Update DepthAnything post-processing logic to avoid artifacts caused by numerical overflow.

Lint

.github/pull_request_template.md

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

SECURITY.md

@@ -0,0 +1,14 @@
+# 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/nodes/defaultNodes.md

@@ -99,7 +99,6 @@ 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                                                                                                                                |

invokeai/app/api/routers/app_info.py

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

invokeai/app/invocations/baseinvocation.py

@@ -63,6 +63,7 @@ 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"
@@ -70,6 +71,7 @@ class Classification(str, Enum, metaclass=MetaEnum):
     Prototype = "prototype"
     Deprecated = "deprecated"
     Internal = "internal"
+    Special = "special"
 
 
 class UIConfigBase(BaseModel):

invokeai/app/invocations/blend_latents.py

@@ -1,98 +1,120 @@
-from typing import Any, Union
+from typing import Optional, 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, Input, InputField, LatentsField
+from invokeai.app.invocations.fields import FieldDescriptions, ImageField, 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"],
+    tags=["latents", "blend", "mask"],
     category="latents",
-    version="1.0.3",
+    version="1.1.0",
 )
 class BlendLatentsInvocation(BaseInvocation):
-    """Blend two latents using a given alpha. Latents must have same size."""
+    """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."""
 
-    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)
+    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
 
     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 Exception("Latents to blend must be the same size.")
+            raise ValueError("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
-        bl = slerp(self.alpha, latents_a, latents_b)
-        assert isinstance(bl, torch.Tensor)
-        blended_latents: torch.Tensor = bl  # for type checking convenience
+        blended_latents = slerp(self.alpha, latents_a, latents_b, device)
 
         # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
         blended_latents = blended_latents.to("cpu")
-
-        TorchDevice.empty_cache()
+        torch.cuda.empty_cache()
 
         name = context.tensors.save(tensor=blended_latents)
-        return LatentsOutput.build(latents_name=name, latents=blended_latents, seed=self.latents_a.seed)
+        return LatentsOutput.build(latents_name=name, latents=blended_latents)

invokeai/app/invocations/compel.py

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

invokeai/app/invocations/create_denoise_mask.py

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

invokeai/app/invocations/create_gradient_mask.py

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

invokeai/app/invocations/fields.py

@@ -41,6 +41,7 @@ class UIType(str, Enum, metaclass=MetaEnum):
     # region Model Field Types
     MainModel = "MainModelField"
     FluxMainModel = "FluxMainModelField"
+    SD3MainModel = "SD3MainModelField"
     SDXLMainModel = "SDXLMainModelField"
     SDXLRefinerModel = "SDXLRefinerModelField"
     ONNXModel = "ONNXModelField"
@@ -52,6 +53,8 @@ class UIType(str, Enum, metaclass=MetaEnum):
     T2IAdapterModel = "T2IAdapterModelField"
     T5EncoderModel = "T5EncoderModelField"
     CLIPEmbedModel = "CLIPEmbedModelField"
+    CLIPLEmbedModel = "CLIPLEmbedModelField"
+    CLIPGEmbedModel = "CLIPGEmbedModelField"
     SpandrelImageToImageModel = "SpandrelImageToImageModelField"
     # endregion
 
@@ -131,8 +134,10 @@ 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"
@@ -140,6 +145,7 @@ 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"
@@ -246,6 +252,12 @@ class FluxConditioningField(BaseModel):
     conditioning_name: str = Field(description="The name of conditioning tensor")
 
 
+class SD3ConditioningField(BaseModel):
+    """A conditioning tensor primitive value"""
+
+    conditioning_name: str = Field(description="The name of conditioning tensor")
+
+
 class ConditioningField(BaseModel):
     """A conditioning tensor primitive value"""
 

invokeai/app/invocations/flux_denoise.py

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

invokeai/app/invocations/flux_model_loader.py

@@ -0,0 +1,89 @@
+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

@@ -5,7 +5,7 @@ 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, Input, InputField
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, UIComponent
 from invokeai.app.invocations.model import CLIPField, T5EncoderField
 from invokeai.app.invocations.primitives import FluxConditioningOutput
 from invokeai.app.services.shared.invocation_context import InvocationContext
@@ -41,7 +41,10 @@ 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.")
+    prompt: str = InputField(
+        description="Text prompt to encode.",
+        ui_component=UIComponent.Textarea,
+    )
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> FluxConditioningOutput:
@@ -71,6 +74,7 @@ class FluxTextEncoderInvocation(BaseInvocation):
 
             t5_encoder = HFEncoder(t5_text_encoder, t5_tokenizer, False, self.t5_max_seq_len)
 
+            context.util.signal_progress("Running T5 encoder")
             prompt_embeds = t5_encoder(prompt)
 
         assert isinstance(prompt_embeds, torch.Tensor)
@@ -111,6 +115,7 @@ class FluxTextEncoderInvocation(BaseInvocation):
 
             clip_encoder = HFEncoder(clip_text_encoder, clip_tokenizer, True, 77)
 
+            context.util.signal_progress("Running CLIP encoder")
             pooled_prompt_embeds = clip_encoder(prompt)
 
         assert isinstance(pooled_prompt_embeds, torch.Tensor)

invokeai/app/invocations/flux_vae_decode.py

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

invokeai/app/invocations/flux_vae_encode.py

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

invokeai/app/invocations/image_panels.py

@@ -0,0 +1,59 @@
+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

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

invokeai/app/invocations/latents_to_image.py

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

invokeai/app/invocations/metadata.py

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

invokeai/app/invocations/model.py

@@ -1,5 +1,5 @@
 import copy
-from typing import List, Literal, Optional
+from typing import List, Optional
 
 from pydantic import BaseModel, Field
 
@@ -13,11 +13,9 @@ 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,
 )
@@ -139,78 +137,6 @@ 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

@@ -1,43 +1,4 @@
-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
@@ -65,191 +26,3 @@ 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

@@ -4,7 +4,13 @@ from typing import Optional
 
 import torch
 
-from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
+from invokeai.app.invocations.baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    Classification,
+    invocation,
+    invocation_output,
+)
 from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
 from invokeai.app.invocations.fields import (
     BoundingBoxField,
@@ -18,6 +24,7 @@ from invokeai.app.invocations.fields import (
     InputField,
     LatentsField,
     OutputField,
+    SD3ConditioningField,
     TensorField,
     UIComponent,
 )
@@ -426,6 +433,17 @@ class FluxConditioningOutput(BaseInvocationOutput):
         return cls(conditioning=FluxConditioningField(conditioning_name=conditioning_name))
 
 
+@invocation_output("sd3_conditioning_output")
+class SD3ConditioningOutput(BaseInvocationOutput):
+    """Base class for nodes that output a single SD3 conditioning tensor"""
+
+    conditioning: SD3ConditioningField = OutputField(description=FieldDescriptions.cond)
+
+    @classmethod
+    def build(cls, conditioning_name: str) -> "SD3ConditioningOutput":
+        return cls(conditioning=SD3ConditioningField(conditioning_name=conditioning_name))
+
+
 @invocation_output("conditioning_output")
 class ConditioningOutput(BaseInvocationOutput):
     """Base class for nodes that output a single conditioning tensor"""
@@ -521,3 +539,23 @@ 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

@@ -0,0 +1,338 @@
+from typing import Callable, Optional, Tuple
+
+import torch
+import torchvision.transforms as tv_transforms
+from diffusers.models.transformers.transformer_sd3 import SD3Transformer2DModel
+from torchvision.transforms.functional import resize as tv_resize
+from tqdm import tqdm
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, invocation
+from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
+from invokeai.app.invocations.fields import (
+    DenoiseMaskField,
+    FieldDescriptions,
+    Input,
+    InputField,
+    LatentsField,
+    SD3ConditioningField,
+    WithBoard,
+    WithMetadata,
+)
+from invokeai.app.invocations.model import TransformerField
+from invokeai.app.invocations.primitives import LatentsOutput
+from invokeai.app.invocations.sd3_text_encoder import SD3_T5_MAX_SEQ_LEN
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.flux.sampling_utils import clip_timestep_schedule_fractional
+from invokeai.backend.model_manager.config import BaseModelType
+from invokeai.backend.sd3.extensions.inpaint_extension import InpaintExtension
+from invokeai.backend.stable_diffusion.diffusers_pipeline import PipelineIntermediateState
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import SD3ConditioningInfo
+from invokeai.backend.util.devices import TorchDevice
+
+
+@invocation(
+    "sd3_denoise",
+    title="SD3 Denoise",
+    tags=["image", "sd3"],
+    category="image",
+    version="1.1.0",
+    classification=Classification.Prototype,
+)
+class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
+    """Run denoising process with a SD3 model."""
+
+    # If latents is provided, this means we are doing image-to-image.
+    latents: Optional[LatentsField] = InputField(
+        default=None, description=FieldDescriptions.latents, input=Input.Connection
+    )
+    # denoise_mask is used for image-to-image inpainting. Only the masked region is modified.
+    denoise_mask: Optional[DenoiseMaskField] = InputField(
+        default=None, description=FieldDescriptions.denoise_mask, input=Input.Connection
+    )
+    denoising_start: float = InputField(default=0.0, ge=0, le=1, description=FieldDescriptions.denoising_start)
+    denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
+    transformer: TransformerField = InputField(
+        description=FieldDescriptions.sd3_model, input=Input.Connection, title="Transformer"
+    )
+    positive_conditioning: SD3ConditioningField = InputField(
+        description=FieldDescriptions.positive_cond, input=Input.Connection
+    )
+    negative_conditioning: SD3ConditioningField = InputField(
+        description=FieldDescriptions.negative_cond, input=Input.Connection
+    )
+    cfg_scale: float | list[float] = InputField(default=3.5, description=FieldDescriptions.cfg_scale, title="CFG Scale")
+    width: int = InputField(default=1024, multiple_of=16, description="Width of the generated image.")
+    height: int = InputField(default=1024, multiple_of=16, description="Height of the generated image.")
+    steps: int = InputField(default=10, gt=0, description=FieldDescriptions.steps)
+    seed: int = InputField(default=0, description="Randomness seed for reproducibility.")
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        latents = self._run_diffusion(context)
+        latents = latents.detach().to("cpu")
+
+        name = context.tensors.save(tensor=latents)
+        return LatentsOutput.build(latents_name=name, latents=latents, seed=None)
+
+    def _prep_inpaint_mask(self, context: InvocationContext, latents: torch.Tensor) -> torch.Tensor | None:
+        """Prepare the inpaint mask.
+        - Loads the mask
+        - Resizes if necessary
+        - Casts to same device/dtype as latents
+
+        Args:
+            context (InvocationContext): The invocation context, for loading the inpaint mask.
+            latents (torch.Tensor): A latent image tensor. Used to determine the target shape, device, and dtype for the
+                inpaint mask.
+
+        Returns:
+            torch.Tensor | None: Inpaint mask. Values of 0.0 represent the regions to be fully denoised, and 1.0
+                represent the regions to be preserved.
+        """
+        if self.denoise_mask is None:
+            return None
+        mask = context.tensors.load(self.denoise_mask.mask_name)
+
+        # The input denoise_mask contains values in [0, 1], where 0.0 represents the regions to be fully denoised, and
+        # 1.0 represents the regions to be preserved.
+        # We invert the mask so that the regions to be preserved are 0.0 and the regions to be denoised are 1.0.
+        mask = 1.0 - mask
+
+        _, _, latent_height, latent_width = latents.shape
+        mask = tv_resize(
+            img=mask,
+            size=[latent_height, latent_width],
+            interpolation=tv_transforms.InterpolationMode.BILINEAR,
+            antialias=False,
+        )
+
+        mask = mask.to(device=latents.device, dtype=latents.dtype)
+        return mask
+
+    def _load_text_conditioning(
+        self,
+        context: InvocationContext,
+        conditioning_name: str,
+        joint_attention_dim: int,
+        dtype: torch.dtype,
+        device: torch.device,
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        # Load the conditioning data.
+        cond_data = context.conditioning.load(conditioning_name)
+        assert len(cond_data.conditionings) == 1
+        sd3_conditioning = cond_data.conditionings[0]
+        assert isinstance(sd3_conditioning, SD3ConditioningInfo)
+        sd3_conditioning = sd3_conditioning.to(dtype=dtype, device=device)
+
+        t5_embeds = sd3_conditioning.t5_embeds
+        if t5_embeds is None:
+            t5_embeds = torch.zeros(
+                (1, SD3_T5_MAX_SEQ_LEN, joint_attention_dim),
+                device=device,
+                dtype=dtype,
+            )
+
+        clip_prompt_embeds = torch.cat([sd3_conditioning.clip_l_embeds, sd3_conditioning.clip_g_embeds], dim=-1)
+        clip_prompt_embeds = torch.nn.functional.pad(
+            clip_prompt_embeds, (0, t5_embeds.shape[-1] - clip_prompt_embeds.shape[-1])
+        )
+
+        prompt_embeds = torch.cat([clip_prompt_embeds, t5_embeds], dim=-2)
+        pooled_prompt_embeds = torch.cat(
+            [sd3_conditioning.clip_l_pooled_embeds, sd3_conditioning.clip_g_pooled_embeds], dim=-1
+        )
+
+        return prompt_embeds, pooled_prompt_embeds
+
+    def _get_noise(
+        self,
+        num_samples: int,
+        num_channels_latents: int,
+        height: int,
+        width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        seed: int,
+    ) -> torch.Tensor:
+        # We always generate noise on the same device and dtype then cast to ensure consistency across devices/dtypes.
+        rand_device = "cpu"
+        rand_dtype = torch.float16
+
+        return torch.randn(
+            num_samples,
+            num_channels_latents,
+            int(height) // LATENT_SCALE_FACTOR,
+            int(width) // LATENT_SCALE_FACTOR,
+            device=rand_device,
+            dtype=rand_dtype,
+            generator=torch.Generator(device=rand_device).manual_seed(seed),
+        ).to(device=device, dtype=dtype)
+
+    def _prepare_cfg_scale(self, num_timesteps: int) -> list[float]:
+        """Prepare the CFG scale list.
+
+        Args:
+            num_timesteps (int): The number of timesteps in the scheduler. Could be different from num_steps depending
+            on the scheduler used (e.g. higher order schedulers).
+
+        Returns:
+            list[float]: _description_
+        """
+        if isinstance(self.cfg_scale, float):
+            cfg_scale = [self.cfg_scale] * num_timesteps
+        elif isinstance(self.cfg_scale, list):
+            assert len(self.cfg_scale) == num_timesteps
+            cfg_scale = self.cfg_scale
+        else:
+            raise ValueError(f"Invalid CFG scale type: {type(self.cfg_scale)}")
+
+        return cfg_scale
+
+    def _run_diffusion(
+        self,
+        context: InvocationContext,
+    ):
+        inference_dtype = TorchDevice.choose_torch_dtype()
+        device = TorchDevice.choose_torch_device()
+
+        transformer_info = context.models.load(self.transformer.transformer)
+
+        # Load/process the conditioning data.
+        # TODO(ryand): Make CFG optional.
+        do_classifier_free_guidance = True
+        pos_prompt_embeds, pos_pooled_prompt_embeds = self._load_text_conditioning(
+            context=context,
+            conditioning_name=self.positive_conditioning.conditioning_name,
+            joint_attention_dim=transformer_info.model.config.joint_attention_dim,
+            dtype=inference_dtype,
+            device=device,
+        )
+        neg_prompt_embeds, neg_pooled_prompt_embeds = self._load_text_conditioning(
+            context=context,
+            conditioning_name=self.negative_conditioning.conditioning_name,
+            joint_attention_dim=transformer_info.model.config.joint_attention_dim,
+            dtype=inference_dtype,
+            device=device,
+        )
+        # TODO(ryand): Support both sequential and batched CFG inference.
+        prompt_embeds = torch.cat([neg_prompt_embeds, pos_prompt_embeds], dim=0)
+        pooled_prompt_embeds = torch.cat([neg_pooled_prompt_embeds, pos_pooled_prompt_embeds], dim=0)
+
+        # Prepare the timestep schedule.
+        # We add an extra step to the end to account for the final timestep of 0.0.
+        timesteps: list[float] = torch.linspace(1, 0, self.steps + 1).tolist()
+        # Clip the timesteps schedule based on denoising_start and denoising_end.
+        timesteps = clip_timestep_schedule_fractional(timesteps, self.denoising_start, self.denoising_end)
+        total_steps = len(timesteps) - 1
+
+        # Prepare the CFG scale list.
+        cfg_scale = self._prepare_cfg_scale(total_steps)
+
+        # Load the input latents, if provided.
+        init_latents = context.tensors.load(self.latents.latents_name) if self.latents else None
+        if init_latents is not None:
+            init_latents = init_latents.to(device=device, dtype=inference_dtype)
+
+        # Generate initial latent noise.
+        num_channels_latents = transformer_info.model.config.in_channels
+        assert isinstance(num_channels_latents, int)
+        noise = self._get_noise(
+            num_samples=1,
+            num_channels_latents=num_channels_latents,
+            height=self.height,
+            width=self.width,
+            dtype=inference_dtype,
+            device=device,
+            seed=self.seed,
+        )
+
+        # Prepare input latent image.
+        if init_latents is not None:
+            # Noise the init_latents by the appropriate amount for the first timestep.
+            t_0 = timesteps[0]
+            latents = t_0 * noise + (1.0 - t_0) * init_latents
+        else:
+            # init_latents are not provided, so we are not doing image-to-image (i.e. we are starting from pure noise).
+            if self.denoising_start > 1e-5:
+                raise ValueError("denoising_start should be 0 when initial latents are not provided.")
+            latents = noise
+
+        # If len(timesteps) == 1, then short-circuit. We are just noising the input latents, but not taking any
+        # denoising steps.
+        if len(timesteps) <= 1:
+            return latents
+
+        # Prepare inpaint extension.
+        inpaint_mask = self._prep_inpaint_mask(context, latents)
+        inpaint_extension: InpaintExtension | None = None
+        if inpaint_mask is not None:
+            assert init_latents is not None
+            inpaint_extension = InpaintExtension(
+                init_latents=init_latents,
+                inpaint_mask=inpaint_mask,
+                noise=noise,
+            )
+
+        step_callback = self._build_step_callback(context)
+
+        step_callback(
+            PipelineIntermediateState(
+                step=0,
+                order=1,
+                total_steps=total_steps,
+                timestep=int(timesteps[0]),
+                latents=latents,
+            ),
+        )
+
+        with transformer_info.model_on_device() as (cached_weights, transformer):
+            assert isinstance(transformer, SD3Transformer2DModel)
+
+            # 6. Denoising loop
+            for step_idx, (t_curr, t_prev) in tqdm(list(enumerate(zip(timesteps[:-1], timesteps[1:], strict=True)))):
+                # Expand the latents if we are doing CFG.
+                latent_model_input = torch.cat([latents] * 2) if do_classifier_free_guidance else latents
+                # Expand the timestep to match the latent model input.
+                # Multiply by 1000 to match the default FlowMatchEulerDiscreteScheduler num_train_timesteps.
+                timestep = torch.tensor([t_curr * 1000], device=device).expand(latent_model_input.shape[0])
+
+                noise_pred = transformer(
+                    hidden_states=latent_model_input,
+                    timestep=timestep,
+                    encoder_hidden_states=prompt_embeds,
+                    pooled_projections=pooled_prompt_embeds,
+                    joint_attention_kwargs=None,
+                    return_dict=False,
+                )[0]
+
+                # Apply CFG.
+                if do_classifier_free_guidance:
+                    noise_pred_uncond, noise_pred_cond = noise_pred.chunk(2)
+                    noise_pred = noise_pred_uncond + cfg_scale[step_idx] * (noise_pred_cond - noise_pred_uncond)
+
+                # Compute the previous noisy sample x_t -> x_t-1.
+                latents_dtype = latents.dtype
+                latents = latents.to(dtype=torch.float32)
+                latents = latents + (t_prev - t_curr) * noise_pred
+                latents = latents.to(dtype=latents_dtype)
+
+                if inpaint_extension is not None:
+                    latents = inpaint_extension.merge_intermediate_latents_with_init_latents(latents, t_prev)
+
+                step_callback(
+                    PipelineIntermediateState(
+                        step=step_idx + 1,
+                        order=1,
+                        total_steps=total_steps,
+                        timestep=int(t_curr),
+                        latents=latents,
+                    ),
+                )
+
+        return latents
+
+    def _build_step_callback(self, context: InvocationContext) -> Callable[[PipelineIntermediateState], None]:
+        def step_callback(state: PipelineIntermediateState) -> None:
+            context.util.sd_step_callback(state, BaseModelType.StableDiffusion3)
+
+        return step_callback

