": "Agregar un panel privado",
-        "addSharedBoard": "Añadir panel compartido",
+        "hideBoards": "Ocultar Paneles",
+        "addPrivateBoard": "Agregar un tablero privado",
+        "addSharedBoard": "Agregar Panel Compartido",
         "boards": "Paneles",
-        "archiveBoard": "Archivar panel",
+        "archiveBoard": "Archivar Panel",
         "archived": "Archivado",
         "selectedForAutoAdd": "Seleccionado para agregar automáticamente",
-        "unarchiveBoard": "Desarchivar el panel",
-        "noBoards": "No hay paneles {{boardType}}",
-        "shared": "Paneles compartidos",
-        "deletedPrivateBoardsCannotbeRestored": "Los paneles eliminados no se pueden restaurar. Al elegir \"Eliminar solo el panel\", las imágenes se colocan en un estado privado y sin categoría para el creador de la imagen.",
-        "viewBoards": "Ver paneles",
-        "private": "Paneles privados",
-        "updateBoardError": "No se pudo actualizar el panel"
+        "unarchiveBoard": "Desarchivar el tablero",
+        "noBoards": "No hay tableros {{boardType}}",
+        "shared": "Carpetas compartidas",
+        "deletedPrivateBoardsCannotbeRestored": "Los tableros eliminados no se pueden restaurar. Al elegir \"Eliminar solo tablero\", las imágenes se colocan en un estado privado y sin categoría para el creador de la imagen."
     },
     "accordions": {
         "compositing": {
             "title": "Composición",
-            "infillTab": "Relleno",
-            "coherenceTab": "Parámetros de la coherencia"
+            "infillTab": "Relleno"
         },
         "generation": {
             "title": "Generación"
@@ -405,10 +309,7 @@
             "workflows": "Flujos de trabajo",
             "models": "Modelos",
             "modelsTab": "$t(ui.tabs.models) $t(common.tab)",
-            "workflowsTab": "$t(ui.tabs.workflows) $t(common.tab)",
-            "upscaling": "Upscaling",
-            "gallery": "Galería",
-            "upscalingTab": "$t(ui.tabs.upscaling) $t(common.tab)"
+            "workflowsTab": "$t(ui.tabs.workflows) $t(common.tab)"
         }
     },
     "queue": {
@@ -416,81 +317,12 @@
         "front": "Delante",
         "batchQueuedDesc_one": "Se agregó {{count}} sesión a {{direction}} la cola",
         "batchQueuedDesc_many": "Se agregaron {{count}} sesiones a {{direction}} la cola",
-        "batchQueuedDesc_other": "Se agregaron {{count}} sesiones a {{direction}} la cola",
-        "clearQueueAlertDialog": "Al vaciar la cola se cancela inmediatamente cualquier elemento de procesamiento y se vaciará la cola por completo. Los filtros pendientes se cancelarán.",
-        "time": "Tiempo",
-        "clearFailed": "Error al vaciar la cola",
-        "cancelFailed": "Error al cancelar el elemento",
-        "resumeFailed": "Error al reanudar el proceso",
-        "pause": "Pausar",
-        "pauseTooltip": "Pausar el proceso",
-        "cancelBatchSucceeded": "Lote cancelado",
-        "pruneSucceeded": "Se purgaron {{item_count}} elementos completados de la cola",
-        "pruneFailed": "Error al purgar la cola",
-        "cancelBatchFailed": "Error al cancelar los lotes",
-        "pauseFailed": "Error al pausar el proceso",
-        "status": "Estado",
-        "origin": "Origen",
-        "destination": "Destino",
-        "generations_one": "Generación",
-        "generations_many": "Generaciones",
-        "generations_other": "Generaciones",
-        "resume": "Reanudar",
-        "queueEmpty": "Cola vacía",
-        "cancelItem": "Cancelar elemento",
-        "cancelBatch": "Cancelar lote",
-        "openQueue": "Abrir la cola",
-        "completed": "Completado",
-        "enqueueing": "Añadir lotes a la cola",
-        "clear": "Limpiar",
-        "pauseSucceeded": "Proceso pausado",
-        "resumeSucceeded": "Proceso reanudado",
-        "resumeTooltip": "Reanudar proceso",
-        "cancel": "Cancelar",
-        "cancelTooltip": "Cancelar artículo actual",
-        "pruneTooltip": "Purgar {{item_count}} elementos completados",
-        "batchQueued": "Lote en cola",
-        "pending": "Pendiente",
-        "item": "Elemento",
-        "total": "Total",
-        "in_progress": "En proceso",
-        "failed": "Fallido",
-        "completedIn": "Completado en",
-        "upscaling": "Upscaling",
-        "canvas": "Lienzo",
-        "generation": "Generación",
-        "workflows": "Flujo de trabajo",
-        "other": "Otro",
-        "queueFront": "Añadir al principio de la cola",
-        "gallery": "Galería",
-        "batchFieldValues": "Valores de procesamiento por lotes",
-        "session": "Sesión",
-        "notReady": "La cola aún no está lista",
-        "graphQueued": "Gráfico en cola",
-        "clearQueueAlertDialog2": "¿Estás seguro que deseas vaciar la cola?",
-        "next": "Siguiente",
-        "iterations_one": "Interacción",
-        "iterations_many": "Interacciones",
-        "iterations_other": "Interacciones",
-        "current": "Actual",
-        "queue": "Cola",
-        "queueBack": "Añadir a la cola",
-        "cancelSucceeded": "Elemento cancelado",
-        "clearTooltip": "Cancelar y limpiar todos los elementos",
-        "clearSucceeded": "Cola vaciada",
-        "canceled": "Cancelado",
-        "batch": "Lote",
-        "graphFailedToQueue": "Error al poner el gráfico en cola",
-        "batchFailedToQueue": "Error al poner en cola el lote",
-        "prompts_one": "Prompt",
-        "prompts_many": "Prompts",
-        "prompts_other": "Prompts",
-        "prune": "Eliminar"
+        "batchQueuedDesc_other": "Se agregaron {{count}} sesiones a {{direction}} la cola"
     },
     "upsell": {
         "inviteTeammates": "Invitar compañeros de equipo",
         "shareAccess": "Compartir acceso",
-        "professionalUpsell": "Disponible en la edición profesional de Invoke. Haga clic aquí o visite invoke.com/pricing para obtener más detalles."
+        "professionalUpsell": "Disponible en la edición profesional de Invoke. Haz clic aquí o visita invoke.com/pricing para obtener más detalles."
     },
     "controlLayers": {
         "layer_one": "Capa",
@@ -498,415 +330,6 @@
         "layer_other": "Capas",
         "layer_withCount_one": "({{count}}) capa",
         "layer_withCount_many": "({{count}}) capas",
-        "layer_withCount_other": "({{count}}) capas",
-        "copyToClipboard": "Copiar al portapapeles"
-    },
-    "whatsNew": {
-        "readReleaseNotes": "Leer las notas de la versión",
-        "watchRecentReleaseVideos": "Ver videos de versiones recientes",
-        "watchUiUpdatesOverview": "Descripción general de las actualizaciones de la interfaz de usuario de Watch",
-        "whatsNewInInvoke": "Novedades en Invoke",
-        "items": [
-            "<StrongComponent>SD 3.5</StrongComponent>: compatibilidad con SD 3.5 Medium y Large.",
-            "<StrongComponent>Lienzo</StrongComponent>: Se ha simplificado el procesamiento de la capa de control y se ha mejorado la configuración predeterminada del control."
-        ]
-    },
-    "invocationCache": {
-        "enableFailed": "Error al activar la cache",
-        "cacheSize": "Tamaño de la caché",
-        "hits": "Accesos a la caché",
-        "invocationCache": "Caché",
-        "misses": "Errores de la caché",
-        "clear": "Limpiar",
-        "maxCacheSize": "Tamaño máximo de la caché",
-        "enableSucceeded": "Cache activada",
-        "clearFailed": "Error al borrar la cache",
-        "enable": "Activar",
-        "useCache": "Uso de la caché",
-        "disableSucceeded": "Caché desactivada",
-        "clearSucceeded": "Caché borrada",
-        "disable": "Desactivar",
-        "disableFailed": "Error al desactivar la caché"
-    },
-    "hrf": {
-        "hrf": "Solución de alta resolución",
-        "enableHrf": "Activar corrección de alta resolución",
-        "metadata": {
-            "enabled": "Corrección de alta resolución activada",
-            "strength": "Forzar la corrección de alta resolución",
-            "method": "Método de corrección de alta resolución"
-        },
-        "upscaleMethod": "Método de expansión"
-    },
-    "prompt": {
-        "addPromptTrigger": "Añadir activador de los avisos",
-        "compatibleEmbeddings": "Incrustaciones compatibles",
-        "noMatchingTriggers": "No hay activadores coincidentes"
-    },
-    "hotkeys": {
-        "hotkeys": "Atajo del teclado",
-        "canvas": {
-            "selectViewTool": {
-                "desc": "Selecciona la herramienta de Visualización.",
-                "title": "Visualización"
-            },
-            "cancelFilter": {
-                "title": "Cancelar el filtro",
-                "desc": "Cancelar el filtro pendiente."
-            },
-            "applyTransform": {
-                "title": "Aplicar la transformación",
-                "desc": "Aplicar la transformación pendiente a la capa seleccionada."
-            },
-            "applyFilter": {
-                "desc": "Aplicar el filtro pendiente a la capa seleccionada.",
-                "title": "Aplicar filtro"
-            },
-            "selectBrushTool": {
-                "title": "Pincel",
-                "desc": "Selecciona la herramienta pincel."
-            },
-            "selectBboxTool": {
-                "desc": "Seleccionar la herramienta de selección del marco.",
-                "title": "Selección del marco"
-            },
-            "selectMoveTool": {
-                "desc": "Selecciona la herramienta Mover.",
-                "title": "Mover"
-            },
-            "selectRectTool": {
-                "title": "Rectángulo",
-                "desc": "Selecciona la herramienta Rectángulo."
-            },
-            "decrementToolWidth": {
-                "title": "Reducir el ancho de la herramienta",
-                "desc": "Disminuye la anchura de la herramienta pincel o goma de borrar, según la que esté seleccionada."
-            },
-            "incrementToolWidth": {
-                "title": "Incrementar la anchura de la herramienta",
-                "desc": "Aumenta la anchura de la herramienta pincel o goma de borrar, según la que esté seleccionada."
-            },
-            "fitBboxToCanvas": {
-                "title": "Ajustar bordes al lienzo",
-                "desc": "Escala y posiciona la vista para ajustarla a los bodes."
-            },
-            "fitLayersToCanvas": {
-                "title": "Ajustar capas al lienzo",
-                "desc": "Escala y posiciona la vista para que se ajuste a todas las capas visibles."