invokeai/app/invocations/sd3_image_to_latents.py

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

invokeai/app/invocations/sd3_latents_to_image.py

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

invokeai/app/invocations/sd3_model_loader.py

@@ -0,0 +1,108 @@
+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

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

invokeai/app/invocations/segment_anything.py

@@ -5,7 +5,7 @@ from typing import Literal
 import numpy as np
 import torch
 from PIL import Image
-from pydantic import BaseModel, Field, model_validator
+from pydantic import BaseModel, Field
 from transformers import AutoModelForMaskGeneration, AutoProcessor
 from transformers.models.sam import SamModel
 from transformers.models.sam.processing_sam import SamProcessor
@@ -77,19 +77,14 @@ class SegmentAnythingInvocation(BaseInvocation):
         default="all",
     )
 
-    @model_validator(mode="after")
-    def check_point_lists_or_bounding_box(self):
-        if self.point_lists is None and self.bounding_boxes is None:
-            raise ValueError("Either point_lists or bounding_box must be provided.")
-        elif self.point_lists is not None and self.bounding_boxes is not None:
-            raise ValueError("Only one of point_lists or bounding_box can be provided.")
-        return self
-
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> MaskOutput:
         # The models expect a 3-channel RGB image.
         image_pil = context.images.get_pil(self.image.image_name, mode="RGB")
 
+        if self.point_lists is not None and self.bounding_boxes is not None:
+            raise ValueError("Only one of point_lists or bounding_box can be provided.")
+
         if (not self.bounding_boxes or len(self.bounding_boxes) == 0) and (
             not self.point_lists or len(self.point_lists) == 0
         ):

invokeai/app/services/model_load/model_load_default.py

@@ -86,7 +86,7 @@ class ModelLoadService(ModelLoadServiceBase):
 
         def torch_load_file(checkpoint: Path) -> AnyModel:
             scan_result = scan_file_path(checkpoint)
-            if scan_result.infected_files != 0:
+            if scan_result.infected_files != 0 or scan_result.scan_err:
                 raise Exception("The model at {checkpoint} is potentially infected by malware. Aborting load.")
             result = torch_load(checkpoint, map_location="cpu")
             return result

invokeai/app/services/model_records/model_records_base.py

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

invokeai/app/services/session_queue/session_queue_common.py

@@ -16,6 +16,7 @@ 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,
@@ -51,11 +52,7 @@ class SessionQueueItemNotFoundError(ValueError):
 
 # region Batch
 
-BatchDataType = Union[
-    StrictStr,
-    float,
-    int,
-]
+BatchDataType = Union[StrictStr, float, int, ImageField]
 
 
 class NodeFieldValue(BaseModel):

invokeai/app/services/shared/invocation_context.py

@@ -160,6 +160,10 @@ class LoggerInterface(InvocationContextInterface):
 
 
 class ImagesInterface(InvocationContextInterface):
+    def __init__(self, services: InvocationServices, data: InvocationContextData, util: "UtilInterface") -> None:
+        super().__init__(services, data)
+        self._util = util
+
     def save(
         self,
         image: Image,
@@ -186,6 +190,8 @@ class ImagesInterface(InvocationContextInterface):
             The saved image DTO.
         """
 
+        self._util.signal_progress("Saving image")
+
         # If `metadata` is provided directly, use that. Else, use the metadata provided by `WithMetadata`, falling back to None.
         metadata_ = None
         if metadata:
@@ -336,6 +342,10 @@ 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.
 
@@ -368,11 +378,15 @@ class ModelsInterface(InvocationContextInterface):
 
         if isinstance(identifier, str):
             model = self._services.model_manager.store.get_model(identifier)
-            return self._services.model_manager.load.load_model(model, submodel_type)
         else:
-            _submodel_type = submodel_type or identifier.submodel_type
+            submodel_type = submodel_type or identifier.submodel_type
             model = self._services.model_manager.store.get_model(identifier.key)
-            return self._services.model_manager.load.load_model(model, _submodel_type)
+
+        message = f"Loading model {model.name}"
+        if submodel_type:
+            message += f" ({submodel_type.value})"
+        self._util.signal_progress(message)
+        return self._services.model_manager.load.load_model(model, submodel_type)
 
     def load_by_attrs(
         self, name: str, base: BaseModelType, type: ModelType, submodel_type: Optional[SubModelType] = None
@@ -397,6 +411,10 @@ class ModelsInterface(InvocationContextInterface):
         if len(configs) > 1:
             raise ValueError(f"More than one model found with name {name}, base {base}, and type {type}")
 
+        message = f"Loading model {name}"
+        if submodel_type:
+            message += f" ({submodel_type.value})"
+        self._util.signal_progress(message)
         return self._services.model_manager.load.load_model(configs[0], submodel_type)
 
     def get_config(self, identifier: Union[str, "ModelIdentifierField"]) -> AnyModelConfig:
@@ -467,6 +485,7 @@ class ModelsInterface(InvocationContextInterface):
         Returns:
             Path to the downloaded model
         """
+        self._util.signal_progress(f"Downloading model {source}")
         return self._services.model_manager.install.download_and_cache_model(source=source)
 
     def load_local_model(
@@ -489,6 +508,8 @@ class ModelsInterface(InvocationContextInterface):
         Returns:
             A LoadedModelWithoutConfig object.
         """
+
+        self._util.signal_progress(f"Loading model {model_path.name}")
         return self._services.model_manager.load.load_model_from_path(model_path=model_path, loader=loader)
 
     def load_remote_model(
@@ -514,6 +535,8 @@ class ModelsInterface(InvocationContextInterface):
             A LoadedModelWithoutConfig object.
         """
         model_path = self._services.model_manager.install.download_and_cache_model(source=str(source))
+
+        self._util.signal_progress(f"Loading model {source}")
         return self._services.model_manager.load.load_model_from_path(model_path=model_path, loader=loader)
 
 
@@ -707,12 +730,12 @@ def build_invocation_context(
     """
 
     logger = LoggerInterface(services=services, data=data)
-    images = ImagesInterface(services=services, data=data)
     tensors = TensorsInterface(services=services, data=data)
-    models = ModelsInterface(services=services, data=data)
     config = ConfigInterface(services=services, data=data)
     util = UtilInterface(services=services, data=data, is_canceled=is_canceled)
     conditioning = ConditioningInterface(services=services, data=data)
+    models = ModelsInterface(services=services, data=data, util=util)
+    images = ImagesInterface(services=services, data=data, util=util)
     boards = BoardsInterface(services=services, data=data)
 
     ctx = InvocationContext(

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

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

invokeai/app/util/step_callback.py

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

invokeai/backend/flux/ip_adapter/state_dict_utils.py

@@ -41,10 +41,12 @@ 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

@@ -31,13 +31,16 @@ 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
+            cross_attention_dim=params.context_dim,
+            clip_embeddings_dim=params.clip_embeddings_dim,
+            clip_extra_context_tokens=params.clip_extra_context_tokens,
         )
         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/image_util/depth_anything/depth_anything_pipeline.py

@@ -17,9 +17,23 @@ class DepthAnythingPipeline(RawModel):
         self._pipeline = pipeline
 
     def generate_depth(self, image: Image.Image) -> Image.Image:
-        depth_map = self._pipeline(image)["depth"]
-        assert isinstance(depth_map, Image.Image)
-        return depth_map
+        pipeline_result = self._pipeline(image)
+        predicted_depth = pipeline_result["predicted_depth"]
+        assert isinstance(predicted_depth, torch.Tensor)
+
+        # Convert to PIL Image.
+        # Note: The pipeline already returns a PIL Image (pipeline_result["depth"]), but it contains artifacts as
+        # described here: https://github.com/invoke-ai/InvokeAI/issues/7358.
+        # We implement custom post-processing logic to avoid the artifacts.
+        prediction = torch.nn.functional.interpolate(
+            predicted_depth.unsqueeze(1), size=image.size[::-1], mode="bilinear", align_corners=False
+        )
+        prediction = prediction / prediction.max()
+        output = prediction.squeeze().cpu().numpy()
+        output = (output * 255).clip(0, 255)
+        formatted = output.astype("uint8")
+        depth = Image.fromarray(formatted)
+        return depth
 
     def to(self, device: Optional[torch.device] = None, dtype: Optional[torch.dtype] = None):
         if device is not None and device.type not in {"cpu", "cuda"}:

invokeai/backend/lora/conversions/flux_diffusers_lora_conversion_utils.py

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

invokeai/backend/model_manager/config.py

@@ -53,6 +53,7 @@ class BaseModelType(str, Enum):
     Any = "any"
     StableDiffusion1 = "sd-1"
     StableDiffusion2 = "sd-2"
+    StableDiffusion3 = "sd-3"
     StableDiffusionXL = "sdxl"
     StableDiffusionXLRefiner = "sdxl-refiner"
     Flux = "flux"
@@ -83,8 +84,10 @@ class SubModelType(str, Enum):
     Transformer = "transformer"
     TextEncoder = "text_encoder"
     TextEncoder2 = "text_encoder_2"
+    TextEncoder3 = "text_encoder_3"
     Tokenizer = "tokenizer"
     Tokenizer2 = "tokenizer_2"
+    Tokenizer3 = "tokenizer_3"
     VAE = "vae"
     VAEDecoder = "vae_decoder"
     VAEEncoder = "vae_encoder"
@@ -92,6 +95,13 @@ class SubModelType(str, Enum):
     SafetyChecker = "safety_checker"
 
 
+class ClipVariantType(str, Enum):
+    """Variant type."""
+
+    L = "large"
+    G = "gigantic"
+
+
 class ModelVariantType(str, Enum):
     """Variant type."""
 