-            },
-            "setFillToWhite": {
-                "title": "Establecer color en blanco",
-                "desc": "Establece el color actual de la herramienta en blanco."
-            },
-            "resetSelected": {
-                "title": "Restablecer capa",
-                "desc": "Restablecer la capa seleccionada. Solo se aplica a Máscara de retoque y Guía regional."
-            },
-            "setZoomTo400Percent": {
-                "desc": "Ajuste la aplicación del lienzo al 400%.",
-                "title": "Ampliar al 400%"
-            },
-            "transformSelected": {
-                "desc": "Transformar la capa seleccionada.",
-                "title": "Transformar"
-            },
-            "selectColorPickerTool": {
-                "title": "Selector de color",
-                "desc": "Seleccione la herramienta de selección de color."
-            },
-            "selectEraserTool": {
-                "title": "Borrador",
-                "desc": "Selecciona la herramienta Borrador."
-            },
-            "setZoomTo100Percent": {
-                "title": "Ampliar al 100%",
-                "desc": "Ajuste ampliar el lienzo al 100%."
-            },
-            "undo": {
-                "title": "Deshacer",
-                "desc": "Deshacer la última acción en el lienzo."
-            },
-            "nextEntity": {
-                "desc": "Seleccione la siguiente capa de la lista.",
-                "title": "Capa siguiente"
-            },
-            "redo": {
-                "title": "Rehacer",
-                "desc": "Rehacer la última acción en el lienzo."
-            },
-            "prevEntity": {
-                "title": "Capa anterior",
-                "desc": "Seleccione la capa anterior de la lista."
-            },
-            "title": "Lienzo",
-            "setZoomTo200Percent": {
-                "title": "Ampliar al 200%",
-                "desc": "Ajuste la ampliación del lienzo al 200%."
-            },
-            "setZoomTo800Percent": {
-                "title": "Ampliar al 800%",
-                "desc": "Ajuste la ampliación del lienzo al 800%."
-            },
-            "filterSelected": {
-                "desc": "Filtra la capa seleccionada. Solo se aplica a las capas Ráster y Control.",
-                "title": "Filtrar"
-            },
-            "cancelTransform": {
-                "title": "Cancelar transformación",
-                "desc": "Cancelar la transformación pendiente."
-            },
-            "deleteSelected": {
-                "title": "Borrar la capa",
-                "desc": "Borrar la capa seleccionada."
-            },
-            "quickSwitch": {
-                "desc": "Cambiar entre las dos últimas capas seleccionadas. Si una capa está seleccionada, cambia siempre entre ella y la última capa no seleccionada.",
-                "title": "Cambio rápido de capa"
-            }
-        },
-        "app": {
-            "selectModelsTab": {
-                "title": "Seleccione la pestaña Modelos",
-                "desc": "Selecciona la pestaña Modelos."
-            },
-            "focusPrompt": {
-                "desc": "Mueve el foco del cursor a la indicación positiva.",
-                "title": "Enfoque"
-            },
-            "toggleLeftPanel": {
-                "title": "Alternar panel izquierdo",
-                "desc": "Mostrar u ocultar el panel izquierdo."
-            },
-            "selectQueueTab": {
-                "title": "Seleccione la pestaña Cola",
-                "desc": "Seleccione la pestaña Cola."
-            },
-            "selectCanvasTab": {
-                "title": "Seleccione la pestaña Lienzo",
-                "desc": "Selecciona la pestaña Lienzo."
-            },
-            "clearQueue": {
-                "title": "Vaciar cola",
-                "desc": "Cancelar y variar todos los elementos de la cola."
-            },
-            "selectUpscalingTab": {
-                "title": "Selecciona la pestaña Ampliar",
-                "desc": "Selecciona la pestaña Aumento de escala."
-            },
-            "togglePanels": {
-                "desc": "Muestra u oculta los paneles izquierdo y derecho a la vez.",
-                "title": "Alternar paneles"
-            },
-            "toggleRightPanel": {
-                "title": "Alternar panel derecho",
-                "desc": "Mostrar u ocultar el panel derecho."
-            },
-            "invokeFront": {
-                "desc": "Pone en cola la solicitud de compilación y la agrega al principio de la cola.",
-                "title": "Invocar (frente)"
-            },
-            "cancelQueueItem": {
-                "title": "Cancelar",
-                "desc": "Cancelar el elemento de la cola que se está procesando."
-            },
-            "invoke": {
-                "desc": "Pone en cola la solicitud de compilación y la agrega al final de la cola.",
-                "title": "Invocar"
-            },
-            "title": "Aplicación",
-            "selectWorkflowsTab": {
-                "title": "Seleccione la pestaña Flujos de trabajo",
-                "desc": "Selecciona la pestaña Flujos de trabajo."
-            },
-            "resetPanelLayout": {
-                "title": "Reiniciar la posición del panel",
-                "desc": "Restablece los paneles izquierdo y derecho a su tamaño y disposición por defecto."
-            }
-        },
-        "workflows": {
-            "addNode": {
-                "title": "Añadir nodo",
-                "desc": "Abrir añadir nodo."
-            },
-            "selectAll": {
-                "title": "Seleccionar todo",
-                "desc": "Seleccione todos los nodos y enlaces."
-            },
-            "deleteSelection": {
-                "desc": "Borrar todos los nodos y enlaces seleccionados.",
-                "title": "Borrar"
-            },
-            "undo": {
-                "desc": "Deshaga la última acción.",
-                "title": "Deshacer"
-            },
-            "redo": {
-                "desc": "Rehacer la última acción.",
-                "title": "Rehacer"
-            },
-            "pasteSelection": {
-                "desc": "Pegar nodos y bordes copiados.",
-                "title": "Pegar"
-            },
-            "title": "Flujos de trabajo",
-            "copySelection": {
-                "desc": "Copiar nodos y bordes seleccionados.",
-                "title": "Copiar"
-            },
-            "pasteSelectionWithEdges": {
-                "desc": "Pega los nodos copiados, los enlaces y todos los enlaces conectados a los nodos copiados.",
-                "title": "Pegar con enlaces"
-            }
-        },
-        "viewer": {
-            "useSize": {
-                "title": "Usar dimensiones",
-                "desc": "Utiliza las dimensiones de la imagen actual como el tamaño del borde."
-            },
-            "remix": {
-                "title": "Remezcla",
-                "desc": "Recupera todos los metadatos excepto la semilla de la imagen actual."
-            },
-            "loadWorkflow": {
-                "desc": "Carga el flujo de trabajo guardado de la imagen actual (si tiene uno).",
-                "title": "Cargar flujo de trabajo"
-            },
-            "recallAll": {
-                "desc": "Recupera todos los metadatos de la imagen actual.",
-                "title": "Recuperar todos los metadatos"
-            },
-            "recallPrompts": {
-                "desc": "Recuerde las indicaciones positivas y negativas de la imagen actual.",
-                "title": "Recordatorios"
-            },
-            "recallSeed": {
-                "title": "Recuperar semilla",
-                "desc": "Recupera la semilla de la imagen actual."
-            },
-            "runPostprocessing": {
-                "title": "Ejecutar posprocesamiento",
-                "desc": "Ejecutar el posprocesamiento seleccionado en la imagen actual."
-            },
-            "toggleMetadata": {
-                "title": "Mostrar/ocultar los metadatos",
-                "desc": "Mostrar u ocultar la superposición de metadatos de la imagen actual."
-            },
-            "nextComparisonMode": {
-                "desc": "Desplácese por los modos de comparación.",
-                "title": "Siguiente comparación"
-            },
-            "title": "Visor de imágenes",
-            "toggleViewer": {
-                "title": "Mostrar/Ocultar el visor de imágenes",
-                "desc": "Mostrar u ocultar el visor de imágenes. Solo disponible en la pestaña Lienzo."
-            },
-            "swapImages": {
-                "title": "Intercambiar imágenes en la comparación",
-                "desc": "Intercambia las imágenes que se están comparando."
-            }
-        },
-        "gallery": {
-            "clearSelection": {
-                "title": "Limpiar selección",
-                "desc": "Borrar la selección actual, si hay alguna."
-            },
-            "galleryNavUp": {
-                "title": "Subir",
-                "desc": "Navega hacia arriba en la cuadrícula de la galería y selecciona esa imagen. Si estás en la parte superior de la página, ve a la página anterior."
-            },
-            "galleryNavLeft": {
-                "title": "Izquierda",
-                "desc": "Navegue hacia la izquierda en la rejilla de la galería, seleccionando esa imagen. Si está en la primera imagen de la fila, vaya a la fila anterior. Si está en la primera imagen de la página, vaya a la página anterior."
-            },
-            "galleryNavDown": {
-                "title": "Bajar",
-                "desc": "Navegue hacia abajo en la parrilla de la galería, seleccionando esa imagen. Si se encuentra al final de la página, vaya a la página siguiente."
-            },
-            "galleryNavRight": {
-                "title": "A la derecha",
-                "desc": "Navegue hacia la derecha en la rejilla de la galería, seleccionando esa imagen. Si está en la última imagen de la fila, vaya a la fila siguiente. Si está en la última imagen de la página, vaya a la página siguiente."
-            },
-            "galleryNavUpAlt": {
-                "desc": "Igual que arriba, pero selecciona la imagen de comparación, abriendo el modo de comparación si no está ya abierto.",
-                "title": "Arriba (Comparar imagen)"
-            },
-            "deleteSelection": {
-                "desc": "Borrar todas las imágenes seleccionadas. Por defecto, se le pedirá que confirme la eliminación. Si las imágenes están actualmente en uso en la aplicación, se te avisará.",
-                "title": "Borrar"
-            },
-            "title": "Galería",
-            "selectAllOnPage": {
-                "title": "Seleccionar todo en la página",
-                "desc": "Seleccionar todas las imágenes en la página actual."