@@ -147,6 +157,17 @@ class ModelSourceType(str, Enum):
 DEFAULTS_PRECISION = Literal["fp16", "fp32"]
 
 
+AnyVariant: TypeAlias = Union[ModelVariantType, ClipVariantType, None]
+
+
+class SubmodelDefinition(BaseModel):
+    path_or_prefix: str
+    model_type: ModelType
+    variant: AnyVariant = None
+
+    model_config = ConfigDict(protected_namespaces=())
+
+
 class MainModelDefaultSettings(BaseModel):
     vae: str | None = Field(default=None, description="Default VAE for this model (model key)")
     vae_precision: DEFAULTS_PRECISION | None = Field(default=None, description="Default VAE precision for this model")
@@ -193,6 +214,9 @@ class ModelConfigBase(BaseModel):
         schema["required"].extend(["key", "type", "format"])
 
     model_config = ConfigDict(validate_assignment=True, json_schema_extra=json_schema_extra)
+    submodels: Optional[Dict[SubModelType, SubmodelDefinition]] = Field(
+        description="Loadable submodels in this model", default=None
+    )
 
 
 class CheckpointConfigBase(ModelConfigBase):
@@ -335,7 +359,7 @@ class MainConfigBase(ModelConfigBase):
     default_settings: Optional[MainModelDefaultSettings] = Field(
         description="Default settings for this model", default=None
     )
-    variant: ModelVariantType = ModelVariantType.Normal
+    variant: AnyVariant = ModelVariantType.Normal
 
 
 class MainCheckpointConfig(CheckpointConfigBase, MainConfigBase):
@@ -419,12 +443,33 @@ class CLIPEmbedDiffusersConfig(DiffusersConfigBase):
 
     type: Literal[ModelType.CLIPEmbed] = ModelType.CLIPEmbed
     format: Literal[ModelFormat.Diffusers] = ModelFormat.Diffusers
+    variant: ClipVariantType = ClipVariantType.L
 
     @staticmethod
     def get_tag() -> Tag:
         return Tag(f"{ModelType.CLIPEmbed.value}.{ModelFormat.Diffusers.value}")
 
 
+class CLIPGEmbedDiffusersConfig(CLIPEmbedDiffusersConfig):
+    """Model config for CLIP-G Embeddings."""
+
+    variant: ClipVariantType = ClipVariantType.G
+
+    @staticmethod
+    def get_tag() -> Tag:
+        return Tag(f"{ModelType.CLIPEmbed.value}.{ModelFormat.Diffusers.value}.{ClipVariantType.G}")
+
+
+class CLIPLEmbedDiffusersConfig(CLIPEmbedDiffusersConfig):
+    """Model config for CLIP-L Embeddings."""
+
+    variant: ClipVariantType = ClipVariantType.L
+
+    @staticmethod
+    def get_tag() -> Tag:
+        return Tag(f"{ModelType.CLIPEmbed.value}.{ModelFormat.Diffusers.value}.{ClipVariantType.L}")
+
+
 class CLIPVisionDiffusersConfig(DiffusersConfigBase):
     """Model config for CLIPVision."""
 
@@ -501,6 +546,8 @@ AnyModelConfig = Annotated[
         Annotated[SpandrelImageToImageConfig, SpandrelImageToImageConfig.get_tag()],
         Annotated[CLIPVisionDiffusersConfig, CLIPVisionDiffusersConfig.get_tag()],
         Annotated[CLIPEmbedDiffusersConfig, CLIPEmbedDiffusersConfig.get_tag()],
+        Annotated[CLIPLEmbedDiffusersConfig, CLIPLEmbedDiffusersConfig.get_tag()],
+        Annotated[CLIPGEmbedDiffusersConfig, CLIPGEmbedDiffusersConfig.get_tag()],
     ],
     Discriminator(get_model_discriminator_value),
 ]

invokeai/backend/model_manager/load/load_default.py

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

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

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

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

@@ -42,6 +42,7 @@ VARIANT_TO_IN_CHANNEL_MAP = {
 @ModelLoaderRegistry.register(
     base=BaseModelType.StableDiffusionXLRefiner, type=ModelType.Main, format=ModelFormat.Diffusers
 )
+@ModelLoaderRegistry.register(base=BaseModelType.StableDiffusion3, type=ModelType.Main, format=ModelFormat.Diffusers)
 @ModelLoaderRegistry.register(base=BaseModelType.StableDiffusion1, type=ModelType.Main, format=ModelFormat.Checkpoint)
 @ModelLoaderRegistry.register(base=BaseModelType.StableDiffusion2, type=ModelType.Main, format=ModelFormat.Checkpoint)
 @ModelLoaderRegistry.register(base=BaseModelType.StableDiffusionXL, type=ModelType.Main, format=ModelFormat.Checkpoint)
@@ -51,13 +52,6 @@ VARIANT_TO_IN_CHANNEL_MAP = {
 class StableDiffusionDiffusersModel(GenericDiffusersLoader):
     """Class to load main models."""
 
-    model_base_to_model_type = {
-        BaseModelType.StableDiffusion1: "FrozenCLIPEmbedder",
-        BaseModelType.StableDiffusion2: "FrozenOpenCLIPEmbedder",
-        BaseModelType.StableDiffusionXL: "SDXL",
-        BaseModelType.StableDiffusionXLRefiner: "SDXL-Refiner",
-    }
-
     def _load_model(
         self,
         config: AnyModelConfig,

invokeai/backend/model_manager/probe.py

@@ -1,7 +1,7 @@
 import json
 import re
 from pathlib import Path
-from typing import Any, Dict, Literal, Optional, Union
+from typing import Any, Callable, Dict, Literal, Optional, Union
 
 import safetensors.torch
 import spandrel
@@ -22,6 +22,7 @@ from invokeai.backend.lora.conversions.flux_kohya_lora_conversion_utils import i
 from invokeai.backend.model_hash.model_hash import HASHING_ALGORITHMS, ModelHash
 from invokeai.backend.model_manager.config import (
     AnyModelConfig,
+    AnyVariant,
     BaseModelType,
     ControlAdapterDefaultSettings,
     InvalidModelConfigException,
@@ -33,8 +34,15 @@ 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
@@ -112,6 +120,7 @@ class ModelProbe(object):
         "StableDiffusionXLPipeline": ModelType.Main,
         "StableDiffusionXLImg2ImgPipeline": ModelType.Main,
         "StableDiffusionXLInpaintPipeline": ModelType.Main,
+        "StableDiffusion3Pipeline": ModelType.Main,
         "LatentConsistencyModelPipeline": ModelType.Main,
         "AutoencoderKL": ModelType.VAE,
         "AutoencoderTiny": ModelType.VAE,
@@ -122,8 +131,12 @@ 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]
@@ -170,7 +183,10 @@ class ModelProbe(object):
         fields["path"] = model_path.as_posix()
         fields["type"] = fields.get("type") or model_type
         fields["base"] = fields.get("base") or probe.get_base_type()
-        fields["variant"] = fields.get("variant") or probe.get_variant_type()
+        variant_func = cls.TYPE2VARIANT.get(fields["type"], None)
+        fields["variant"] = (
+            fields.get("variant") or (variant_func and variant_func(model_path.as_posix())) or probe.get_variant_type()
+        )
         fields["prediction_type"] = fields.get("prediction_type") or probe.get_scheduler_prediction_type()
         fields["image_encoder_model_id"] = fields.get("image_encoder_model_id") or probe.get_image_encoder_model_id()
         fields["name"] = fields.get("name") or cls.get_model_name(model_path)
@@ -217,6 +233,10 @@ class ModelProbe(object):
                 and fields["prediction_type"] == SchedulerPredictionType.VPrediction
             )
 
+        get_submodels = getattr(probe, "get_submodels", None)
+        if fields["base"] == BaseModelType.StableDiffusion3 and callable(get_submodels):
+            fields["submodels"] = get_submodels()
+
         model_info = ModelConfigFactory.make_config(fields)  # , key=fields.get("key", None))
         return model_info
 
@@ -449,7 +469,7 @@ class ModelProbe(object):
         """
         # scan model
         scan_result = scan_file_path(checkpoint)
-        if scan_result.infected_files != 0:
+        if scan_result.infected_files != 0 or scan_result.scan_err:
             raise Exception("The model {model_name} is potentially infected by malware. Aborting import.")
 
 
@@ -465,6 +485,7 @@ 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",
@@ -747,18 +768,33 @@ class FolderProbeBase(ProbeBase):
 
 class PipelineFolderProbe(FolderProbeBase):
     def get_base_type(self) -> BaseModelType:
-        with open(self.model_path / "unet" / "config.json", "r") as file:
-            unet_conf = json.load(file)
-        if unet_conf["cross_attention_dim"] == 768:
-            return BaseModelType.StableDiffusion1
-        elif unet_conf["cross_attention_dim"] == 1024:
-            return BaseModelType.StableDiffusion2
-        elif unet_conf["cross_attention_dim"] == 1280:
-            return BaseModelType.StableDiffusionXLRefiner
-        elif unet_conf["cross_attention_dim"] == 2048:
-            return BaseModelType.StableDiffusionXL
-        else:
-            raise InvalidModelConfigException(f"Unknown base model for {self.model_path}")
+        # Handle pipelines with a UNet (i.e SD 1.x, SD2, SDXL).
+        config_path = self.model_path / "unet" / "config.json"
+        if config_path.exists():
+            with open(config_path) as file:
+                unet_conf = json.load(file)
+            if unet_conf["cross_attention_dim"] == 768:
+                return BaseModelType.StableDiffusion1
+            elif unet_conf["cross_attention_dim"] == 1024:
+                return BaseModelType.StableDiffusion2
+            elif unet_conf["cross_attention_dim"] == 1280:
+                return BaseModelType.StableDiffusionXLRefiner
+            elif unet_conf["cross_attention_dim"] == 2048:
+                return BaseModelType.StableDiffusionXL
+            else:
+                raise InvalidModelConfigException(f"Unknown base model for {self.model_path}")
+
+        # Handle pipelines with a transformer (i.e. SD3).
+        config_path = self.model_path / "transformer" / "config.json"
+        if config_path.exists():
+            with open(config_path) as file:
+                transformer_conf = json.load(file)
+            if transformer_conf["_class_name"] == "SD3Transformer2DModel":
+                return BaseModelType.StableDiffusion3
+            else:
+                raise InvalidModelConfigException(f"Unknown base model for {self.model_path}")
+
+        raise InvalidModelConfigException(f"Unknown base model for {self.model_path}")
 
     def get_scheduler_prediction_type(self) -> SchedulerPredictionType:
         with open(self.model_path / "scheduler" / "scheduler_config.json", "r") as file:
@@ -770,6 +806,23 @@ class PipelineFolderProbe(FolderProbeBase):
         else:
             raise InvalidModelConfigException("Unknown scheduler prediction type: {scheduler_conf['prediction_type']}")
 
+    def get_submodels(self) -> Dict[SubModelType, SubmodelDefinition]:
+        config = ConfigLoader.load_config(self.model_path, config_name="model_index.json")
+        submodels: Dict[SubModelType, SubmodelDefinition] = {}
+        for key, value in config.items():
+            if key.startswith("_") or not (isinstance(value, list) and len(value) == 2):
+                continue
+            model_loader = str(value[1])
+            if model_type := ModelProbe.CLASS2TYPE.get(model_loader):
+                variant_func = ModelProbe.TYPE2VARIANT.get(model_type, None)
+                submodels[SubModelType(key)] = SubmodelDefinition(
+                    path_or_prefix=(self.model_path / key).resolve().as_posix(),
+                    model_type=model_type,
+                    variant=variant_func and variant_func((self.model_path / key).as_posix()),
+                )
+
+        return submodels
+
     def get_variant_type(self) -> ModelVariantType:
         # This only works for pipelines! Any kind of
         # exception results in our returning the

invokeai/backend/model_manager/starter_models.py

@@ -140,6 +140,22 @@ flux_dev = StarterModel(
     type=ModelType.Main,
     dependencies=[t5_base_encoder, flux_vae, clip_l_encoder],
 )
+sd35_medium = StarterModel(
+    name="SD3.5 Medium",
+    base=BaseModelType.StableDiffusion3,
+    source="stabilityai/stable-diffusion-3.5-medium",
+    description="Medium SD3.5 Model: ~15GB",
+    type=ModelType.Main,
+    dependencies=[],
+)
+sd35_large = StarterModel(
+    name="SD3.5 Large",
+    base=BaseModelType.StableDiffusion3,
+    source="stabilityai/stable-diffusion-3.5-large",
+    description="Large SD3.5 Model: ~19G",
+    type=ModelType.Main,
+    dependencies=[],
+)
 cyberrealistic_sd1 = StarterModel(
     name="CyberRealistic v4.1",
     base=BaseModelType.StableDiffusion1,
@@ -282,13 +298,12 @@ ip_adapter_sdxl = StarterModel(
     previous_names=["IP Adapter SDXL"],
 )
 ip_adapter_flux = StarterModel(
-    name="Standard Reference (XLabs FLUX IP-Adapter)",
+    name="Standard Reference (XLabs FLUX IP-Adapter v2)",
     base=BaseModelType.Flux,
-    source="https://huggingface.co/XLabs-AI/flux-ip-adapter/resolve/main/flux-ip-adapter.safetensors",
+    source="https://huggingface.co/XLabs-AI/flux-ip-adapter-v2/resolve/main/ip_adapter.safetensors",
     description="References images with a more generalized/looser degree of precision.",
     type=ModelType.IPAdapter,
     dependencies=[clip_vit_l_image_encoder],
-    previous_names=["XLabs FLUX IP-Adapter"],
 )
 # endregion
 # region ControlNet
@@ -570,6 +585,8 @@ 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