-            }
-        },
-        "searchHotkeys": "Buscar teclas de acceso rápido",
-        "noHotkeysFound": "Sin teclas de acceso rápido",
-        "clearSearch": "Limpiar la búsqueda"
-    },
-    "metadata": {
-        "guidance": "Orientación",
-        "createdBy": "Creado por",
-        "noImageDetails": "Sin detalles en la imagen",
-        "cfgRescaleMultiplier": "$t(parameters.cfgRescaleMultiplier)",
-        "height": "Altura",
-        "imageDimensions": "Dimensiones de la imagen",
-        "seamlessXAxis": "Eje X sin juntas",
-        "seamlessYAxis": "Eje Y sin juntas",
-        "generationMode": "Modo de generación",
-        "scheduler": "Programador",
-        "width": "Ancho",
-        "Threshold": "Umbral de ruido",
-        "canvasV2Metadata": "Lienzo",
-        "metadata": "Metadatos",
-        "model": "Modelo",
-        "allPrompts": "Todas las indicaciones",
-        "cfgScale": "Escala CFG",
-        "imageDetails": "Detalles de la imagen",
-        "negativePrompt": "Indicación negativa",
-        "noMetaData": "Sin metadatos",
-        "parameterSet": "Parámetro {{parameter}} establecido",
-        "vae": "Autocodificador",
-        "workflow": "Flujo de trabajo",
-        "seed": "Semilla",
-        "strength": "Forzar imagen a imagen",
-        "recallParameters": "Parámetros de recuperación",
-        "recallParameter": "Recuperar {{label}}",
-        "steps": "Pasos",
-        "noRecallParameters": "Sin parámetros para recuperar",
-        "parsingFailed": "Error al analizar"
-    },
-    "system": {
-        "logLevel": {
-            "debug": "Depurar",
-            "info": "Información",
-            "warn": "Advertir",
-            "fatal": "Grave",
-            "error": "Error",
-            "trace": "Rastro",
-            "logLevel": "Nivel del registro"
-        },
-        "enableLogging": "Activar registro",
-        "logNamespaces": {
-            "workflows": "Flujos de trabajo",
-            "system": "Sistema",
-            "metadata": "Metadatos",
-            "gallery": "Galería",
-            "logNamespaces": "Espacios para los nombres de registro",
-            "generation": "Generación",
-            "events": "Eventos",
-            "canvas": "Lienzo",
-            "config": "Ajustes",
-            "models": "Modelos",
-            "queue": "Cola"
-        }
-    },
-    "newUserExperience": {
-        "downloadStarterModels": "Descargar modelos de inicio",
-        "toGetStarted": "Para empezar, introduzca un mensaje en el cuadro y haga clic en <StrongComponent>Invocar</StrongComponent> para generar su primera imagen. Seleccione una plantilla para mejorar los resultados. Puede elegir guardar sus imágenes directamente en <StrongComponent>Galería</StrongComponent> o editarlas en <StrongComponent>Lienzo</StrongComponent>.",
-        "importModels": "Importar modelos",
-        "noModelsInstalled": "Parece que no tienes ningún modelo instalado",
-        "gettingStartedSeries": "¿Desea más orientación? Consulte nuestra <LinkComponent>Serie de introducción</LinkComponent> para obtener consejos sobre cómo aprovechar todo el potencial de Invoke Studio.",
-        "toGetStartedLocal": "Para empezar, asegúrate de descargar o importar los modelos necesarios para ejecutar Invoke. A continuación, introduzca un mensaje en el cuadro y haga clic en <StrongComponent>Invocar</StrongComponent> para generar su primera imagen. Seleccione una plantilla para mejorar los resultados. Puede elegir guardar sus imágenes directamente en <StrongComponent>Galería</StrongComponent> o editarlas en el <StrongComponent>Lienzo</StrongComponent>."
+        "layer_withCount_other": "({{count}}) capas"
     }
 }

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

@@ -5,7 +5,7 @@
         "reportBugLabel": "Signaler un bug",
         "settingsLabel": "Paramètres",
         "img2img": "Image vers Image",
-        "nodes": "Workflows",
+        "nodes": "Processus",
         "upload": "Importer",
         "load": "Charger",
         "back": "Retour",
@@ -95,8 +95,7 @@
         "positivePrompt": "Prompt Positif",
         "negativePrompt": "Prompt Négatif",
         "ok": "Ok",
-        "close": "Fermer",
-        "clipboard": "Presse-papier"
+        "close": "Fermer"
     },
     "gallery": {
         "galleryImageSize": "Taille de l'image",
@@ -162,7 +161,7 @@
         "unstarImage": "Retirer le marquage de l'Image",
         "viewerImage": "Visualisation de l'Image",
         "imagesSettings": "Paramètres des images de la galerie",
-        "assetsTab": "Fichiers que vous avez importés pour vos projets.",
+        "assetsTab": "Fichiers que vous avez importé pour vos projets.",
         "imagesTab": "Images que vous avez créées et enregistrées dans Invoke.",
         "boardsSettings": "Paramètres des planches"
     },
@@ -220,6 +219,7 @@
         "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",
@@ -254,6 +254,7 @@
         "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",
@@ -283,28 +284,24 @@
         "skippingXDuplicates_many": ", en ignorant {{count}} doublons",
         "skippingXDuplicates_other": ", en ignorant {{count}} doublons",
         "installingModel": "Modèle 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."
+        "installingBundle": "Pack en cours d'installation"
     },
     "parameters": {
         "images": "Images",
-        "steps": "Étapes",
-        "cfgScale": "Échelle CFG",
+        "steps": "Etapes",
+        "cfgScale": "CFG Echelle",
         "width": "Largeur",
         "height": "Hauteur",
         "seed": "Graine",
-        "shuffle": "Nouvelle graine",
+        "shuffle": "Mélanger la graine",
         "noiseThreshold": "Seuil de Bruit",
         "perlinNoise": "Bruit de Perlin",
         "type": "Type",
         "strength": "Force",
         "upscaling": "Agrandissement",
-        "scale": "Échelle",
+        "scale": "Echelle",
         "imageFit": "Ajuster Image Initiale à la Taille de Sortie",
-        "scaleBeforeProcessing": "Échelle Avant Traitement",
+        "scaleBeforeProcessing": "Echelle Avant Traitement",
         "scaledWidth": "Larg. Échelle",
         "scaledHeight": "Haut. Échelle",
         "infillMethod": "Méthode de Remplissage",
@@ -327,6 +324,7 @@
                 "t2iAdapterIncompatibleBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, la hauteur de la bounding box est {{height}}",
                 "t2iAdapterIncompatibleBboxWidth": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, la largeur de la bounding box est {{width}}",
                 "ipAdapterIncompatibleBaseModel": "modèle de base d'IP adapter incompatible",
+                "rgNoRegion": "aucune zone sélectionnée",
                 "controlAdapterNoModelSelected": "aucun modèle de Control Adapter sélectionné"
             },
             "noPrompts": "Aucun prompts généré",
@@ -424,10 +422,7 @@
         "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",
-        "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"
+        "confirmOnNewSession": "Confirmer lors d'une nouvelle session"
     },
     "toast": {
         "uploadFailed": "Importation échouée",
@@ -440,22 +435,22 @@
         "parameterNotSet": "Paramètre non Rappelé",
         "canceled": "Traitement annulé",
         "addedToBoard": "Ajouté aux ressources de la planche {{name}}",
-        "workflowLoaded": "Workflow chargé",
+        "workflowLoaded": "Processus chargé",
         "connected": "Connecté au serveur",
         "setNodeField": "Définir comme champ de nœud",
         "imageUploadFailed": "Échec de l'importation de l'image",
-        "loadedWithWarnings": "Workflow chargé avec des avertissements",
+        "loadedWithWarnings": "Processus chargé avec des avertissements",
         "imageUploaded": "Image importée",
         "modelAddedSimple": "Modèle ajouté à la file d'attente",
         "setControlImage": "Définir comme image de contrôle",
-        "workflowDeleted": "Workflow supprimé",
+        "workflowDeleted": "Processus 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 Workflow",
-        "problemDeletingWorkflow": "Problème de suppression du Workflow",
+        "problemRetrievingWorkflow": "Problème de récupération du processus",
+        "problemDeletingWorkflow": "Problème de suppression du processus",
         "prunedQueue": "File d'attente vidée",
         "parameters": "Paramètres",
         "modelImportCanceled": "Importation du modèle annulée",
@@ -555,7 +550,7 @@
     "accordions": {
         "advanced": {
             "title": "Avancé",
-            "options": "Options $t(accordions.advanced.title)"
+            "options": "$t(accordions.advanced.title) Options"
         },
         "image": {
             "title": "Image"
@@ -636,7 +631,7 @@
         "graphQueued": "Graph ajouté à la file d'attente",
         "other": "Autre",
         "generation": "Génération",
-        "workflows": "Workflows",
+        "workflows": "Processus",
         "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",
@@ -709,8 +704,8 @@
                 "desc": "Rappelle toutes les métadonnées pour l'image actuelle."
             },
             "loadWorkflow": {
-                "title": "Ouvrir un Workflow",
-                "desc": "Charge le workflow enregistré lié à l'image actuelle (s'il en a un)."
+                "title": "Charger le processus",
+                "desc": "Charge le processus enregistré de l'image actuelle (s'il en a un)."
             },
             "recallSeed": {
                 "desc": "Rappelle la graine pour l'image actuelle.",
@@ -761,8 +756,8 @@
                 "desc": "Séléctionne l'onglet Agrandissement."
             },
             "selectWorkflowsTab": {
-                "desc": "Sélectionne l'onglet Workflows.",
-                "title": "Sélectionner l'onglet Workflows"
+                "desc": "Sélectionne l'onglet Processus.",
+                "title": "Sélectionner l'onglet Processus"
             },
             "togglePanels": {
                 "desc": "Affiche ou masque les panneaux gauche et droit en même temps.",
@@ -968,11 +963,11 @@
             },
             "undo": {
                 "title": "Annuler",
-                "desc": "Annule la dernière action de workflow."
+                "desc": "Annule la dernière action de processus."
             },
             "redo": {
                 "title": "Rétablir",
-                "desc": "Rétablit la dernière action de workflow."
+                "desc": "Rétablit la dernière action de processus."
             },
             "addNode": {
                 "desc": "Ouvre le menu d'ajout de nœud.",
@@ -990,7 +985,7 @@
                 "desc": "Colle les nœuds et les connections copiés.",
                 "title": "Coller"
             },
-            "title": "Workflows"
+            "title": "Processus"
         }
     },
     "popovers": {
@@ -1377,43 +1372,6 @@
                 "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": {
@@ -1434,11 +1392,12 @@
         "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": "Workflow",
+        "workflow": "Processus",
         "width": "Largeur",
         "Threshold": "Seuil de bruit",
         "noMetaData": "Aucune métadonnée trouvée",
@@ -1487,8 +1446,8 @@
         "hideMinimapnodes": "Masquer MiniCarte",
         "zoomOutNodes": "Dézoomer",
         "zoomInNodes": "Zoomer",
-        "downloadWorkflow": "Exporter le Workflow au format JSON",
-        "loadWorkflow": "Charger un Workflow",
+        "downloadWorkflow": "Télécharger processus en JSON",
+        "loadWorkflow": "Charger le processus",
         "reloadNodeTemplates": "Recharger les modèles de nœuds",
         "animatedEdges": "Connexions animées",
         "cannotConnectToSelf": "Impossible de se connecter à soi-même",
@@ -1511,16 +1470,16 @@
         "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 Workflow",
+        "noWorkflow": "Pas de processus",
         "validateConnectionsHelp": "Prévenir la création de connexions invalides et l'invocation de graphes invalides",
-        "workflowSettings": "Paramètres de l'Éditeur de Workflow",
-        "workflowValidation": "Erreur de validation du Workflow",
+        "workflowSettings": "Paramètres de l'Éditeur de Processus",
+        "workflowValidation": "Erreur de validation du processus",
         "executionStateInProgress": "En cours",
         "node": "Noeud",
         "scheduler": "Planificateur",
         "notes": "Notes",
-        "notesDescription": "Ajouter des notes sur votre workflow",
-        "unableToLoadWorkflow": "Impossible de charger le Workflow",
+        "notesDescription": "Ajouter des notes sur votre processus",
+        "unableToLoadWorkflow": "Impossible de charger le processus",
         "addNode": "Ajouter un nœud",
         "problemSettingTitle": "Problème lors de définition du Titre",
         "connectionWouldCreateCycle": "La connexion créerait un cycle",
@@ -1543,7 +1502,7 @@
         "noOutputRecorded": "Aucun résultat enregistré",
         "removeLinearView": "Retirer de la vue linéaire",
         "snapToGrid": "Aligner sur la grille",
-        "workflow": "Workflow",
+        "workflow": "Processus",
         "updateApp": "Mettre à jour l'application",
         "updateNode": "Mettre à jour le nœud",
         "nodeOutputs": "Sorties de nœud",
@@ -1556,7 +1515,7 @@
         "string": "Chaîne de caractères",
         "workflowName": "Nom",
         "snapToGridHelp": "Aligner les nœuds sur la grille lors du déplacement",
-        "unableToValidateWorkflow": "Impossible de valider le Workflow",
+        "unableToValidateWorkflow": "Impossible de valider le processus",
         "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",
@@ -1569,15 +1528,15 @@
         "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 du Workflow",
-        "newWorkflowDesc2": "Votre workflow actuel comporte des modifications non enregistrées.",
+        "unableToGetWorkflowVersion": "Impossible d'obtenir la version du schéma de processus",
+        "newWorkflowDesc2": "Votre processus 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 workflow actuel comporte des modifications non enregistrées.",
-        "clearWorkflow": "Effacer le Workflow",
-        "clearWorkflowDesc": "Effacer ce workflow et en commencer un nouveau ?",
+        "clearWorkflowDesc2": "Votre processus actuel comporte des modifications non enregistrées.",
+        "clearWorkflow": "Effacer le Processus",
+        "clearWorkflowDesc": "Effacer ce processus 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)",
@@ -1586,7 +1545,7 @@
         "ipAdapter": "IP-Adapter",
         "viewMode": "Utiliser en vue linéaire",
         "collectionFieldType": "{{name}} (Collection)",
-        "newWorkflow": "Nouveau Workflow",
+        "newWorkflow": "Nouveau processus",
         "reorderLinearView": "Réorganiser la vue linéaire",
         "unknownOutput": "Sortie inconnue : {{name}}",
         "outputFieldTypeParseError": "Impossible d'analyser le type du champ de sortie {{node}}.{{field}} ({{message}})",
@@ -1596,13 +1555,13 @@
         "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 Workflow",
-        "unknownErrorValidatingWorkflow": "Erreur inconnue lors de la validation du Workflow",
+        "editMode": "Modifier dans l'éditeur de processus",
+        "unknownErrorValidatingWorkflow": "Erreur inconnue lors de la validation du processus",
         "updateAllNodes": "Mettre à jour les nœuds",
         "allNodesUpdated": "Tous les nœuds mis à jour",
-        "newWorkflowDesc": "Créer un nouveau workflow ?",
+        "newWorkflowDesc": "Créer un nouveau processus ?",
         "edit": "Modifier",
-        "noFieldsViewMode": "Ce workflow n'a aucun champ sélectionné à afficher. Consultez le workflow complet pour configurer les valeurs.",
+        "noFieldsViewMode": "Ce processus n'a aucun champ sélectionné à afficher. Consultez le processus 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",
@@ -1616,9 +1575,9 @@
         "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 Workflows</LinkComponent>.",
-        "noWorkflows": "Aucun Workflows",
-        "noMatchingWorkflows": "Aucun Workflows correspondant"
+        "workflowHelpText": "Besoin d'aide ? Consultez notre guide sur <LinkComponent>Comment commencer avec les Processus</LinkComponent>.",
+        "noWorkflows": "Aucun Processus",
+        "noMatchingWorkflows": "Aucun processus correspondant"
     },
     "models": {
         "noMatchingModels": "Aucun modèle correspondant",
@@ -1635,51 +1594,59 @@
     },
     "workflows": {
         "workflowLibrary": "Bibliothèque",
-        "loading": "Chargement des Workflows",
-        "searchWorkflows": "Chercher des Workflows",
-        "workflowCleared": "Workflow effacé",
+        "loading": "Chargement des processus",
+        "searchWorkflows": "Rechercher des processus",
+        "workflowCleared": "Processus effacé",
         "noDescription": "Aucune description",
-        "deleteWorkflow": "Supprimer le Workflow",
-        "openWorkflow": "Ouvrir le Workflow",
+        "deleteWorkflow": "Supprimer le processus",
+        "openWorkflow": "Ouvrir le processus",
         "uploadWorkflow": "Charger à partir d'un fichier",
-        "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",
+        "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",
         "downloadWorkflow": "Enregistrer dans le fichier",
-        "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",
+        "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",
         "ascending": "Ascendant",
-        "loadFromGraph": "Charger le Workflow à partir du graphique",
+        "loadFromGraph": "Charger le processus à partir du graphique",
         "descending": "Descendant",
         "created": "Créé",
         "updated": "Mis à jour",
-        "loadWorkflow": "$t(common.load) Workflow",
+        "loadWorkflow": "$t(common.load) Processus",
         "convertGraph": "Convertir le graphique",
         "opened": "Ouvert",
         "name": "Nom",
         "autoLayout": "Mise en page automatique",
-        "defaultWorkflows": "Workflows par défaut",
-        "userWorkflows": "Workflows de l'utilisateur",
-        "projectWorkflows": "Workflows du projet",
+        "defaultWorkflows": "Processus par défaut",
+        "userWorkflows": "Processus utilisateur",
+        "projectWorkflows": "Processus du projet",
         "copyShareLink": "Copier le lien de partage",
-        "chooseWorkflowFromLibrary": "Choisir le Workflow dans la Bibliothèque",
+        "chooseWorkflowFromLibrary": "Choisir le Processus dans la Bibliothèque",
         "uploadAndSaveWorkflow": "Importer dans la bibliothèque",
         "edit": "Modifer",
-        "deleteWorkflow2": "Êtes-vous sûr de vouloir supprimer ce Workflow ? Cette action ne peut pas être annulé.",
+        "deleteWorkflow2": "Êtes-vous sûr de vouloir supprimer ce processus ? Ceci ne peut pas être annulé.",
         "download": "Télécharger",
-        "copyShareLinkForWorkflow": "Copier le lien de partage pour le Workflow",
+        "copyShareLinkForWorkflow": "Copier le lien de partage pour le processus",
         "delete": "Supprimer"
     },
     "whatsNew": {
+        "canvasV2Announcement": {
+            "watchReleaseVideo": "Regarder la vidéo de lancement",
+            "newLayerTypes": "Nouveaux types de couches pour un contrôle encore plus précis",
+            "fluxSupport": "Support pour la famille de modèles Flux",
+            "readReleaseNotes": "Lire les notes de version",
+            "newCanvas": "Une nouvelle Toile de contrôle puissant",
+            "watchUiUpdatesOverview": "Regarder l'aperçu des mises à jour de l'UI"
+        },
         "whatsNewInInvoke": "Quoi de neuf dans Invoke"
     },
     "ui": {
@@ -1690,7 +1657,7 @@
             "gallery": "Galerie",
             "upscalingTab": "$t(ui.tabs.upscaling) $t(common.tab)",
             "generation": "Génération",
-            "workflows": "Workflows",
+            "workflows": "Processus",
             "workflowsTab": "$t(ui.tabs.workflows) $t(common.tab)",
             "models": "Modèles",
             "modelsTab": "$t(ui.tabs.models) $t(common.tab)"
@@ -1800,9 +1767,7 @@
             "bboxGroup": "Créer à partir de la bounding box",
             "newRegionalReferenceImage": "Nouvelle image de référence régionale",
             "newGlobalReferenceImage": "Nouvelle image de référence globale",
-            "newControlLayer": "Nouveau couche de contrôle",
-            "newInpaintMask": "Nouveau Masque Inpaint",
-            "newRegionalGuidance": "Nouveau Guide Régional"
+            "newControlLayer": "Nouveau couche de contrôle"
         },
         "bookmark": "Marque-page pour Changement Rapide",
         "saveLayerToAssets": "Enregistrer la couche dans les ressources",
@@ -1815,6 +1780,8 @@
                 "on": "Activé",
                 "label": "Aligner sur la grille"
             },
+            "isolatedFilteringPreview": "Aperçu de filtrage isolé",
+            "isolatedTransformingPreview": "Aperçu de transformation isolée",
             "invertBrushSizeScrollDirection": "Inverser le défilement pour la taille du pinceau",
             "pressureSensitivity": "Sensibilité à la pression",
             "preserveMask": {
@@ -1822,10 +1789,9 @@
                 "alert": "Préserver la zone masquée"
             },
             "isolatedPreview": "Aperçu Isolé",
-            "isolatedStagingPreview": "Aperçu de l'attente isolé",
-            "isolatedLayerPreview": "Aperçu de la couche isolée",
-            "isolatedLayerPreviewDesc": "Pour afficher uniquement cette couche lors de l'exécution d'opérations telles que le filtrage ou la transformation."
+            "isolatedStagingPreview": "Aperçu de l'attente isolé"
         },
+        "convertToRasterLayer": "Convertir en Couche de Rastérisation",
         "transparency": "Transparence",
         "moveBackward": "Reculer",
         "rectangle": "Rectangle",
@@ -1948,6 +1914,7 @@
         "globalReferenceImage_withCount_one": "$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}}",
@@ -1984,6 +1951,7 @@
         "inpaintMask_withCount_many": "Remplir les masques",
         "inpaintMask_withCount_other": "Remplir les masques",
         "newImg2ImgCanvasFromImage": "Nouvelle Img2Img à partir de l'image",
+        "resetCanvas": "Réinitialiser la Toile",
         "bboxOverlay": "Afficher la superposition des Bounding Box",
         "moveToFront": "Déplacer vers le permier plan",
         "moveToBack": "Déplacer vers l'arrière plan",
@@ -2009,39 +1977,7 @@
         "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",
-        "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."