@@ -8,6 +8,7 @@ import safetensors
 import torch
 from picklescan.scanner import scan_file_path
 
+from invokeai.backend.model_manager.config import ClipVariantType
 from invokeai.backend.quantization.gguf.loaders import gguf_sd_loader
 
 
@@ -43,7 +44,7 @@ def _fast_safetensors_reader(path: str) -> Dict[str, torch.Tensor]:
     return checkpoint
 
 
-def read_checkpoint_meta(path: Union[str, Path], scan: bool = False) -> Dict[str, torch.Tensor]:
+def read_checkpoint_meta(path: Union[str, Path], scan: bool = True) -> Dict[str, torch.Tensor]:
     if str(path).endswith(".safetensors"):
         try:
             path_str = path.as_posix() if isinstance(path, Path) else path
@@ -54,7 +55,7 @@ def read_checkpoint_meta(path: Union[str, Path], scan: bool = False) -> Dict[str
     else:
         if scan:
             scan_result = scan_file_path(path)
-            if scan_result.infected_files != 0:
+            if scan_result.infected_files != 0 or scan_result.scan_err:
                 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
@@ -165,3 +166,25 @@ def convert_bundle_to_flux_transformer_checkpoint(
         del transformer_state_dict[k]
 
     return original_state_dict
+
+
+def get_clip_variant_type(location: str) -> Optional[ClipVariantType]:
+    try:
+        path = Path(location)
+        config_path = path / "config.json"
+        if not config_path.exists():
+            config_path = path / "text_encoder" / "config.json"
+        if not config_path.exists():
+            return ClipVariantType.L
+        with open(config_path) as file:
+            clip_conf = json.load(file)
+            hidden_size = clip_conf.get("hidden_size", -1)
+            match hidden_size:
+                case 1280:
+                    return ClipVariantType.G
+                case 768:
+                    return ClipVariantType.L
+                case _:
+                    return ClipVariantType.L
+    except Exception:
+        return ClipVariantType.L

invokeai/backend/model_manager/util/select_hf_files.py

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

invokeai/backend/sd3/extensions/inpaint_extension.py

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

invokeai/backend/stable_diffusion/diffusion/conditioning_data.py

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

invokeai/frontend/web/knip.ts

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

invokeai/frontend/web/package.json

@@ -52,13 +52,13 @@
     }
   },
   "dependencies": {
+    "@atlaskit/pragmatic-drag-and-drop": "^1.4.0",
+    "@atlaskit/pragmatic-drag-and-drop-auto-scroll": "^1.4.0",
+    "@atlaskit/pragmatic-drag-and-drop-hitbox": "^1.0.3",
     "@dagrejs/dagre": "^1.1.4",
     "@dagrejs/graphlib": "^2.2.4",
-    "@dnd-kit/core": "^6.1.0",
-    "@dnd-kit/sortable": "^8.0.0",
-    "@dnd-kit/utilities": "^3.2.2",
     "@fontsource-variable/inter": "^5.1.0",
-    "@invoke-ai/ui-library": "^0.0.43",
+    "@invoke-ai/ui-library": "^0.0.44",
     "@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: ^0.0.43
-    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)
+    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)
   '@nanostores/react':
     specifier: ^0.7.3
     version: 0.7.3(nanostores@0.11.3)(react@18.3.1)
@@ -319,6 +319,28 @@ packages:
       '@jridgewell/trace-mapping': 0.3.25
     dev: true
 
+  /@atlaskit/pragmatic-drag-and-drop-auto-scroll@1.4.0:
+    resolution: {integrity: sha512-5GoikoTSW13UX76F9TDeWB8x3jbbGlp/Y+3aRkHe1MOBMkrWkwNpJ42MIVhhX/6NSeaZiPumP0KbGJVs2tOWSQ==}
+    dependencies:
+      '@atlaskit/pragmatic-drag-and-drop': 1.4.0
+      '@babel/runtime': 7.25.7
+    dev: false
+
+  /@atlaskit/pragmatic-drag-and-drop-hitbox@1.0.3:
+    resolution: {integrity: sha512-/Sbu/HqN2VGLYBhnsG7SbRNg98XKkbF6L7XDdBi+izRybfaK1FeMfodPpm/xnBHPJzwYMdkE0qtLyv6afhgMUA==}
+    dependencies:
+      '@atlaskit/pragmatic-drag-and-drop': 1.4.0
+      '@babel/runtime': 7.25.7
+    dev: false
+
+  /@atlaskit/pragmatic-drag-and-drop@1.4.0:
+    resolution: {integrity: sha512-qRY3PTJIcxfl/QB8Gwswz+BRvlmgAC5pB+J2hL6dkIxgqAgVwOhAamMUKsrOcFU/axG2Q7RbNs1xfoLKDuhoPg==}
+    dependencies:
+      '@babel/runtime': 7.25.7
+      bind-event-listener: 3.0.0
+      raf-schd: 4.0.3
+    dev: false
+
   /@babel/code-frame@7.25.7:
     resolution: {integrity: sha512-0xZJFNE5XMpENsgfHYTw8FbX4kv53mFLn2i3XPoq69LyhYSCBJtitaHx9QnsVTrsogI4Z3+HtEfZ2/GFPOtf5g==}
     engines: {node: '>=6.9.0'}
@@ -493,8 +515,8 @@ packages:
     resolution: {integrity: sha512-MV6D4VLRIHr4PkW4zMyqfrNS1mPlCTiCXwvYGtDFQYr+xHFfonhAuf9WjsSc0nyp2m0OdkSLnzmVKkZFLo25Tg==}
     dev: false
 
-  /@chakra-ui/anatomy@2.3.4:
-    resolution: {integrity: sha512-fFIYN7L276gw0Q7/ikMMlZxP7mvnjRaWJ7f3Jsf9VtDOi6eAYIBRrhQe6+SZ0PGmoOkRaBc7gSE5oeIbgFFyrw==}
+  /@chakra-ui/anatomy@2.3.5:
+    resolution: {integrity: sha512-3im33cUOxCbISjaBlINE2u8BOwJSCdzpjCX0H+0JxK2xz26UaVA5xeI3NYHUoxDnr/QIrgfrllGxS0szYwOcyg==}
     dev: false
 
   /@chakra-ui/breakpoint-utils@2.0.8:
@@ -551,12 +573,12 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/hooks@2.4.2(react@18.3.1):
-    resolution: {integrity: sha512-LRKiVE1oA7afT5tbbSKAy7Uas2xFHE6IkrQdbhWCHmkHBUtPvjQQDgwtnd4IRZPmoEfNGwoJ/MQpwOM/NRTTwA==}
+  /@chakra-ui/hooks@2.4.3(react@18.3.1):
+    resolution: {integrity: sha512-Sr2zsoTZw3p7HbrUy4aLpTIkE2XXUelAUgg3NGwMzrmx75bE0qVyiuuTFOuyEzGxYVV2Fe8QtcKKilm6RwzTGg==}
     peerDependencies:
       react: '>=18'
     dependencies:
-      '@chakra-ui/utils': 2.2.2(react@18.3.1)
+      '@chakra-ui/utils': 2.2.3(react@18.3.1)
       '@zag-js/element-size': 0.31.1
       copy-to-clipboard: 3.3.3
       framesync: 6.1.2
@@ -574,13 +596,13 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/icons@2.2.4(@chakra-ui/react@2.10.2)(react@18.3.1):
+  /@chakra-ui/icons@2.2.4(@chakra-ui/react@2.10.4)(react@18.3.1):
     resolution: {integrity: sha512-l5QdBgwrAg3Sc2BRqtNkJpfuLw/pWRDwwT58J6c4PqQT6wzXxyNa8Q0PForu1ltB5qEiFb1kxr/F/HO1EwNa6g==}
     peerDependencies:
       '@chakra-ui/react': '>=2.0.0'
       react: '>=18'
     dependencies:
-      '@chakra-ui/react': 2.10.2(@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/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)
       react: 18.3.1
     dev: false
 
@@ -803,8 +825,8 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@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==}
+  /@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==}
     peerDependencies:
       '@emotion/react': '>=11'
       '@emotion/styled': '>=11'
@@ -812,10 +834,10 @@ packages:
       react: '>=18'
       react-dom: '>=18'
     dependencies:
-      '@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)
+      '@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)
       '@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
@@ -846,10 +868,10 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/styled-system@2.11.2(react@18.3.1):
-    resolution: {integrity: sha512-y++z2Uop+hjfZX9mbH88F1ikazPv32asD2er56zMJBemUAzweXnHTpiCQbluEDSUDhqmghVZAdb+5L4XLbsRxA==}
+  /@chakra-ui/styled-system@2.12.1(react@18.3.1):
+    resolution: {integrity: sha512-DQph1nDiCPtgze7nDe0a36530ByXb5VpPosKGyWMvKocVeZJcDtYG6XM0+V5a0wKuFBXsViBBRIFUTiUesJAcg==}
     dependencies:
-      '@chakra-ui/utils': 2.2.2(react@18.3.1)
+      '@chakra-ui/utils': 2.2.3(react@18.3.1)
       csstype: 3.1.3
     transitivePeerDependencies:
       - react
@@ -893,14 +915,14 @@ packages:
       color2k: 2.0.3
     dev: false
 
-  /@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==}
+  /@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==}
     peerDependencies:
       '@chakra-ui/styled-system': '>=2.0.0'
     dependencies:
-      '@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)
+      '@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)
       color2k: 2.0.3
     transitivePeerDependencies:
       - react
@@ -926,15 +948,15 @@ packages:
       '@chakra-ui/theme-tools': 2.1.2(@chakra-ui/styled-system@2.9.2)
     dev: false
 
-  /@chakra-ui/theme@3.4.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1):
-    resolution: {integrity: sha512-ZwFBLfiMC3URwaO31ONXoKH9k0TX0OW3UjdPF3EQkQpYyrk/fm36GkkzajjtdpWEd7rzDLRsQjPmvwNaSoNDtg==}
+  /@chakra-ui/theme@3.4.7(@chakra-ui/styled-system@2.12.1)(react@18.3.1):
+    resolution: {integrity: sha512-pfewthgZTFNUYeUwGvhPQO/FTIyf375cFV1AT8N1y0aJiw4KDe7YTGm7p0aFy4AwAjH2ydMgeEx/lua4tx8qyQ==}
     peerDependencies:
       '@chakra-ui/styled-system': '>=2.8.0'
     dependencies:
-      '@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)
+      '@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)
     transitivePeerDependencies:
       - react
     dev: false
@@ -959,8 +981,8 @@ packages:
       lodash.mergewith: 4.6.2
     dev: false
 
-  /@chakra-ui/utils@2.2.2(react@18.3.1):
-    resolution: {integrity: sha512-jUPLT0JzRMWxpdzH6c+t0YMJYrvc5CLericgITV3zDSXblkfx3DsYXqU11DJTSGZI9dUKzM1Wd0Wswn4eJwvFQ==}
+  /@chakra-ui/utils@2.2.3(react@18.3.1):
+    resolution: {integrity: sha512-cldoCQuexZ6e07/9hWHKD4l1QXXlM1Nax9tuQOBvVf/EgwNZt3nZu8zZRDFlhAOKCTQDkmpLTTu+eXXjChNQOw==}
     peerDependencies:
       react: '>=16.8.0'
     dependencies:
@@ -980,49 +1002,6 @@ packages:
     engines: {node: '>17.0.0'}
     dev: false
 
-  /@dnd-kit/accessibility@3.1.0(react@18.3.1):
-    resolution: {integrity: sha512-ea7IkhKvlJUv9iSHJOnxinBcoOI3ppGnnL+VDJ75O45Nss6HtZd8IdN8touXPDtASfeI2T2LImb8VOZcL47wjQ==}
-    peerDependencies:
-      react: '>=16.8.0'
-    dependencies:
-      react: 18.3.1
-      tslib: 2.7.0
-    dev: false
-
-  /@dnd-kit/core@6.1.0(react-dom@18.3.1)(react@18.3.1):
-    resolution: {integrity: sha512-J3cQBClB4TVxwGo3KEjssGEXNJqGVWx17aRTZ1ob0FliR5IjYgTxl5YJbKTzA6IzrtelotH19v6y7uoIRUZPSg==}
-    peerDependencies:
-      react: '>=16.8.0'
-      react-dom: '>=16.8.0'
-    dependencies:
-      '@dnd-kit/accessibility': 3.1.0(react@18.3.1)
-      '@dnd-kit/utilities': 3.2.2(react@18.3.1)
-      react: 18.3.1
-      react-dom: 18.3.1(react@18.3.1)
-      tslib: 2.7.0
-    dev: false
-
-  /@dnd-kit/sortable@8.0.0(@dnd-kit/core@6.1.0)(react@18.3.1):
-    resolution: {integrity: sha512-U3jk5ebVXe1Lr7c2wU7SBZjcWdQP+j7peHJfCspnA81enlu88Mgd7CC8Q+pub9ubP7eKVETzJW+IBAhsqbSu/g==}
-    peerDependencies:
-      '@dnd-kit/core': ^6.1.0
-      react: '>=16.8.0'
-    dependencies:
-      '@dnd-kit/core': 6.1.0(react-dom@18.3.1)(react@18.3.1)
-      '@dnd-kit/utilities': 3.2.2(react@18.3.1)
-      react: 18.3.1
-      tslib: 2.7.0
-    dev: false
-
-  /@dnd-kit/utilities@3.2.2(react@18.3.1):
-    resolution: {integrity: sha512-+MKAJEOfaBe5SmV6t34p80MMKhjvUz0vRrvVJbPT0WElzaOJ/1xs+D+KDv+tD/NE5ujfrChEcshd4fLn0wpiqg==}
-    peerDependencies:
-      react: '>=16.8.0'
-    dependencies:
-      react: 18.3.1
-      tslib: 2.7.0
-    dev: false
-
   /@emotion/babel-plugin@11.12.0:
     resolution: {integrity: sha512-y2WQb+oP8Jqvvclh8Q55gLUyb7UFvgv7eJfsj7td5TToBrIUtPay2kMrZi4xjq9qw2vD0ZR5fSho0yqoFgX7Rw==}
     dependencies:
@@ -1696,20 +1675,20 @@ packages:
       prettier: 3.3.3
     dev: true
 