-        },
-        "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)"
+        "controlLayer_withCount_other": "Controler les couches"
     },
     "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.",
@@ -2112,7 +2048,7 @@
             "config": "Configuration",
             "canvas": "Toile",
             "generation": "Génération",
-            "workflows": "Workflows",
+            "workflows": "Processus",
             "system": "Système",
             "models": "Modèles",
             "logNamespaces": "Journalisation des espaces de noms",
@@ -2135,9 +2071,9 @@
     "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 semble qu'aucun modèle ne soit installé",
+        "noModelsInstalled": "Il semblerait qu'aucun modèle ne soit installé",
         "downloadStarterModels": "Télécharger les modèles de démarrage",
-        "importModels": "Importer des Modèles",
+        "importModels": "Importer Modèles",
         "toGetStartedLocal": "Pour commencer, assurez-vous de télécharger ou d'importer des modèles nécessaires pour exécuter Invoke. Ensuite, saisissez le prompt dans la boîte et cliquez sur <StrongComponent>Invoke</StrongComponent> pour générer votre première image. Sélectionnez un template de prompt pour améliorer les résultats. Vous pouvez choisir de sauvegarder vos images directement sur <StrongComponent>Galerie</StrongComponent> ou les modifier sur la <StrongComponent>Toile</StrongComponent>."
     },
     "upsell": {

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

@@ -92,12 +92,7 @@
         "none": "Niente",
         "new": "Nuovo",
         "view": "Vista",
-        "close": "Chiudi",
-        "clipboard": "Appunti",
-        "ok": "Ok",
-        "generating": "Generazione",
-        "loadingModel": "Caricamento del modello",
-        "warnings": "Avvisi"
+        "close": "Chiudi"
     },
     "gallery": {
         "galleryImageSize": "Dimensione dell'immagine",
@@ -547,6 +542,7 @@
         "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",
@@ -592,26 +588,7 @@
         "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.",
-        "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",
-        "hfTokenInvalidErrorMessage": "Gettone HuggingFace non valido o mancante.",
-        "hfTokenRequired": "Stai tentando di scaricare un modello che richiede un gettone HuggingFace valido.",
-        "hfTokenUnableToVerifyErrorMessage": "Impossibile verificare il gettone HuggingFace. Ciò è probabilmente dovuto a un errore di rete. Riprova più tardi.",
-        "hfTokenHelperText": "Per utilizzare alcuni modelli è necessario un gettone HF. Fai clic qui per creare o ottenere il tuo gettone.",
-        "hfTokenInvalid": "Gettone HF non valido o mancante",
-        "hfTokenUnableToVerify": "Impossibile verificare il gettone HF",
-        "hfTokenSaved": "Gettone HF salvato",
-        "hfForbidden": "Non hai accesso a questo modello HF",
-        "hfTokenLabel": "Gettone HuggingFace (richiesto per alcuni modelli)",
-        "hfForbiddenErrorMessage": "Consigliamo di visitare la pagina del repository su HuggingFace.com. Il proprietario potrebbe richiedere l'accettazione dei termini per poter effettuare il download.",
-        "hfTokenInvalidErrorMessage2": "Aggiornalo in "
+        "starterBundleHelpText": "Installa facilmente tutti i modelli necessari per iniziare con un modello base, tra cui un modello principale, controlnet, adattatori IP e altro. Selezionando un pacchetto salterai tutti i modelli che hai già installato."
     },
     "parameters": {
         "images": "Immagini",
@@ -672,15 +649,11 @@
                 "ipAdapterIncompatibleBaseModel": "Il modello base dell'adattatore IP non è compatibile",
                 "ipAdapterNoImageSelected": "Nessuna immagine dell'adattatore IP selezionata",
                 "rgNoPromptsOrIPAdapters": "Nessun prompt o adattatore IP",
+                "rgNoRegion": "Nessuna regione selezionata",
                 "t2iAdapterIncompatibleBboxWidth": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, larghezza riquadro è {{width}}",
                 "t2iAdapterIncompatibleBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, altezza riquadro è {{height}}",
                 "t2iAdapterIncompatibleScaledBboxWidth": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, larghezza del riquadro scalato {{width}}",
-                "t2iAdapterIncompatibleScaledBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, altezza del riquadro scalato {{height}}",
-                "rgNegativePromptNotSupported": "prompt negativo non supportato per il modello base selezionato",
-                "rgAutoNegativeNotSupported": "auto-negativo non supportato per il modello base selezionato",
-                "emptyLayer": "livello vuoto",
-                "unsupportedModel": "livello non supportato per il modello base selezionato",
-                "rgReferenceImagesNotSupported": "immagini di riferimento regionali non supportate per il modello base selezionato"
+                "t2iAdapterIncompatibleScaledBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, altezza del riquadro scalato {{height}}"
             },
             "fluxModelIncompatibleBboxHeight": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16), altezza riquadro è {{height}}",
             "fluxModelIncompatibleBboxWidth": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16), larghezza riquadro è {{width}}",
@@ -692,11 +665,7 @@
             "canvasIsTransforming": "La tela sta trasformando",
             "canvasIsRasterizing": "La tela sta rasterizzando",
             "canvasIsCompositing": "La tela è in fase di composizione",
-            "canvasIsFiltering": "La tela sta filtrando",
-            "collectionTooManyItems": "{{nodeLabel}} -> {{fieldLabel}}: troppi elementi, massimo {{maxItems}}",
-            "canvasIsSelectingObject": "La tela è occupata (selezione dell'oggetto)",
-            "collectionTooFewItems": "{{nodeLabel}} -> {{fieldLabel}}: troppi pochi elementi, minimo {{minItems}}",
-            "collectionEmpty": "{{nodeLabel}} -> {{fieldLabel}} raccolta vuota"
+            "canvasIsFiltering": "La tela sta filtrando"
         },
         "useCpuNoise": "Usa la CPU per generare rumore",
         "iterations": "Iterazioni",
@@ -720,10 +689,7 @@
         "boxBlur": "Sfocatura Box",
         "staged": "Maschera espansa",
         "optimizedImageToImage": "Immagine-a-immagine ottimizzata",
-        "sendToCanvas": "Invia alla Tela",
-        "coherenceMinDenoise": "Min rid. rumore",
-        "recallMetadata": "Richiama i metadati",
-        "disabledNoRasterContent": "Disabilitato (nessun contenuto Raster)"
+        "sendToCanvas": "Invia alla Tela"
     },
     "settings": {
         "models": "Modelli",
@@ -758,11 +724,7 @@
         "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",
-        "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.",
-        "showDetailedInvocationProgress": "Mostra dettagli avanzamento"
+        "confirmOnNewSession": "Conferma su nuova sessione"
     },
     "toast": {
         "uploadFailed": "Caricamento fallito",
@@ -981,9 +943,7 @@
         "saveToGallery": "Salva nella Galleria",
         "noMatchingWorkflows": "Nessun flusso di lavoro corrispondente",
         "noWorkflows": "Nessun flusso di lavoro",
-        "workflowHelpText": "Hai bisogno di aiuto? Consulta la nostra guida <LinkComponent>Introduzione ai flussi di lavoro</LinkComponent>.",
-        "specialDesc": "Questa invocazione comporta una gestione speciale nell'applicazione. Ad esempio, i nodi Lotto vengono utilizzati per mettere in coda più grafici da un singolo flusso di lavoro.",
-        "internalDesc": "Questa invocazione è utilizzata internamente da Invoke. Potrebbe subire modifiche significative durante gli aggiornamenti dell'app e potrebbe essere rimossa in qualsiasi momento."
+        "workflowHelpText": "Hai bisogno di aiuto? Consulta la nostra guida <LinkComponent>Introduzione ai flussi di lavoro</LinkComponent>."
     },
     "boards": {
         "autoAddBoard": "Aggiungi automaticamente bacheca",
@@ -1104,8 +1064,7 @@
         "workflows": "Flussi di lavoro",
         "generation": "Generazione",
         "other": "Altro",
-        "gallery": "Galleria",
-        "batchSize": "Dimensione del lotto"
+        "gallery": "Galleria"
     },
     "models": {
         "noMatchingModels": "Nessun modello corrispondente",
@@ -1117,8 +1076,7 @@
         "noLoRAsInstalled": "Nessun LoRA installato",
         "addLora": "Aggiungi LoRA",
         "defaultVAE": "VAE predefinito",
-        "concepts": "Concetti",
-        "lora": "LoRA"
+        "concepts": "Concetti"
     },
     "invocationCache": {
         "disable": "Disabilita",
@@ -1175,8 +1133,7 @@
             "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",
@@ -1208,8 +1165,7 @@
             "heading": "Percentuale passi Inizio / Fine",
             "paragraphs": [
                 "La parte del processo di rimozione del rumore in cui verrà applicato l'adattatore di controllo.",
-                "In genere, gli adattatori di controllo applicati all'inizio del processo guidano la composizione, mentre quelli applicati alla fine guidano i dettagli.",
-                "• Passo finale (%): specifica quando interrompere l'applicazione della guida di questo livello e ripristinare la guida generale dal modello e altre impostazioni."
+                "In genere, gli adattatori di controllo applicati all'inizio del processo guidano la composizione, mentre quelli applicati alla fine guidano i dettagli."
             ]
         },
         "noiseUseCPU": {
@@ -1292,9 +1248,8 @@
         },
         "paramDenoisingStrength": {
             "paragraphs": [
-                "Controlla la differenza tra l'immagine generata e il/i livello/i raster.",
-                "Una forza inferiore rimane più vicina ai livelli raster visibili combinati. Una forza superiore si basa maggiormente sul prompt globale.",
-                "Se non sono presenti livelli raster con contenuto visibile, questa impostazione viene ignorata."
+                "Quanto rumore viene aggiunto all'immagine in ingresso.",
+                "0 risulterà in un'immagine identica, mentre 1 risulterà in un'immagine completamente nuova."
             ],
             "heading": "Forza di riduzione del rumore"
         },
@@ -1306,16 +1261,14 @@
         },
         "infillMethod": {
             "paragraphs": [
-                "Metodo di riempimento durante il processo di Outpaint o Inpaint."
+                "Metodo di riempimento durante il processo di Outpainting o Inpainting."
             ],
             "heading": "Metodo di riempimento"
         },
         "controlNetWeight": {
             "heading": "Peso",
             "paragraphs": [
-                "Regola la forza con cui il livello influenza il processo di generazione",
-                "• Peso maggiore (0.75-2): crea un impatto più significativo sul risultato finale.",
-                "• Peso inferiore (0-0.75): crea un impatto minore sul risultato finale."
+                "Peso dell'adattatore di controllo. Un peso maggiore porterà a impatti maggiori sull'immagine finale."