-  /@invoke-ai/ui-library@0.0.43(@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==}
+  /@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==}
     peerDependencies:
       '@fontsource-variable/inter': ^5.0.16
       react: ^18.2.0
       react-dom: ^18.2.0
     dependencies:
-      '@chakra-ui/anatomy': 2.3.4
-      '@chakra-ui/icons': 2.2.4(@chakra-ui/react@2.10.2)(react@18.3.1)
+      '@chakra-ui/anatomy': 2.2.2
+      '@chakra-ui/icons': 2.2.4(@chakra-ui/react@2.10.4)(react@18.3.1)
       '@chakra-ui/layout': 2.3.1(@chakra-ui/system@2.6.2)(react@18.3.1)
       '@chakra-ui/portal': 2.1.0(react-dom@18.3.1)(react@18.3.1)
-      '@chakra-ui/react': 2.10.2(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1)
-      '@chakra-ui/styled-system': 2.11.2(react@18.3.1)
-      '@chakra-ui/theme-tools': 2.2.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1)
+      '@chakra-ui/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)
       '@emotion/react': 11.13.3(@types/react@18.3.11)(react@18.3.1)
       '@emotion/styled': 11.13.0(@emotion/react@11.13.3)(@types/react@18.3.11)(react@18.3.1)
       '@fontsource-variable/inter': 5.1.0
@@ -4313,6 +4292,10 @@ packages:
       open: 8.4.2
     dev: true
 
+  /bind-event-listener@3.0.0:
+    resolution: {integrity: sha512-PJvH288AWQhKs2v9zyfYdPzlPqf5bXbGMmhmUIY9x4dAUGIWgomO771oBQNwJnMQSnUIXhKu6sgzpBRXTlvb8Q==}
+    dev: false
+
   /bl@4.1.0:
     resolution: {integrity: sha512-1W07cM9gS6DcLperZfFSj+bWLtaPGSOHWhPiGzXmvVJbRLdG82sH/Kn8EtW1VqWVA54AKf2h5k5BbnIbwF3h6w==}
     dependencies:
@@ -7557,6 +7540,10 @@ packages:
     resolution: {integrity: sha512-NuaNSa6flKT5JaSYQzJok04JzTL1CA6aGhv5rfLW3PgqA+M2ChpZQnAC8h8i4ZFkBS8X5RqkDBHA7r4hej3K9A==}
     dev: true
 
+  /raf-schd@4.0.3:
+    resolution: {integrity: sha512-tQkJl2GRWh83ui2DiPTJz9wEiMN20syf+5oKfB03yYP7ioZcJwsIK8FjrtLwH1m7C7e+Tt2yYBlrOpdT+dyeIQ==}
+    dev: false
+
   /raf-throttle@2.0.6:
     resolution: {integrity: sha512-C7W6hy78A+vMmk5a/B6C5szjBHrUzWJkVyakjKCK59Uy2CcA7KhO1JUvvH32IXYFIcyJ3FMKP3ZzCc2/71I6Vg==}
     dev: false

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

@@ -768,7 +768,8 @@
         "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."
+        "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"
     },
     "queue": {
         "status": "Status",
@@ -871,7 +872,9 @@
         "recallParameter": "{{label}} Abrufen",
         "parsingFailed": "Parsing Fehlgeschlagen",
         "canvasV2Metadata": "Leinwand",
-        "guidance": "Führung"
+        "guidance": "Führung",
+        "seamlessXAxis": "Nahtlose X Achse",
+        "seamlessYAxis": "Nahtlose Y Achse"
     },
     "popovers": {
         "noiseUseCPU": {
@@ -1392,7 +1395,13 @@
         "pullBboxIntoLayerOk": "Bbox in die Ebene gezogen",
         "saveBboxToGallery": "Bbox in Galerie speichern",
         "tool": {
-            "bbox": "Bbox"
+            "bbox": "Bbox",
+            "brush": "Pinsel",
+            "eraser": "Radiergummi",
+            "colorPicker": "Farbwähler",
+            "view": "Ansicht",
+            "rectangle": "Rechteck",
+            "move": "Verschieben"
         },
         "transform": {
             "fitToBbox": "An Bbox anpassen",
@@ -1434,7 +1443,6 @@
         "deleteReferenceImage": "Referenzbild löschen",
         "referenceImage": "Referenzbild",
         "opacity": "Opazität",
-        "resetCanvas": "Leinwand zurücksetzen",
         "removeBookmark": "Lesezeichen entfernen",
         "rasterLayer": "Raster-Ebene",
         "rasterLayers_withCount_visible": "Raster-Ebenen ({{count}})",
@@ -1511,7 +1519,30 @@
         "layer_one": "Ebene",
         "layer_other": "Ebenen",
         "layer_withCount_one": "Ebene ({{count}})",
-        "layer_withCount_other": "Ebenen ({{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"
+        }
     },
     "upsell": {
         "shareAccess": "Zugang teilen",

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

@@ -122,6 +122,7 @@
         "goTo": "Go to",
         "hotkeysLabel": "Hotkeys",
         "loadingImage": "Loading Image",
+        "loadingModel": "Loading Model",
         "imageFailedToLoad": "Unable to Load Image",
         "img2img": "Image To Image",
         "inpaint": "inpaint",
@@ -174,7 +175,8 @@
         "placeholderSelectAModel": "Select a model",
         "reset": "Reset",
         "none": "None",
-        "new": "New"
+        "new": "New",
+        "generating": "Generating"
     },
     "hrf": {
         "hrf": "High Resolution Fix",
@@ -261,7 +263,8 @@
         "iterations_one": "Iteration",
         "iterations_other": "Iterations",
         "generations_one": "Generation",
-        "generations_other": "Generations"
+        "generations_other": "Generations",
+        "batchSize": "Batch Size"
     },
     "invocationCache": {
         "invocationCache": "Invocation Cache",
@@ -704,6 +707,8 @@
         "baseModel": "Base Model",
         "cancel": "Cancel",
         "clipEmbed": "CLIP Embed",
+        "clipLEmbed": "CLIP-L Embed",
+        "clipGEmbed": "CLIP-G Embed",
         "config": "Config",
         "convert": "Convert",
         "convertingModelBegin": "Converting Model. Please wait.",
@@ -973,6 +978,8 @@
         "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",
@@ -997,6 +1004,7 @@
         "controlNetControlMode": "Control Mode",
         "copyImage": "Copy Image",
         "denoisingStrength": "Denoising Strength",
+        "disabledNoRasterContent": "Disabled (No Raster Content)",
         "downloadImage": "Download Image",
         "general": "General",
         "guidance": "Guidance",
@@ -1010,8 +1018,11 @@
             "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",
@@ -1020,10 +1031,11 @@
             "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 filtering",
-            "canvasIsTransforming": "Canvas is transforming",
-            "canvasIsRasterizing": "Canvas is rasterizing",
-            "canvasIsCompositing": "Canvas is compositing",
+            "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)",
             "noPrompts": "No prompts generated",
             "noNodesInGraph": "No nodes in graph",
             "systemDisconnected": "System disconnected",
@@ -1136,6 +1148,7 @@
         "resetWebUI": "Reset Web UI",
         "resetWebUIDesc1": "Resetting the web UI only resets the browser's local cache of your images and remembered settings. It does not delete any images from disk.",
         "resetWebUIDesc2": "If images aren't showing up in the gallery or something else isn't working, please try resetting before submitting an issue on GitHub.",
+        "showDetailedInvocationProgress": "Show Progress Details",
         "showProgressInViewer": "Show Progress Images in Viewer",
         "ui": "User Interface",
         "clearIntermediatesDisabled": "Queue must be empty to clear intermediates",
@@ -1306,8 +1319,9 @@
         "controlNetBeginEnd": {
             "heading": "Begin / End Step Percentage",
             "paragraphs": [
-                "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."
+                "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."
             ]
         },
         "controlNetControlMode": {
@@ -1317,7 +1331,7 @@
         "controlNetProcessor": {
             "heading": "Processor",
             "paragraphs": [
-                "Method of processing the input image to guide the generation process. Different processors will providedifferent effects or styles in your generated images."
+                "Method of processing the input image to guide the generation process. Different processors will provide different effects or styles in your generated images."
             ]
         },
         "controlNetResizeMode": {
@@ -1325,13 +1339,15 @@
             "paragraphs": ["Method to fit Control Adapter's input image size to the output generation size."]
         },
         "ipAdapterMethod": {
-            "heading": "Method",
-            "paragraphs": ["Method by which to apply the current IP Adapter."]
+            "heading": "Mode",
+            "paragraphs": ["The mode defines how the reference image will guide the generation process."]
         },
         "controlNetWeight": {
             "heading": "Weight",
             "paragraphs": [
-                "Weight of the Control Adapter. Higher weight will lead to larger impacts on the final image."
+                "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."
             ]
         },
         "dynamicPrompts": {
@@ -1412,8 +1428,9 @@
         "paramDenoisingStrength": {
             "heading": "Denoising Strength",
             "paragraphs": [
-                "How much noise is added to the input image.",
-                "0 will result in an identical image, while 1 will result in a completely new image."
+                "Controls how much the generated image varies from the raster layer(s).",
+                "Lower strength stays closer to the combined visible raster layers. Higher strength relies more on the global prompt.",
+                "When there are no raster layers with visible content, this setting is ignored."
             ]
         },
         "paramHeight": {
@@ -1652,7 +1669,6 @@
         "newControlLayerError": "Problem Creating Control Layer",
         "newRasterLayerOk": "Created Raster Layer",
         "newRasterLayerError": "Problem Creating Raster Layer",
-        "newFromImage": "New from Image",
         "pullBboxIntoLayerOk": "Bbox Pulled Into Layer",
         "pullBboxIntoLayerError": "Problem Pulling BBox Into Layer",
         "pullBboxIntoReferenceImageOk": "Bbox Pulled Into ReferenceImage",
@@ -1662,13 +1678,14 @@
         "mergeDown": "Merge Down",
         "mergeVisibleOk": "Merged layers",
         "mergeVisibleError": "Error merging layers",
+        "mergingLayers": "Merging layers",
         "clearHistory": "Clear History",
         "bboxOverlay": "Show Bbox Overlay",
-        "resetCanvas": "Reset Canvas",
+        "newSession": "New Session",
         "clearCaches": "Clear Caches",
         "recalculateRects": "Recalculate Rects",
         "clipToBbox": "Clip Strokes to Bbox",
-        "outputOnlyMaskedRegions": "Output Only Masked Regions",
+        "outputOnlyMaskedRegions": "Output Only Generated Regions",
         "addLayer": "Add Layer",
         "duplicate": "Duplicate",
         "moveToFront": "Move to Front",
@@ -1696,8 +1713,10 @@
         "controlLayer": "Control Layer",
         "inpaintMask": "Inpaint Mask",
         "regionalGuidance": "Regional Guidance",
-        "canvasAsRasterLayer": "$t(controlLayers.canvas) as $t(controlLayers.rasterLayer)",
-        "canvasAsControlLayer": "$t(controlLayers.canvas) as $t(controlLayers.controlLayer)",
+        "asRasterLayer": "As $t(controlLayers.rasterLayer)",
+        "asRasterLayerResize": "As $t(controlLayers.rasterLayer) (Resize)",
+        "asControlLayer": "As $t(controlLayers.controlLayer)",
+        "asControlLayerResize": "As $t(controlLayers.controlLayer) (Resize)",
         "referenceImage": "Reference Image",
         "regionalReferenceImage": "Regional Reference Image",
         "globalReferenceImage": "Global Reference Image",
@@ -1765,6 +1784,7 @@
         "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 %",
@@ -1773,19 +1793,26 @@
         "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.",
         "controlMode": {
             "controlMode": "Control Mode",
-            "balanced": "Balanced",
+            "balanced": "Balanced (recommended)",
             "prompt": "Prompt",
             "control": "Control",
             "megaControl": "Mega Control"
         },
         "ipAdapterMethod": {
-            "ipAdapterMethod": "IP Adapter Method",
-            "full": "Full",
+            "ipAdapterMethod": "Mode",
+            "full": "Style and Composition",
+            "fullDesc": "Applies visual style (colors, textures) & composition (layout, structure).",
             "style": "Style Only",
-            "composition": "Composition Only"
+            "styleDesc": "Applies visual style (colors, textures) without considering its layout.",
+            "composition": "Composition Only",
+            "compositionDesc": "Replicates layout & structure while ignoring the reference's style."
         },
         "fill": {
             "fillColor": "Fill Color",
@@ -1815,6 +1842,9 @@
             "process": "Process",
             "apply": "Apply",
             "cancel": "Cancel",
+            "advanced": "Advanced",
+            "processingLayerWith": "Processing layer with the {{type}} filter.",
+            "forMoreControl": "For more control, click Advanced below.",
             "spandrel_filter": {
                 "label": "Image-to-Image Model",
                 "description": "Run an image-to-image model on the selected layer.",
@@ -1992,7 +2022,9 @@
         "upscaleModelDesc": "Upscale (image to image) model",
         "missingUpscaleInitialImage": "Missing initial image for upscaling",
         "missingUpscaleModel": "Missing upscale model",
-        "missingTileControlNetModel": "No valid tile ControlNet models installed"
+        "missingTileControlNetModel": "No valid tile ControlNet models installed",
+        "incompatibleBaseModel": "Unsupported main model architecture for upscaling",
+        "incompatibleBaseModelDesc": "Upscaling is supported for SD1.5 and SDXL architecture models only. Change the main model to enable upscaling."
     },
     "stylePresets": {
         "active": "Active",
@@ -2095,11 +2127,74 @@
     },
     "whatsNew": {
         "whatsNewInInvoke": "What's New in Invoke",
-        "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",
+        "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."
+        ],
         "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": "Postprocesado",
+        "postprocessing": "Postprocesamiento",
         "txt2img": "De texto a imagen",
         "accept": "Aceptar",
         "cancel": "Cancelar",
@@ -64,7 +64,7 @@
         "prevPage": "Página Anterior",
         "red": "Rojo",
         "alpha": "Transparencia",
-        "outputs": "Salidas",
+        "outputs": "Resultados",
         "learnMore": "Aprende más",
         "enabled": "Activado",
         "disabled": "Desactivado",
@@ -73,7 +73,32 @@
         "created": "Creado",
         "save": "Guardar",
         "unknownError": "Error Desconocido",
-        "blue": "Azul"
+        "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"
     },
     "gallery": {
         "galleryImageSize": "Tamaño de la imagen",
@@ -85,7 +110,63 @@
         "deleteImage_other": "Eliminar {{count}} Imágenes",
         "deleteImagePermanent": "Las imágenes eliminadas no se pueden restaurar.",
         "assets": "Activos",
-        "autoAssignBoardOnClick": "Asignación automática de tableros al hacer clic"
+        "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"
     },
     "modelManager": {
         "modelManager": "Gestor de Modelos",
@@ -131,7 +212,13 @@
         "modelDeleted": "Modelo eliminado",
         "modelDeleteFailed": "Error al borrar el modelo",
         "settings": "Ajustes",
-        "syncModels": "Sincronizar las plantillas"
+        "syncModels": "Sincronizar las plantillas",
+        "clipEmbed": "Incrustar CLIP",
+        "addModels": "Añadir modelos",
+        "advanced": "Avanzado",
+        "clipGEmbed": "Incrustar CLIP-G",
+        "cancel": "Cancelar",
+        "clipLEmbed": "Incrustar CLIP-L"
     },
     "parameters": {
         "images": "Imágenes",
@@ -158,19 +245,19 @@
         "useSeed": "Usar Semilla",
         "useAll": "Usar Todo",
         "info": "Información",
-        "showOptionsPanel": "Mostrar panel de opciones",
+        "showOptionsPanel": "Mostrar panel lateral (O o T)",
         "symmetry": "Simetría",
         "copyImage": "Copiar la imagen",
         "general": "General",
         "denoisingStrength": "Intensidad de la eliminación del ruido",
-        "seamlessXAxis": "Eje x",
-        "seamlessYAxis": "Eje y",
+        "seamlessXAxis": "Eje X sin juntas",
+        "seamlessYAxis": "Eje Y sin juntas",
         "scheduler": "Programador",
         "positivePromptPlaceholder": "Prompt Positivo",
         "negativePromptPlaceholder": "Prompt Negativo",
         "controlNetControlMode": "Modo de control",
         "clipSkip": "Omitir el CLIP",
-        "maskBlur": "Difuminar",
+        "maskBlur": "Desenfoque de máscara",
         "patchmatchDownScaleSize": "Reducir a escala",
         "coherenceMode": "Modo"
     },
@@ -202,16 +289,19 @@
         "serverError": "Error en el servidor",
         "canceled": "Procesando la cancelación",
         "connected": "Conectado al servidor",
-        "uploadFailedInvalidUploadDesc": "Debe ser una sola imagen PNG o JPEG",
-        "parameterSet": "Conjunto de parámetros",
-        "parameterNotSet": "Parámetro no configurado",
+        "uploadFailedInvalidUploadDesc": "Deben ser imágenes PNG o JPEG.",
+        "parameterSet": "Parámetro recuperado",
+        "parameterNotSet": "Parámetro no recuperado",
         "problemCopyingImage": "No se puede copiar la imagen",
         "errorCopied": "Error al copiar",
         "baseModelChanged": "Modelo base cambiado",
-        "addedToBoard": "Añadido al tablero",
+        "addedToBoard": "Se agregó a los activos del panel {{name}}",
         "baseModelChangedCleared_one": "Borrado o desactivado {{count}} submodelo incompatible",
         "baseModelChangedCleared_many": "Borrados o desactivados {{count}} submodelos incompatibles",
-        "baseModelChangedCleared_other": "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"
     },
     "accessibility": {
         "invokeProgressBar": "Activar la barra de progreso",
@@ -226,7 +316,8 @@
         "mode": "Modo",
         "submitSupportTicket": "Enviar Ticket de Soporte",
         "toggleRightPanel": "Activar o desactivar el panel derecho (G)",
-        "toggleLeftPanel": "Activar o desactivar el panel izquierdo (T)"
+        "toggleLeftPanel": "Activar o desactivar el panel izquierdo (T)",
+        "uploadImages": "Cargar imagen(es)"
     },
     "nodes": {
         "zoomInNodes": "Acercar",
@@ -238,7 +329,8 @@
         "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"
+        "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"
     },
     "boards": {
         "autoAddBoard": "Agregar panel automáticamente",
@@ -255,7 +347,7 @@
         "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…",
@@ -263,29 +355,33 @@
         "downloadBoard": "Descargar panel",
         "deleteBoardOnly": "Borrar solo el panel",
         "myBoard": "Mi panel",
-        "noMatching": "No hay paneles que coincidan",
+        "noMatching": "Sin paneles coincidentes",
         "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 tablero privado",
-        "addSharedBoard": "Agregar Panel Compartido",
+        "hideBoards": "Ocultar paneles",
+        "addPrivateBoard": "Agregar un panel privado",
+        "addSharedBoard": "Añadir panel compartido",
         "boards": "Paneles",
-        "archiveBoard": "Archivar Panel",
+        "archiveBoard": "Archivar panel",
         "archived": "Archivado",
         "selectedForAutoAdd": "Seleccionado para agregar automáticamente",
-        "unarchiveBoard": "Desarchivar el tablero",
-        "noBoards": "No hay tableros {{boardType}}",
-        "shared": "Carpetas compartidas",
-        "deletedPrivateBoardsCannotbeRestored": "Los tableros eliminados no se pueden restaurar. Al elegir \"Eliminar solo tablero\", las imágenes se colocan en un estado privado y sin categoría para el creador de la imagen."
+        "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"
     },
     "accordions": {
         "compositing": {
             "title": "Composición",
-            "infillTab": "Relleno"
+            "infillTab": "Relleno",
+            "coherenceTab": "Parámetros de la coherencia"
         },
         "generation": {
             "title": "Generación"
@@ -309,7 +405,10 @@
             "workflows": "Flujos de trabajo",
             "models": "Modelos",
             "modelsTab": "$t(ui.tabs.models) $t(common.tab)",
-            "workflowsTab": "$t(ui.tabs.workflows) $t(common.tab)"
+            "workflowsTab": "$t(ui.tabs.workflows) $t(common.tab)",
+            "upscaling": "Upscaling",
+            "gallery": "Galería",
+            "upscalingTab": "$t(ui.tabs.upscaling) $t(common.tab)"
         }
     },
     "queue": {
@@ -317,12 +416,81 @@
         "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"
+        "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"
     },
     "upsell": {
         "inviteTeammates": "Invitar compañeros de equipo",
         "shareAccess": "Compartir acceso",
-        "professionalUpsell": "Disponible en la edición profesional de Invoke. Haz clic aquí o visita invoke.com/pricing para obtener más detalles."
+        "professionalUpsell": "Disponible en la edición profesional de Invoke. Haga clic aquí o visite invoke.com/pricing para obtener más detalles."
     },
     "controlLayers": {
         "layer_one": "Capa",
@@ -330,6 +498,415 @@
         "layer_other": "Capas",
         "layer_withCount_one": "({{count}}) capa",
         "layer_withCount_many": "({{count}}) capas",
-        "layer_withCount_other": "({{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>."
     }
 }

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

@@ -1985,7 +1985,6 @@
         "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",
@@ -2034,7 +2033,6 @@
             "help2": "Commencez par un point <Bold>Inclure</Bold> au sein de l'objet cible. Ajoutez d'autres points pour affiner la sélection. Moins de points produisent généralement de meilleurs résultats.",
             "help3": "Inversez la sélection pour sélectionner tout sauf l'objet cible."
         },
-        "canvasAsControlLayer": "$t(controlLayers.canvas) en tant que $t(controlLayers.controlLayer)",
         "convertRegionalGuidanceTo": "Convertir $t(controlLayers.regionalGuidance) vers",
         "copyRasterLayerTo": "Copier $t(controlLayers.rasterLayer) vers",
         "newControlLayer": "Nouveau $t(controlLayers.controlLayer)",
@@ -2044,8 +2042,7 @@
         "convertInpaintMaskTo": "Convertir $t(controlLayers.inpaintMask) vers",
         "copyControlLayerTo": "Copier $t(controlLayers.controlLayer) vers",
         "newInpaintMask": "Nouveau $t(controlLayers.inpaintMask)",
-        "newRasterLayer": "Nouveau $t(controlLayers.rasterLayer)",
-        "canvasAsRasterLayer": "$t(controlLayers.canvas) en tant que $t(controlLayers.rasterLayer)"
+        "newRasterLayer": "Nouveau $t(controlLayers.rasterLayer)"
     },
     "upscaling": {
         "exceedsMaxSizeDetails": "La limite maximale d'agrandissement est de {{maxUpscaleDimension}}x{{maxUpscaleDimension}} pixels. Veuillez essayer une image plus petite ou réduire votre sélection d'échelle.",

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

@@ -94,7 +94,9 @@
         "view": "Vista",
         "close": "Chiudi",
         "clipboard": "Appunti",
-        "ok": "Ok"
+        "ok": "Ok",
+        "generating": "Generazione",
+        "loadingModel": "Caricamento del modello"
     },
     "gallery": {
         "galleryImageSize": "Dimensione dell'immagine",
@@ -597,7 +599,18 @@
         "huggingFace": "HuggingFace",
         "huggingFaceRepoID": "HuggingFace Repository ID",
         "clipEmbed": "CLIP Embed",
-        "t5Encoder": "T5 Encoder"
+        "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 "
     },
     "parameters": {
         "images": "Immagini",
@@ -699,7 +712,9 @@
         "staged": "Maschera espansa",
         "optimizedImageToImage": "Immagine-a-immagine ottimizzata",
         "sendToCanvas": "Invia alla Tela",
-        "coherenceMinDenoise": "Riduzione minima del rumore"
+        "coherenceMinDenoise": "Min rid. rumore",
+        "recallMetadata": "Richiama i metadati",
+        "disabledNoRasterContent": "Disabilitato (nessun contenuto Raster)"
     },
     "settings": {
         "models": "Modelli",
@@ -737,7 +752,8 @@
         "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."
+        "modelDescriptionsDisabledDesc": "Le descrizioni dei modelli nei menu a discesa sono state disabilitate. Abilitale nelle Impostazioni.",
+        "showDetailedInvocationProgress": "Mostra dettagli avanzamento"
     },
     "toast": {
         "uploadFailed": "Caricamento fallito",
@@ -1263,8 +1279,9 @@
         },
         "paramDenoisingStrength": {
             "paragraphs": [
-                "Quanto rumore viene aggiunto all'immagine in ingresso.",
-                "0 risulterà in un'immagine identica, mentre 1 risulterà in un'immagine completamente nuova."
+                "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."
             ],
             "heading": "Forza di riduzione del rumore"
         },
@@ -1276,7 +1293,7 @@
         },
         "infillMethod": {
             "paragraphs": [
-                "Metodo di riempimento durante il processo di Outpainting o Inpainting."
+                "Metodo di riempimento durante il processo di Outpaint o Inpaint."
             ],
             "heading": "Metodo di riempimento"
         },
@@ -1444,7 +1461,7 @@
             "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'inpainting o l'outpainting"
+                "L'intensità minima di riduzione del rumore per la regione di coerenza durante l'inpaint o l'outpaint"
             ]
         },
         "compositingMaskBlur": {
@@ -1498,7 +1515,7 @@
         "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 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."
+                "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."
             ]
         },
         "paramGuidance": {
@@ -1733,8 +1750,7 @@
         "newRegionalReferenceImageError": "Problema nella creazione dell'immagine di riferimento regionale",
         "newControlLayerOk": "Livello di controllo creato",
         "bboxOverlay": "Mostra sovrapposizione riquadro",
-        "resetCanvas": "Reimposta la tela",
-        "outputOnlyMaskedRegions": "Solo regioni mascherate in uscita",
+        "outputOnlyMaskedRegions": "In uscita solo le regioni generate",
         "enableAutoNegative": "Abilita Auto Negativo",
         "disableAutoNegative": "Disabilita Auto Negativo",
         "showHUD": "Mostra HUD",
@@ -1771,7 +1787,7 @@
         "globalReferenceImage_withCount_many": "Immagini di riferimento Globali",
         "globalReferenceImage_withCount_other": "Immagini di riferimento Globali",
         "controlMode": {
-            "balanced": "Bilanciato",
+            "balanced": "Bilanciato (consigliato)",
             "controlMode": "Modalità di controllo",
             "prompt": "Prompt",
             "control": "Controllo",
@@ -1782,7 +1798,7 @@
         "beginEndStepPercentShort": "Inizio/Fine %",
         "stagingOnCanvas": "Genera immagini nella",
         "ipAdapterMethod": {
-            "full": "Completo",
+            "full": "Stile e Composizione",
             "style": "Solo Stile",
             "composition": "Solo Composizione",
             "ipAdapterMethod": "Metodo Adattatore IP"
@@ -1881,7 +1897,10 @@
             "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)",
@@ -2016,8 +2035,6 @@
         "convertControlLayerTo": "Converti $t(controlLayers.controlLayer) in",
         "newRasterLayer": "Nuovo $t(controlLayers.rasterLayer)",
         "newRegionalGuidance": "Nuova $t(controlLayers.regionalGuidance)",
-        "canvasAsRasterLayer": "$t(controlLayers.canvas) come $t(controlLayers.rasterLayer)",
-        "canvasAsControlLayer": "$t(controlLayers.canvas) come $t(controlLayers.controlLayer)",
         "convertInpaintMaskTo": "Converti $t(controlLayers.inpaintMask) in",
         "copyRegionalGuidanceTo": "Copia $t(controlLayers.regionalGuidance) in",
         "convertRasterLayerTo": "Converti $t(controlLayers.rasterLayer) in",
@@ -2025,7 +2042,9 @@
         "newControlLayer": "Nuovo $t(controlLayers.controlLayer)",
         "newInpaintMask": "Nuova $t(controlLayers.inpaintMask)",
         "replaceCurrent": "Sostituisci corrente",
-        "mergeDown": "Unire in basso"
+        "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."
     },
     "ui": {
         "tabs": {
@@ -2057,7 +2076,9 @@
         "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"
+        "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."
     },
     "upsell": {
         "inviteTeammates": "Invita collaboratori",
@@ -2119,12 +2140,13 @@
     },
     "whatsNew": {
         "whatsNewInInvoke": "Novità in Invoke",
-        "line2": "Supporto Flux esteso, ora con immagini di riferimento globali",
-        "line3": "Tooltip e menu contestuali migliorati",
         "readReleaseNotes": "Leggi le note di rilascio",
         "watchRecentReleaseVideos": "Guarda i video su questa versione",
-        "line1": "Strumento <ItalicComponent>Seleziona oggetto</ItalicComponent> per la selezione e la modifica precise degli oggetti",
-        "watchUiUpdatesOverview": "Guarda le novità dell'interfaccia"
+        "watchUiUpdatesOverview": "Guarda le novità dell'interfaccia",
+        "items": [
+            "<StrongComponent>SD 3.5</StrongComponent>: supporto per SD 3.5 Medium e Large.",
+            "<StrongComponent>Tela</StrongComponent>: elaborazione semplificata del livello di controllo e impostazioni di controllo predefinite migliorate."
+        ]
     },
     "system": {
         "logLevel": {