             ]
         },
         "paramCFGScale": {
@@ -1476,7 +1429,7 @@
             "heading": "Livello minimo di riduzione del rumore",
             "paragraphs": [
                 "Intensità minima di riduzione rumore per la modalità di Coerenza",
-                "L'intensità minima di riduzione del rumore per la regione di coerenza durante l'inpaint o l'outpaint"
+                "L'intensità minima di riduzione del rumore per la regione di coerenza durante l'inpainting o l'outpainting"
             ]
         },
         "compositingMaskBlur": {
@@ -1530,7 +1483,7 @@
         "optimizedDenoising": {
             "heading": "Immagine-a-immagine ottimizzata",
             "paragraphs": [
-                "Abilita 'Immagine-a-immagine ottimizzata' per una scala di riduzione del rumore più graduale per le trasformazioni da immagine a immagine e di inpaint con modelli Flux. Questa impostazione migliora la capacità di controllare la quantità di modifica applicata a un'immagine, ma può essere disattivata se preferisci usare la scala di riduzione rumore standard. Questa impostazione è ancora in fase di messa a punto ed è in stato beta."
+                "Abilita 'Immagine-a-immagine ottimizzata' per una scala di riduzione del rumore più graduale per le trasformazioni da immagine a immagine e di inpainting con modelli Flux. Questa impostazione migliora la capacità di controllare la quantità di modifica applicata a un'immagine, ma può essere disattivata se preferisci usare la scala di riduzione rumore standard. Questa impostazione è ancora in fase di messa a punto ed è in stato beta."
             ]
         },
         "paramGuidance": {
@@ -1539,42 +1492,6 @@
                 "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": {
@@ -1596,6 +1513,7 @@
         "refinerSteps": "Passi Affinamento"
     },
     "metadata": {
+        "seamless": "Senza giunture",
         "positivePrompt": "Prompt positivo",
         "negativePrompt": "Prompt negativo",
         "generationMode": "Modalità generazione",
@@ -1623,10 +1541,7 @@
         "parsingFailed": "Analisi non riuscita",
         "recallParameter": "Richiama {{label}}",
         "canvasV2Metadata": "Tela",
-        "guidance": "Guida",
-        "seamlessXAxis": "Asse X senza giunte",
-        "seamlessYAxis": "Asse Y senza giunte",
-        "vae": "VAE"
+        "guidance": "Guida"
     },
     "hrf": {
         "enableHrf": "Abilita Correzione Alta Risoluzione",
@@ -1723,11 +1638,11 @@
         "regionalGuidance": "Guida regionale",
         "opacity": "Opacità",
         "mergeVisible": "Fondi il visibile",
-        "mergeVisibleOk": "Livelli uniti",
+        "mergeVisibleOk": "Livelli visibili 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",
+        "mergeVisibleError": "Errore durante l'unione dei livelli visibili",
         "regionalReferenceImage": "Immagine di riferimento Regionale",
         "newLayerFromImage": "Nuovo livello da immagine",
         "newCanvasFromImage": "Nuova tela da immagine",
@@ -1765,7 +1680,8 @@
         "newRegionalReferenceImageError": "Problema nella creazione dell'immagine di riferimento regionale",
         "newControlLayerOk": "Livello di controllo creato",
         "bboxOverlay": "Mostra sovrapposizione riquadro",
-        "outputOnlyMaskedRegions": "In uscita solo le regioni generate",
+        "resetCanvas": "Reimposta la tela",
+        "outputOnlyMaskedRegions": "Solo regioni mascherate in uscita",
         "enableAutoNegative": "Abilita Auto Negativo",
         "disableAutoNegative": "Disabilita Auto Negativo",
         "showHUD": "Mostra HUD",
@@ -1802,7 +1718,7 @@
         "globalReferenceImage_withCount_many": "Immagini di riferimento Globali",
         "globalReferenceImage_withCount_other": "Immagini di riferimento Globali",
         "controlMode": {
-            "balanced": "Bilanciato (consigliato)",
+            "balanced": "Bilanciato",
             "controlMode": "Modalità di controllo",
             "prompt": "Prompt",
             "control": "Controllo",
@@ -1813,15 +1729,12 @@
         "beginEndStepPercentShort": "Inizio/Fine %",
         "stagingOnCanvas": "Genera immagini nella",
         "ipAdapterMethod": {
-            "full": "Stile e Composizione",
+            "full": "Completo",
             "style": "Solo Stile",
             "composition": "Solo Composizione",
-            "ipAdapterMethod": "Metodo Adattatore IP",
-            "fullDesc": "Applica lo stile visivo (colori, texture) e la composizione (disposizione, struttura).",
-            "styleDesc": "Applica lo stile visivo (colori, texture) senza considerare la disposizione.",
-            "compositionDesc": "Replica disposizione e struttura ignorando lo stile di riferimento."
+            "ipAdapterMethod": "Metodo Adattatore IP"
         },
-        "showingType": "Mostra {{type}}",
+        "showingType": "Mostrare {{type}}",
         "dynamicGrid": "Griglia dinamica",
         "tool": {
             "view": "Muovi",
@@ -1915,10 +1828,7 @@
             "lineart_anime_edge_detection": {
                 "description": "Genera una mappa dei bordi dal livello selezionato utilizzando il modello di rilevamento dei bordi Lineart Anime.",
                 "label": "Rilevamento bordi Lineart Anime"
-            },
-            "forMoreControl": "Per un maggiore controllo, fare clic su Avanzate qui sotto.",
-            "advanced": "Avanzate",
-            "processingLayerWith": "Elaborazione del livello con il filtro {{type}}."
+            }
         },
         "controlLayers_withCount_hidden": "Livelli di controllo ({{count}} nascosti)",
         "regionalGuidance_withCount_hidden": "Guida regionale ({{count}} nascosti)",
@@ -1952,6 +1862,8 @@
         "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",
@@ -1964,7 +1876,9 @@
         "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": {
@@ -1976,9 +1890,7 @@
             "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",
@@ -2023,55 +1935,9 @@
             "canvasGroup": "Tela",
             "newRasterLayer": "Nuovo Livello Raster",
             "saveCanvasToGallery": "Salva la Tela nella Galleria",
-            "saveToGalleryGroup": "Salva nella Galleria",
-            "newInpaintMask": "Nuova maschera Inpaint",
-            "newRegionalGuidance": "Nuova Guida Regionale"
+            "saveToGalleryGroup": "Salva nella Galleria"
         },
-        "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)",
-        "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",
-        "mergingLayers": "Unione dei livelli",
-        "controlLayerEmptyState": "<UploadButton>Carica un'immagine</UploadButton>, trascina un'immagine dalla <GalleryButton>galleria</GalleryButton> su questo livello oppure disegna sulla tela per iniziare.",
-        "useImage": "Usa immagine",
-        "resetGenerationSettings": "Ripristina impostazioni di generazione",
-        "referenceImageEmptyState": "Per iniziare, <UploadButton>carica un'immagine</UploadButton> oppure trascina un'immagine dalla <GalleryButton>galleria</GalleryButton> su questo livello.",
-        "asRasterLayer": "Come $t(controlLayers.rasterLayer)",
-        "asRasterLayerResize": "Come $t(controlLayers.rasterLayer) (Ridimensiona)",
-        "asControlLayer": "Come $t(controlLayers.controlLayer)",
-        "asControlLayerResize": "Come $t(controlLayers.controlLayer) (Ridimensiona)",
-        "newSession": "Nuova sessione",
-        "resetCanvasLayers": "Ripristina livelli Tela"
+        "newImg2ImgCanvasFromImage": "Nuova Immagine da immagine"
     },
     "ui": {
         "tabs": {
@@ -2103,9 +1969,7 @@
         "postProcessingMissingModelWarning": "Visita <LinkComponent>Gestione modelli</LinkComponent> per installare un modello di post-elaborazione (da immagine a immagine).",
         "exceedsMaxSize": "Le impostazioni di ampliamento superano il limite massimo delle dimensioni",
         "exceedsMaxSizeDetails": "Il limite massimo di ampliamento è {{maxUpscaleDimension}}x{{maxUpscaleDimension}} pixel. Prova un'immagine più piccola o diminuisci la scala selezionata.",
-        "upscale": "Amplia",
-        "incompatibleBaseModel": "Architettura del modello principale non supportata per l'ampliamento",
-        "incompatibleBaseModelDesc": "L'ampliamento è supportato solo per i modelli di architettura SD1.5 e SDXL. Cambia il modello principale per abilitare l'ampliamento."
+        "upscale": "Amplia"
     },
     "upsell": {
         "inviteTeammates": "Invita collaboratori",
@@ -2166,14 +2030,15 @@
         "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": {
-        "whatsNewInInvoke": "Novità in Invoke",
-        "readReleaseNotes": "Leggi le note di rilascio",
-        "watchRecentReleaseVideos": "Guarda i video su questa versione",
-        "watchUiUpdatesOverview": "Guarda le novità dell'interfaccia",
-        "items": [
-            "<StrongComponent>Flussi di lavoro</StrongComponent>: esegui un flusso di lavoro per una raccolta di immagini utilizzando il nuovo nodo <StrongComponent>Lotto di immagini</StrongComponent>.",
-            "<StrongComponent>Tela</StrongComponent>: elaborazione semplificata del livello di controllo e impostazioni di controllo predefinite migliorate."
-        ]
+        "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"
     },
     "system": {
         "logLevel": {
@@ -2199,67 +2064,5 @@
             "logNamespaces": "Elementi del registro"
         },
         "enableLogging": "Abilita la registrazione"
-    },
-    "supportVideos": {
-        "gettingStarted": "Iniziare",
-        "supportVideos": "Video di supporto",
-        "videos": {
-            "usingControlLayersAndReferenceGuides": {
-                "title": "Utilizzo di livelli di controllo e guide di riferimento",
-                "description": "Scopri come guidare la creazione delle tue immagini con livelli di controllo e immagini di riferimento."
-            },
-            "creatingYourFirstImage": {
-                "description": "Introduzione alla creazione di un'immagine da zero utilizzando gli strumenti di Invoke.",
-                "title": "Creazione della tua prima immagine"
-            },
-            "understandingImageToImageAndDenoising": {
-                "description": "Panoramica delle trasformazioni immagine-a-immagine e della riduzione del rumore in Invoke.",
-                "title": "Comprendere immagine-a-immagine e riduzione del rumore"
-            },
-            "howDoIDoImageToImageTransformation": {
-                "description": "Tutorial su come eseguire trasformazioni da immagine a immagine in Invoke.",
-                "title": "Come si esegue la trasformazione da immagine-a-immagine?"
-            },
-            "howDoIUseInpaintMasks": {
-                "title": "Come si usano le maschere Inpaint?",
-                "description": "Come applicare maschere inpaint per la correzione e la variazione delle immagini."