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

@@ -16,7 +16,7 @@
         "discordLabel": "Discord",
         "nodes": "ワークフロー",
         "txt2img": "txt2img",
-        "postprocessing": "Post Processing",
+        "postprocessing": "ポストプロセス",
         "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": "プロンプト",
-        "negativePrompt": "除外する要素",
+        "positivePrompt": "ポジティブプロンプト",
+        "negativePrompt": "ネガティブプロンプト",
         "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",
@@ -80,7 +80,20 @@
         "editor": "エディタ",
         "safetensors": "Safetensors",
         "tab": "タブ",
-        "toResolve": "解決方法"
+        "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"
     },
     "gallery": {
         "galleryImageSize": "画像のサイズ",
@@ -125,12 +138,114 @@
         "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。"
+        "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"
     },
     "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"
+        "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"
     },
     "modelManager": {
         "modelManager": "モデルマネージャ",
@@ -165,7 +280,7 @@
         "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（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）",
+        "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）",
         "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",
@@ -178,7 +293,9 @@
         "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"
+        "cancel": "キャンセル",
+        "uploadImage": "画像をアップロード",
+        "addModels": "モデルを追加"
     },
     "parameters": {
         "images": "画像",
@@ -200,7 +317,19 @@
         "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"
+        "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"
     },
     "settings": {
         "models": "モデル",
@@ -213,7 +342,11 @@
     },
     "toast": {
         "uploadFailed": "アップロード失敗",
-        "imageCopied": "画像をコピー"
+        "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"
     },
     "accessibility": {
         "invokeProgressBar": "進捗バー",
@@ -226,7 +359,10 @@
         "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"
+        "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)"
     },
     "metadata": {
         "Threshold": "ノイズ閾値",
@@ -237,7 +373,8 @@
         "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": "パラメータを呼び出す"
+        "recallParameters": "パラメータを再使用",
+        "recallParameter": "{{label}} を再使用"
     },
     "queue": {
         "queueEmpty": "キューが空です",
@@ -297,14 +434,22 @@
         "prune": "刈り込み",
         "prompts_other": "プロンプト",
         "iterations_other": "繰り返し",
-        "generations_other": "生成"
+        "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"
     },
     "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"
+        "selectModel": "モデルを選択してください",
+        "concepts": "コンセプト",
+        "addLora": "LoRAを追加"
     },
     "nodes": {
         "addNode": "ノードを追加",
@@ -339,7 +484,8 @@
         "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..."
+        "loadingNodes": "ノードを読み込み中...",
+        "scheduler": "スケジューラー"
     },
     "boards": {
         "autoAddBoard": "自動追加するボード",
@@ -362,7 +508,18 @@
         "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:"
+        "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"
     },
     "invocationCache": {
         "invocationCache": "呼び出しキャッシュ",
@@ -387,6 +544,33 @@
             "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": {
@@ -427,5 +611,79 @@
         "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/ru.json

@@ -1660,7 +1660,6 @@
         "clearCaches": "Очистить кэши",
         "recalculateRects": "Пересчитать прямоугольники",
         "saveBboxToGallery": "Сохранить рамку в галерею",
-        "resetCanvas": "Сбросить холст",
         "canvas": "Холст",
         "global": "Глобальный",
         "newGlobalReferenceImageError": "Проблема с созданием глобального эталонного изображения",