-            },
-            "howDoIOutpaint": {
-                "description": "Guida all'outpainting oltre i confini dell'immagine originale.",
-                "title": "Come posso eseguire l'outpainting?"
-            },
-            "exploringAIModelsAndConceptAdapters": {
-                "description": "Approfondisci i modelli di intelligenza artificiale e scopri come utilizzare gli adattatori concettuali per il controllo creativo.",
-                "title": "Esplorazione dei modelli di IA e degli adattatori concettuali"
-            },
-            "upscaling": {
-                "title": "Ampliamento",
-                "description": "Come ampliare le immagini con gli strumenti di Invoke per migliorarne la risoluzione."
-            },
-            "creatingAndComposingOnInvokesControlCanvas": {
-                "description": "Impara a comporre immagini utilizzando la tela di controllo di Invoke.",
-                "title": "Creare e comporre sulla tela di controllo di Invoke"
-            },
-            "howDoIGenerateAndSaveToTheGallery": {
-                "description": "Passaggi per generare e salvare le immagini nella galleria.",
-                "title": "Come posso generare e salvare nella Galleria?"
-            },
-            "howDoIEditOnTheCanvas": {
-                "title": "Come posso apportare modifiche sulla tela?",
-                "description": "Guida alla modifica delle immagini direttamente sulla tela."
-            },
-            "howDoIUseControlNetsAndControlLayers": {
-                "title": "Come posso utilizzare le Reti di Controllo e i Livelli di Controllo?",
-                "description": "Impara ad applicare livelli di controllo e reti di controllo alle tue immagini."
-            },
-            "howDoIUseGlobalIPAdaptersAndReferenceImages": {
-                "title": "Come si utilizzano gli adattatori IP globali e le immagini di riferimento?",
-                "description": "Introduzione all'aggiunta di immagini di riferimento e adattatori IP globali."
-            }
-        },
-        "controlCanvas": "Tela di Controllo",
-        "watch": "Guarda",
-        "studioSessionsDesc1": "Dai un'occhiata a <StudioSessionsPlaylistLink /> per approfondimenti su Invoke.",
-        "studioSessionsDesc2": "Unisciti al nostro <DiscordLink /> per partecipare alle sessioni live e fare domande. Le sessioni vengono caricate sulla playlist la settimana successiva."
     }
 }

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

@@ -16,7 +16,7 @@
         "discordLabel": "Discord",
         "nodes": "ワークフロー",
         "txt2img": "txt2img",
-        "postprocessing": "ポストプロセス",
+        "postprocessing": "Post Processing",
         "t2iAdapter": "T2I アダプター",
         "communityLabel": "コミュニティ",
         "dontAskMeAgain": "次回から確認しない",
@@ -71,8 +71,8 @@
         "orderBy": "並び順:",
         "enabled": "有効",
         "notInstalled": "未インストール",
-        "positivePrompt": "ポジティブプロンプト",
-        "negativePrompt": "ネガティブプロンプト",
+        "positivePrompt": "プロンプト",
+        "negativePrompt": "除外する要素",
         "selected": "選択済み",
         "aboutDesc": "Invokeを業務で利用する場合はマークしてください:",
         "beta": "ベータ",
@@ -80,20 +80,7 @@
         "editor": "エディタ",
         "safetensors": "Safetensors",
         "tab": "タブ",
-        "toResolve": "解決方法",
-        "openInViewer": "ビューアで開く",
-        "placeholderSelectAModel": "モデルを選択",
-        "clipboard": "クリップボード",
-        "apply": "適用",
-        "loadingImage": "画像をロード中",
-        "off": "オフ",
-        "view": "ビュー",
-        "edit": "編集",
-        "ok": "OK",
-        "reset": "リセット",
-        "none": "なし",
-        "new": "新規",
-        "close": "閉じる"
+        "toResolve": "解決方法"
     },
     "gallery": {
         "galleryImageSize": "画像のサイズ",
@@ -138,114 +125,12 @@
         "compareHelp1": "<Kbd>Alt</Kbd> キーを押しながらギャラリー画像をクリックするか、矢印キーを使用して比較画像を変更します。",
         "compareHelp3": "<Kbd>C</Kbd>を押して、比較した画像を入れ替えます。",
         "compareHelp4": "<Kbd>[Z</Kbd>]または<Kbd>[Esc</Kbd>]を押して終了します。",
-        "compareHelp2": "<Kbd>M</Kbd> キーを押して比較モードを切り替えます。",
-        "move": "移動",
-        "openViewer": "ビューアを開く",
-        "closeViewer": "ビューアを閉じる",
-        "exitSearch": "画像検索を終了",
-        "oldestFirst": "最古から",
-        "showStarredImagesFirst": "スター付き画像を最初に",
-        "exitBoardSearch": "ボード検索を終了",
-        "showArchivedBoards": "アーカイブされたボードを表示",
-        "searchImages": "メタデータで検索",
-        "gallery": "ギャラリー",
-        "newestFirst": "最新から",
-        "jump": "ジャンプ",
-        "go": "進む",
-        "sortDirection": "並び替え順",
-        "displayBoardSearch": "ボード検索",
-        "displaySearch": "画像を検索",
-        "boardsSettings": "ボード設定",
-        "imagesSettings": "ギャラリー画像設定"
+        "compareHelp2": "<Kbd>M</Kbd> キーを押して比較モードを切り替えます。"
     },
     "hotkeys": {
         "searchHotkeys": "ホットキーを検索",
         "clearSearch": "検索をクリア",
-        "noHotkeysFound": "ホットキーが見つかりません",
-        "viewer": {
-            "runPostprocessing": {
-                "title": "ポストプロセスを実行"
-            },
-            "useSize": {
-                "title": "サイズを使用"
-            },
-            "recallPrompts": {
-                "title": "プロンプトを再使用"
-            },
-            "recallAll": {
-                "title": "全てのメタデータを再使用"
-            },
-            "recallSeed": {
-                "title": "シード値を再使用"
-            }
-        },
-        "canvas": {
-            "redo": {
-                "title": "やり直し"
-            },
-            "transformSelected": {
-                "title": "変形"
-            },
-            "undo": {
-                "title": "取り消し"
-            },
-            "selectEraserTool": {
-                "title": "消しゴムツール"
-            },
-            "cancelTransform": {
-                "title": "変形をキャンセル"
-            },
-            "resetSelected": {
-                "title": "レイヤーをリセット"
-            },
-            "applyTransform": {
-                "title": "変形を適用"
-            },
-            "selectColorPickerTool": {
-                "title": "スポイトツール"
-            },
-            "fitBboxToCanvas": {
-                "title": "バウンディングボックスをキャンバスにフィット"
-            },
-            "selectBrushTool": {
-                "title": "ブラシツール"
-            },
-            "selectMoveTool": {
-                "title": "移動ツール"
-            },
-            "selectBboxTool": {
-                "title": "バウンディングボックスツール"
-            },
-            "title": "キャンバス",
-            "fitLayersToCanvas": {
-                "title": "レイヤーをキャンバスにフィット"
-            }
-        },
-        "workflows": {
-            "undo": {
-                "title": "取り消し"
-            },
-            "redo": {
-                "title": "やり直し"
-            }
-        },
-        "app": {
-            "toggleLeftPanel": {
-                "title": "左パネルをトグル",
-                "desc": "左パネルを表示または非表示。"
-            },
-            "title": "アプリケーション",
-            "invoke": {
-                "title": "Invoke"
-            },
-            "cancelQueueItem": {
-                "title": "キャンセル"
-            },
-            "clearQueue": {
-                "title": "キューをクリア"
-            }
-        },
-        "hotkeys": "ホットキー"
+        "noHotkeysFound": "ホットキーが見つかりません"
     },
     "modelManager": {
         "modelManager": "モデルマネージャ",
@@ -280,7 +165,7 @@
         "convertToDiffusers": "ディフューザーに変換",
         "alpha": "アルファ",
         "modelConverted": "モデル変換が完了しました",
-        "predictionType": "予測タイプ（SD 2.x モデルおよび一部のSD 1.x モデル用）",
+        "predictionType": "予測タイプ（安定したディフュージョン 2.x モデルおよび一部の安定したディフュージョン 1.x モデル用）",
         "selectModel": "モデルを選択",
         "advanced": "高度な設定",
         "modelDeleted": "モデルが削除されました",
@@ -293,9 +178,7 @@
         "convertToDiffusersHelpText1": "このモデルは 🧨 Diffusers フォーマットに変換されます。",
         "convertToDiffusersHelpText3": "チェックポイントファイルは、InvokeAIルートフォルダ内にある場合、ディスクから削除されます。カスタムロケーションにある場合は、削除されません。",
         "convertToDiffusersHelpText4": "これは一回限りのプロセスです。コンピュータの仕様によっては、約30秒から60秒かかる可能性があります。",
-        "cancel": "キャンセル",
-        "uploadImage": "画像をアップロード",
-        "addModels": "モデルを追加"
+        "cancel": "キャンセル"
     },
     "parameters": {
         "images": "画像",
@@ -317,19 +200,7 @@
         "info": "情報",
         "showOptionsPanel": "オプションパネルを表示",
         "iterations": "生成回数",
-        "general": "基本設定",
-        "setToOptimalSize": "サイズをモデルに最適化",
-        "invoke": {
-            "addingImagesTo": "画像の追加先"
-        },
-        "aspect": "縦横比",
-        "lockAspectRatio": "縦横比を固定",
-        "scheduler": "スケジューラー",
-        "sendToUpscale": "アップスケーラーに転送",
-        "useSize": "サイズを使用",
-        "postProcessing": "ポストプロセス (Shift + U)",
-        "denoisingStrength": "ノイズ除去強度",
-        "recallMetadata": "メタデータを再使用"
+        "general": "基本設定"
     },
     "settings": {
         "models": "モデル",
@@ -342,11 +213,7 @@
     },
     "toast": {
         "uploadFailed": "アップロード失敗",
-        "imageCopied": "画像をコピー",
-        "imageUploadFailed": "画像のアップロードに失敗しました",
-        "uploadFailedInvalidUploadDesc": "画像はPNGかJPGである必要があります。",
-        "sentToUpscale": "アップスケーラーに転送しました",
-        "imageUploaded": "画像をアップロードしました"
+        "imageCopied": "画像をコピー"
     },
     "accessibility": {
         "invokeProgressBar": "進捗バー",
@@ -359,12 +226,10 @@
         "resetUI": "$t(accessibility.reset) UI",
         "mode": "モード:",
         "about": "Invoke について",
-        "submitSupportTicket": "サポート依頼を送信する",
-        "uploadImages": "画像をアップロード",
-        "toggleLeftPanel": "左パネルをトグル (T)",
-        "toggleRightPanel": "右パネルをトグル (G)"
+        "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",
@@ -373,8 +238,7 @@
         "scheduler": "スケジューラー",
         "positivePrompt": "ポジティブプロンプト",
         "strength": "Image to Image 強度",
-        "recallParameters": "パラメータを再使用",
-        "recallParameter": "{{label}} を再使用"
+        "recallParameters": "パラメータを呼び出す"
     },
     "queue": {
         "queueEmpty": "キューが空です",
@@ -434,22 +298,14 @@
         "prune": "刈り込み",
         "prompts_other": "プロンプト",
         "iterations_other": "繰り返し",
-        "generations_other": "生成",
-        "canvas": "キャンバス",
-        "workflows": "ワークフロー",
-        "upscaling": "アップスケール",
-        "generation": "生成",
-        "other": "その他",
-        "gallery": "ギャラリー"
+        "generations_other": "生成"
     },
     "models": {
         "noMatchingModels": "一致するモデルがありません",
         "loading": "読み込み中",
         "noMatchingLoRAs": "一致するLoRAがありません",
         "noModelsAvailable": "使用可能なモデルがありません",
-        "selectModel": "モデルを選択してください",
-        "concepts": "コンセプト",
-        "addLora": "LoRAを追加"
+        "selectModel": "モデルを選択してください"
     },
     "nodes": {
         "addNode": "ノードを追加",
@@ -484,8 +340,7 @@
         "cannotConnectOutputToOutput": "出力から出力には接続できません",
         "cannotConnectToSelf": "自身のノードには接続できません",
         "colorCodeEdges": "カラー-Code Edges",
-        "loadingNodes": "ノードを読み込み中...",
-        "scheduler": "スケジューラー"
+        "loadingNodes": "ノードを読み込み中..."
     },
     "boards": {
         "autoAddBoard": "自動追加するボード",
@@ -508,18 +363,7 @@
         "deleteBoardAndImages": "ボードと画像の削除",
         "deleteBoardOnly": "ボードのみ削除",
         "deletedBoardsCannotbeRestored": "削除されたボードは復元できません",
-        "movingImagesToBoard_other": "{{count}} の画像をボードに移動:",
-        "hideBoards": "ボードを隠す",
-        "assetsWithCount_other": "{{count}} のアセット",
-        "addPrivateBoard": "プライベートボードを追加",
-        "addSharedBoard": "共有ボードを追加",
-        "boards": "ボード",
-        "private": "プライベートボード",
-        "shared": "共有ボード",
-        "archiveBoard": "ボードをアーカイブ",
-        "archived": "アーカイブ完了",
-        "unarchiveBoard": "アーカイブされていないボード",
-        "imagesWithCount_other": "{{count}} の画像"
+        "movingImagesToBoard_other": "{{count}} の画像をボードに移動:"
     },
     "invocationCache": {
         "invocationCache": "呼び出しキャッシュ",
@@ -544,33 +388,6 @@
             "paragraphs": [
                 "生成された画像の縦横比。"
             ]
-        },
-        "regionalGuidanceAndReferenceImage": {
-            "heading": "領域ガイダンスと領域参照画像"
-        },
-        "regionalReferenceImage": {
-            "heading": "領域参照画像"
-        },
-        "paramScheduler": {
-            "heading": "スケジューラー"
-        },
-        "regionalGuidance": {
-            "heading": "領域ガイダンス"
-        },
-        "rasterLayer": {
-            "heading": "ラスターレイヤー"
-        },
-        "globalReferenceImage": {
-            "heading": "全域参照画像"
-        },
-        "paramUpscaleMethod": {
-            "heading": "アップスケール手法"
-        },
-        "upscaleModel": {
-            "heading": "アップスケールモデル"
-        },
-        "paramAspect": {
-            "heading": "縦横比"
         }
     },
     "accordions": {
@@ -611,79 +428,5 @@
         "tabs": {
             "queue": "キュー"
         }
-    },
-    "controlLayers": {
-        "globalReferenceImage_withCount_other": "全域参照画像",
-        "regionalReferenceImage": "領域参照画像",
-        "saveLayerToAssets": "レイヤーをアセットに保存",
-        "global": "全域",
-        "inpaintMasks_withCount_hidden": "インペイントマスク ({{count}} hidden)",
-        "opacity": "透明度",
-        "canvasContextMenu": {
-            "newRegionalGuidance": "新規領域ガイダンス",
-            "bboxGroup": "バウンディングボックスから作成",
-            "cropCanvasToBbox": "キャンバスをバウンディングボックスでクロップ",
-            "newGlobalReferenceImage": "新規全域参照画像",
-            "newRegionalReferenceImage": "新規領域参照画像"
-        },
-        "regionalGuidance": "領域ガイダンス",
-        "globalReferenceImage": "全域参照画像",
-        "moveForward": "前面へ移動",
-        "copyInpaintMaskTo": "$t(controlLayers.inpaintMask) をコピー",
-        "transform": {
-            "fitToBbox": "バウンディングボックスにフィット",
-            "transform": "変形",
-            "apply": "適用",
-            "cancel": "キャンセル",
-            "reset": "リセット"
-        },
-        "cropLayerToBbox": "レイヤーをバウンディングボックスでクロップ",
-        "convertInpaintMaskTo": "$t(controlLayers.inpaintMask)を変換",
-        "regionalGuidance_withCount_other": "領域ガイダンス",
-        "tool": {
-            "colorPicker": "スポイト",
-            "brush": "ブラシ",
-            "rectangle": "矩形",
-            "move": "移動",
-            "eraser": "消しゴム"
-        },
-        "saveCanvasToGallery": "キャンバスをギャラリーに保存",
-        "saveBboxToGallery": "バウンディングボックスをギャラリーへ保存",
-        "moveToBack": "最背面へ移動",
-        "duplicate": "複製",
-        "addLayer": "レイヤーを追加",
-        "rasterLayer": "ラスターレイヤー",
-        "inpaintMasks_withCount_visible": "({{count}}) インペイントマスク",
-        "regional": "領域",
-        "rectangle": "矩形",
-        "moveBackward": "背面へ移動",
-        "moveToFront": "最前面へ移動",
-        "mergeDown": "レイヤーを統合",
-        "inpaintMask_withCount_other": "インペイントマスク",
-        "canvas": "キャンバス",
-        "fitBboxToLayers": "バウンディングボックスをレイヤーにフィット",
-        "removeBookmark": "ブックマークを外す",
-        "savedToGalleryOk": "ギャラリーに保存しました"
-    },
-    "stylePresets": {
-        "clearTemplateSelection": "選択したテンプレートをクリア",
-        "choosePromptTemplate": "プロンプトテンプレートを選択",
-        "myTemplates": "自分のテンプレート",
-        "flatten": "選択中のテンプレートをプロンプトに展開",
-        "uploadImage": "画像をアップロード",
-        "defaultTemplates": "デフォルトテンプレート",
-        "createPromptTemplate": "プロンプトテンプレートを作成",
-        "promptTemplateCleared": "プロンプトテンプレートをクリアしました",
-        "searchByName": "名前で検索",
-        "toggleViewMode": "表示モードを切り替え"
-    },
-    "upscaling": {
-        "upscaleModel": "アップスケールモデル",
-        "postProcessingModel": "ポストプロセスモデル",
-        "upscale": "アップスケール"
-    },
-    "sdxl": {
-        "denoisingStrength": "ノイズ除去強度",
-        "scheduler": "スケジューラー"
     }
 }

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

@@ -155,6 +155,7 @@
         "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",
@@ -236,6 +237,7 @@
                 "controlAdapterIncompatibleBaseModel": "niet-compatibele basismodel voor controle-adapter",
                 "ipAdapterIncompatibleBaseModel": "niet-compatibele basismodel voor IP-adapter",
                 "ipAdapterNoImageSelected": "geen afbeelding voor IP-adapter geselecteerd",
+                "rgNoRegion": "geen gebied geselecteerd",
                 "rgNoPromptsOrIPAdapters": "geen tekstprompts of IP-adapters",
                 "ipAdapterNoModelSelected": "geen IP-adapter geselecteerd"
             }
@@ -664,6 +666,7 @@
         }
     },
     "metadata": {
+        "seamless": "Naadloos",
         "positivePrompt": "Positieve prompt",
         "negativePrompt": "Negatieve prompt",
         "generationMode": "Genereermodus",

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

@@ -10,24 +10,7 @@
         "load": "Załaduj",
         "statusDisconnected": "Odłączono od serwera",
         "githubLabel": "GitHub",
-        "discordLabel": "Discord",
-        "clipboard": "Schowek",
-        "aboutDesc": "Wykorzystujesz Invoke do pracy? Sprawdź:",
-        "ai": "SI",
-        "areYouSure": "Czy jesteś pewien?",
-        "copyError": "$t(gallery.copy) Błąd",
-        "apply": "Zastosuj",
-        "copy": "Kopiuj",
-        "or": "albo",
-        "add": "Dodaj",
-        "off": "Wyłączony",
-        "accept": "Zaakceptuj",
-        "cancel": "Anuluj",
-        "advanced": "Zawansowane",
-        "back": "Do tyłu",
-        "auto": "Automatyczny",
-        "beta": "Beta",
-        "close": "Wyjdź"
+        "discordLabel": "Discord"
     },
     "gallery": {
         "galleryImageSize": "Rozmiar obrazów",
@@ -82,42 +65,6 @@
         "uploadImage": "Wgrywanie obrazu",
         "previousImage": "Poprzedni obraz",
         "nextImage": "Następny obraz",
-        "menu": "Menu",
-        "mode": "Tryb"
-    },
-    "boards": {
-        "cancel": "Anuluj",
-        "noBoards": "Brak tablic typu {{boardType}}",
-        "imagesWithCount_one": "{{count}} zdjęcie",
-        "imagesWithCount_few": "{{count}} zdjęcia",
-        "imagesWithCount_many": "{{count}} zdjęcia",
-        "private": "Prywatne tablice",
-        "updateBoardError": "Błąd aktualizacji tablicy",
-        "uncategorized": "Nieskategoryzowane",
-        "selectBoard": "Wybierz tablicę",
-        "downloadBoard": "Pobierz tablice",
-        "loading": "Ładowanie...",
-        "move": "Przenieś",
-        "noMatching": "Brak pasujących tablic"
-    },
-    "accordions": {
-        "compositing": {
-            "title": "Kompozycja",
-            "infillTab": "Inskrypcja",
-            "coherenceTab": "Przebieg Koherencji"
-        },
-        "generation": {
-            "title": "Generowanie"
-        },
-        "image": {
-            "title": "Zdjęcie"
-        },
-        "advanced": {
-            "options": "$t(accordions.advanced.title) Opcje",
-            "title": "Zaawansowane"
-        },
-        "control": {
-            "title": "Kontrola"
-        }
+        "menu": "Menu"
     }
 }