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

@@ -96,7 +96,9 @@
         "view": "视图",
         "alpha": "透明度通道",
         "openInViewer": "在查看器中打开",
-        "clipboard": "剪贴板"
+        "clipboard": "剪贴板",
+        "loadingModel": "加载模型",
+        "generating": "生成中"
     },
     "gallery": {
         "galleryImageSize": "预览大小",
@@ -587,7 +589,27 @@
         "huggingFace": "HuggingFace",
         "hfTokenInvalid": "HF 令牌无效或缺失",
         "hfTokenLabel": "HuggingFace 令牌（某些模型所需）",
-        "hfTokenHelperText": "使用某些模型需要 HF 令牌。点击这里创建或获取你的令牌。"
+        "hfTokenHelperText": "使用某些模型需要 HF 令牌。点击这里创建或获取你的令牌。",
+        "includesNModels": "包括 {{n}} 个模型及其依赖项",
+        "starterBundles": "启动器包",
+        "learnMoreAboutSupportedModels": "了解更多关于我们支持的模型的信息",
+        "hfForbidden": "您没有权限访问这个 HF 模型",
+        "hfTokenInvalidErrorMessage": "无效或缺失 HuggingFace 令牌。",
+        "hfTokenRequired": "您正在尝试下载一个需要有效 HuggingFace 令牌的模型。",
+        "hfTokenSaved": "HF 令牌已保存",
+        "hfForbiddenErrorMessage": "我们建议访问 HuggingFace.com 上的仓库页面。所有者可能要求您接受条款才能下载。",
+        "hfTokenUnableToVerifyErrorMessage": "无法验证 HuggingFace 令牌。这可能是由于网络错误导致的。请稍后再试。",
+        "hfTokenInvalidErrorMessage2": "在这里更新它。 ",
+        "hfTokenUnableToVerify": "无法验证 HF 令牌",
+        "skippingXDuplicates_other": "跳过 {{count}} 个重复项",
+        "starterBundleHelpText": "轻松安装所有用于启动基础模型所需的模型，包括主模型、ControlNets、IP适配器等。选择一个安装包时，会跳过已安装的模型。",
+        "installingBundle": "正在安装模型包",
+        "installingModel": "正在安装模型",
+        "installingXModels_other": "正在安装 {{count}} 个模型",
+        "t5Encoder": "T5 编码器",
+        "clipLEmbed": "CLIP-L 嵌入",
+        "clipGEmbed": "CLIP-G 嵌入",
+        "loraModels": "LoRAs（低秩适配）"
     },
     "parameters": {
         "images": "图像",
@@ -646,8 +668,23 @@
                 "controlAdapterIncompatibleBaseModel": "Control Adapter的基础模型不兼容",
                 "ipAdapterIncompatibleBaseModel": "IP Adapter的基础模型不兼容",
                 "ipAdapterNoImageSelected": "未选择IP Adapter图像",
-                "rgNoRegion": "未选择区域"
-            }
+                "rgNoRegion": "未选择区域",
+                "t2iAdapterIncompatibleBboxWidth": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}，边界框宽度为 {{width}}",
+                "t2iAdapterIncompatibleScaledBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}，缩放后的边界框高度为 {{height}}",
+                "t2iAdapterIncompatibleBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}，边界框高度为 {{height}}",
+                "t2iAdapterIncompatibleScaledBboxWidth": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}，缩放后的边界框宽度为 {{width}}"
+            },
+            "canvasIsFiltering": "画布正在过滤",
+            "fluxModelIncompatibleScaledBboxHeight": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16)，缩放后的边界框高度为 {{height}}",
+            "noCLIPEmbedModelSelected": "未为FLUX生成选择CLIP嵌入模型",
+            "noFLUXVAEModelSelected": "未为FLUX生成选择VAE模型",
+            "canvasIsRasterizing": "画布正在栅格化",
+            "canvasIsCompositing": "画布正在合成",
+            "fluxModelIncompatibleBboxWidth": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16)，边界框宽度为 {{width}}",
+            "fluxModelIncompatibleScaledBboxWidth": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16)，缩放后的边界框宽度为 {{width}}",
+            "noT5EncoderModelSelected": "未为FLUX生成选择T5编码器模型",
+            "fluxModelIncompatibleBboxHeight": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16)，边界框高度为 {{height}}",
+            "canvasIsTransforming": "画布正在变换"
         },
         "patchmatchDownScaleSize": "缩小",
         "clipSkip": "CLIP 跳过层",
@@ -669,7 +706,15 @@
         "sendToUpscale": "发送到放大",
         "processImage": "处理图像",
         "infillColorValue": "填充颜色",
-        "coherenceMinDenoise": "最小去噪"
+        "coherenceMinDenoise": "最小去噪",
+        "sendToCanvas": "发送到画布",
+        "disabledNoRasterContent": "已禁用（无栅格内容）",
+        "optimizedImageToImage": "优化的图生图",
+        "guidance": "引导",
+        "gaussianBlur": "高斯模糊",
+        "recallMetadata": "调用元数据",
+        "boxBlur": "方框模糊",
+        "staged": "已分阶段处理"
     },
     "settings": {
         "models": "模型",
@@ -699,7 +744,12 @@
         "enableInformationalPopovers": "启用信息弹窗",
         "reloadingIn": "重新加载中",
         "informationalPopoversDisabled": "信息提示框已禁用",
-        "informationalPopoversDisabledDesc": "信息提示框已被禁用.请在设置中重新启用."
+        "informationalPopoversDisabledDesc": "信息提示框已被禁用.请在设置中重新启用.",
+        "enableModelDescriptions": "在下拉菜单中启用模型描述",
+        "confirmOnNewSession": "新会话时确认",
+        "modelDescriptionsDisabledDesc": "下拉菜单中的模型描述已被禁用。可在设置中启用。",
+        "modelDescriptionsDisabled": "下拉菜单中的模型描述已禁用",
+        "showDetailedInvocationProgress": "显示进度详情"
     },
     "toast": {
         "uploadFailed": "上传失败",
@@ -740,7 +790,24 @@
         "errorCopied": "错误信息已复制",
         "modelImportCanceled": "模型导入已取消",
         "importFailed": "导入失败",
-        "importSuccessful": "导入成功"
+        "importSuccessful": "导入成功",
+        "layerSavedToAssets": "图层已保存到资产",
+        "sentToUpscale": "已发送到放大处理",
+        "addedToUncategorized": "已添加到看板 $t(boards.uncategorized) 的资产中",
+        "linkCopied": "链接已复制",
+        "uploadFailedInvalidUploadDesc_withCount_other": "最多只能上传 {{count}} 张 PNG 或 JPEG 图像。",
+        "problemSavingLayer": "无法保存图层",
+        "unableToLoadImage": "无法加载图像",
+        "imageNotLoadedDesc": "无法找到图像",
+        "unableToLoadStylePreset": "无法加载样式预设",
+        "stylePresetLoaded": "样式预设已加载",
+        "problemCopyingLayer": "无法复制图层",
+        "sentToCanvas": "已发送到画布",
+        "unableToLoadImageMetadata": "无法加载图像元数据",
+        "imageSaved": "图像已保存",
+        "imageSavingFailed": "图像保存失败",
+        "layerCopiedToClipboard": "图层已复制到剪贴板",
+        "imagesWillBeAddedTo": "上传的图像将添加到看板 {{boardName}} 的资产中。"
     },
     "accessibility": {
         "invokeProgressBar": "Invoke 进度条",
@@ -890,7 +957,12 @@
         "clearWorkflow": "清除工作流",
         "imageAccessError": "无法找到图像 {{image_name}}，正在恢复默认设置",
         "boardAccessError": "无法找到面板 {{board_id}}，正在恢复默认设置",
-        "modelAccessError": "无法找到模型 {{key}}，正在恢复默认设置"
+        "modelAccessError": "无法找到模型 {{key}}，正在恢复默认设置",
+        "noWorkflows": "无工作流程",
+        "workflowHelpText": "需要帮助？请查看我们的《<LinkComponent>工作流程入门指南</LinkComponent>》。",
+        "noMatchingWorkflows": "无匹配的工作流程",
+        "saveToGallery": "保存到图库",
+        "singleFieldType": "{{name}}（单一模型）"
     },
     "queue": {
         "status": "状态",
@@ -1221,7 +1293,8 @@
             "heading": "去噪强度",
             "paragraphs": [
                 "为输入图像添加的噪声量。",
-                "输入 0 会导致结果图像和输入完全相同，输入 1 则会生成全新的图像。"
+                "输入 0 会导致结果图像和输入完全相同，输入 1 则会生成全新的图像。",
+                "当没有具有可见内容的栅格图层时，此设置将被忽略。"
             ]
         },
         "paramSeed": {
@@ -1410,7 +1483,8 @@
             "paragraphs": [
                 "控制提示对生成过程的影响程度.",
                 "与生成CFG Scale相似."
-            ]
+            ],
+            "heading": "CFG比例"
         },
         "structure": {
             "heading": "结构",
@@ -1441,6 +1515,62 @@
             "paragraphs": [
                 "比例控制决定了输出图像的大小,它是基于输入图像分辨率的倍数来计算的.例如对一张1024x1024的图像进行2倍上采样，将会得到一张2048x2048的输出图像."
             ]
+        },
+        "globalReferenceImage": {
+            "heading": "全局参考图像",
+            "paragraphs": [
+                "应用参考图像以影响整个生成过程。"
+            ]
+        },
+        "rasterLayer": {
+            "paragraphs": [
+                "画布的基于像素的内容，用于图像生成过程。"
+            ],
+            "heading": "栅格图层"
+        },
+        "regionalGuidanceAndReferenceImage": {
+            "paragraphs": [
+                "对于区域引导，使用画笔引导全局提示中的元素应出现的位置。",
+                "对于区域参考图像，使用画笔将参考图像应用到特定区域。"
+            ],
+            "heading": "区域引导与区域参考图像"
+        },
+        "regionalReferenceImage": {
+            "heading": "区域参考图像",
+            "paragraphs": [
+                "使用画笔将参考图像应用到特定区域。"
+            ]
+        },
+        "optimizedDenoising": {
+            "heading": "优化的图生图",
+            "paragraphs": [
+                "启用‘优化的图生图’功能，可在使用 Flux 模型进行图生图和图像修复转换时提供更平滑的降噪强度调节。此设置可以提高对图像变化程度的控制能力，但如果您更倾向于使用标准的降噪强度调节方式，也可以关闭此功能。该设置仍在优化中，目前处于测试阶段。"
+            ]
+        },
+        "inpainting": {
+            "paragraphs": [
+                "控制由降噪强度引导的修改区域。"
+            ],
+            "heading": "图像重绘"
+        },
+        "regionalGuidance": {
+            "heading": "区域引导",
+            "paragraphs": [
+                "使用画笔引导全局提示中的元素应出现的位置。"
+            ]
+        },
+        "fluxDevLicense": {
+            "heading": "非商业许可",
+            "paragraphs": [
+                "FLUX.1 [dev] 模型受 FLUX [dev] 非商业许可协议的约束。如需在 Invoke 中将此模型类型用于商业目的，请访问我们的网站了解更多信息。"
+            ]
+        },
+        "paramGuidance": {
+            "paragraphs": [
+                "控制提示对生成过程的影响程度。",
+                "较高的引导值可能导致过度饱和，而过高或过低的引导值可能导致生成结果失真。引导仅适用于FLUX DEV模型。"
+            ],
+            "heading": "引导"
         }
     },
     "invocationCache": {
@@ -1503,7 +1633,18 @@
         "convertGraph": "转换图表",
         "loadWorkflow": "$t(common.load) 工作流",
         "loadFromGraph": "从图表加载工作流",
-        "autoLayout": "自动布局"
+        "autoLayout": "自动布局",
+        "edit": "编辑",
+        "copyShareLinkForWorkflow": "复制工作流程的分享链接",
+        "delete": "删除",
+        "download": "下载",
+        "defaultWorkflows": "默认工作流程",
+        "userWorkflows": "用户工作流程",
+        "projectWorkflows": "项目工作流程",
+        "copyShareLink": "复制分享链接",
+        "chooseWorkflowFromLibrary": "从库中选择工作流程",
+        "uploadAndSaveWorkflow": "上传到库",
+        "deleteWorkflow2": "您确定要删除此工作流程吗？此操作无法撤销。"
     },
     "accordions": {
         "compositing": {
@@ -1542,7 +1683,108 @@
         "addPositivePrompt": "添加 $t(controlLayers.prompt)",
         "addNegativePrompt": "添加 $t(controlLayers.negativePrompt)",
         "rectangle": "矩形",
-        "opacity": "透明度"
+        "opacity": "透明度",
+        "canvas": "画布",
+        "fitBboxToLayers": "将边界框适配到图层",
+        "cropLayerToBbox": "将图层裁剪到边界框",
+        "saveBboxToGallery": "将边界框保存到图库",
+        "savedToGalleryOk": "已保存到图库",
+        "saveLayerToAssets": "将图层保存到资产",
+        "removeBookmark": "移除书签",
+        "regional": "区域",
+        "saveCanvasToGallery": "将画布保存到图库",
+        "global": "全局",
+        "bookmark": "添加书签以快速切换",
+        "regionalReferenceImage": "局部参考图像",
+        "mergingLayers": "正在合并图层",
+        "newControlLayerError": "创建控制层时出现问题",
+        "pullBboxIntoReferenceImageError": "将边界框导入参考图像时出现问题",
+        "mergeVisibleOk": "已合并图层",
+        "maskFill": "遮罩填充",
+        "newCanvasFromImage": "从图像创建新画布",
+        "pullBboxIntoReferenceImageOk": "边界框已导入到参考图像",
+        "globalReferenceImage_withCount_other": "全局参考图像",
+        "addInpaintMask": "添加 $t(controlLayers.inpaintMask)",
+        "referenceImage": "参考图像",
+        "globalReferenceImage": "全局参考图像",
+        "newRegionalGuidance": "新建 $t(controlLayers.regionalGuidance)",
+        "savedToGalleryError": "保存到图库时出错",
+        "copyRasterLayerTo": "复制 $t(controlLayers.rasterLayer) 到",
+        "clearHistory": "清除历史记录",
+        "inpaintMask": "修复遮罩",
+        "regionalGuidance_withCount_visible": "区域引导（{{count}} 个）",
+        "inpaintMasks_withCount_hidden": "修复遮罩（{{count}} 个已隐藏）",
+        "enableAutoNegative": "启用自动负面提示",
+        "disableAutoNegative": "禁用自动负面提示",
+        "deleteReferenceImage": "删除参考图像",
+        "sendToCanvas": "发送到画布",
+        "controlLayers_withCount_visible": "控制图层（{{count}} 个）",
+        "rasterLayers_withCount_visible": "栅格图层（{{count}} 个）",
+        "convertRegionalGuidanceTo": "将 $t(controlLayers.regionalGuidance) 转换为",
+        "newInpaintMask": "新建 $t(controlLayers.inpaintMask)",
+        "regionIsEmpty": "选定区域为空",
+        "mergeVisible": "合并可见图层",
+        "showHUD": "显示 HUD（抬头显示）",
+        "newLayerFromImage": "从图像创建新图层",
+        "layer_other": "图层",
+        "transparency": "透明度",
+        "addRasterLayer": "添加 $t(controlLayers.rasterLayer)",
+        "newRasterLayerOk": "已创建栅格层",
+        "newRasterLayerError": "创建栅格层时出现问题",
+        "inpaintMasks_withCount_visible": "修复遮罩（{{count}} 个）",
+        "convertRasterLayerTo": "将 $t(controlLayers.rasterLayer) 转换为",
+        "copyControlLayerTo": "复制 $t(controlLayers.controlLayer) 到",
+        "copyInpaintMaskTo": "复制 $t(controlLayers.inpaintMask) 到",
+        "copyRegionalGuidanceTo": "复制 $t(controlLayers.regionalGuidance) 到",
+        "newRasterLayer": "新建 $t(controlLayers.rasterLayer)",
+        "newControlLayer": "新建 $t(controlLayers.controlLayer)",
+        "newImg2ImgCanvasFromImage": "从图像创建新的图生图",
+        "rasterLayer": "栅格层",
+        "controlLayer": "控制层",
+        "outputOnlyMaskedRegions": "仅输出生成的区域",
+        "addControlLayer": "添加 $t(controlLayers.controlLayer)",
+        "newGlobalReferenceImageOk": "已创建全局参考图像",
+        "newGlobalReferenceImageError": "创建全局参考图像时出现问题",
+        "newRegionalReferenceImageOk": "已创建局部参考图像",
+        "newControlLayerOk": "已创建控制层",
+        "mergeVisibleError": "合并图层时出错",
+        "bboxOverlay": "显示边界框覆盖层",
+        "clipToBbox": "将Clip限制到边界框",
+        "width": "宽度",
+        "addGlobalReferenceImage": "添加 $t(controlLayers.globalReferenceImage)",
+        "inpaintMask_withCount_other": "修复遮罩",
+        "regionalGuidance_withCount_other": "区域引导",
+        "newRegionalReferenceImageError": "创建局部参考图像时出现问题",
+        "pullBboxIntoLayerError": "将边界框导入图层时出现问题",
+        "pullBboxIntoLayerOk": "边界框已导入到图层",
+        "sendToCanvasDesc": "按下“Invoke”按钮会将您的工作进度暂存到画布上。",
+        "sendToGallery": "发送到图库",
+        "sendToGalleryDesc": "按下“Invoke”键会生成并保存一张唯一的图像到您的图库中。",
+        "rasterLayer_withCount_other": "栅格图层",
+        "mergeDown": "向下合并",
+        "clearCaches": "清除缓存",
+        "recalculateRects": "重新计算矩形",
+        "duplicate": "复制",
+        "regionalGuidance_withCount_hidden": "区域引导（{{count}} 个已隐藏）",
+        "convertControlLayerTo": "将 $t(controlLayers.controlLayer) 转换为",
+        "convertInpaintMaskTo": "将 $t(controlLayers.inpaintMask) 转换为",
+        "viewProgressInViewer": "在 <Btn>图像查看器</Btn> 中查看进度和输出结果。",
+        "viewProgressOnCanvas": "在 <Btn>画布</Btn> 上查看进度和暂存的输出内容。",
+        "sendingToGallery": "将生成内容发送到图库",
+        "copyToClipboard": "复制到剪贴板",
+        "controlLayer_withCount_other": "控制图层",
+        "sendingToCanvas": "在画布上准备生成",
+        "addReferenceImage": "添加 $t(controlLayers.referenceImage)",
+        "addRegionalGuidance": "添加 $t(controlLayers.regionalGuidance)",
+        "controlLayers_withCount_hidden": "控制图层（{{count}} 个已隐藏）",
+        "rasterLayers_withCount_hidden": "栅格图层（{{count}} 个已隐藏）",
+        "globalReferenceImages_withCount_hidden": "全局参考图像（{{count}} 个已隐藏）",
+        "globalReferenceImages_withCount_visible": "全局参考图像（{{count}} 个）",
+        "layer_withCount_other": "图层（{{count}} 个）",
+        "enableTransparencyEffect": "启用透明效果",
+        "disableTransparencyEffect": "禁用透明效果",
+        "hidingType": "隐藏 {{type}}",
+        "showingType": "显示 {{type}}"
     },
     "ui": {
         "tabs": {

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

@@ -8,10 +8,8 @@ import { useSyncLoggingConfig } from 'app/logging/useSyncLoggingConfig';
 import { appStarted } from 'app/store/middleware/listenerMiddleware/listeners/appStarted';
 import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
 import type { PartialAppConfig } from 'app/types/invokeai';
-import ImageUploadOverlay from 'common/components/ImageUploadOverlay';
 import { useFocusRegionWatcher } from 'common/hooks/focus';
 import { useClearStorage } from 'common/hooks/useClearStorage';
-import { useFullscreenDropzone } from 'common/hooks/useFullscreenDropzone';
 import { useGlobalHotkeys } from 'common/hooks/useGlobalHotkeys';
 import ChangeBoardModal from 'features/changeBoardModal/components/ChangeBoardModal';
 import {
@@ -19,6 +17,7 @@ import {
   NewGallerySessionDialog,
 } from 'features/controlLayers/components/NewSessionConfirmationAlertDialog';
 import DeleteImageModal from 'features/deleteImageModal/components/DeleteImageModal';
+import { FullscreenDropzone } from 'features/dnd/FullscreenDropzone';
 import { DynamicPromptsModal } from 'features/dynamicPrompts/components/DynamicPromptsPreviewModal';
 import DeleteBoardModal from 'features/gallery/components/Boards/DeleteBoardModal';
 import { ImageContextMenu } from 'features/gallery/components/ImageContextMenu/ImageContextMenu';
@@ -28,6 +27,7 @@ import { ClearQueueConfirmationsAlertDialog } from 'features/queue/components/Cl
 import { DeleteStylePresetDialog } from 'features/stylePresets/components/DeleteStylePresetDialog';
 import { StylePresetModal } from 'features/stylePresets/components/StylePresetForm/StylePresetModal';
 import RefreshAfterResetModal from 'features/system/components/SettingsModal/RefreshAfterResetModal';
+import { VideosModal } from 'features/system/components/VideosModal/VideosModal';
 import { configChanged } from 'features/system/store/configSlice';
 import { selectLanguage } from 'features/system/store/systemSelectors';
 import { AppContent } from 'features/ui/components/AppContent';
@@ -62,8 +62,6 @@ const App = ({ config = DEFAULT_CONFIG, studioInitAction }: Props) => {
   useGetOpenAPISchemaQuery();
   useSyncLoggingConfig();
 
-  const { dropzone, isHandlingUpload, setIsHandlingUpload } = useFullscreenDropzone();
-
   const handleReset = useCallback(() => {
     clearStorage();
     location.reload();
@@ -92,19 +90,8 @@ const App = ({ config = DEFAULT_CONFIG, studioInitAction }: Props) => {
 
   return (
     <ErrorBoundary onReset={handleReset} FallbackComponent={AppErrorBoundaryFallback}>
-      <Box
-        id="invoke-app-wrapper"
-        w="100dvw"
-        h="100dvh"
-        position="relative"
-        overflow="hidden"
-        {...dropzone.getRootProps()}
-      >
-        <input {...dropzone.getInputProps()} />
+      <Box id="invoke-app-wrapper" w="100dvw" h="100dvh" position="relative" overflow="hidden">
         <AppContent />
-        {dropzone.isDragActive && isHandlingUpload && (
-          <ImageUploadOverlay dropzone={dropzone} setIsHandlingUpload={setIsHandlingUpload} />
-        )}
       </Box>
       <DeleteImageModal />
       <ChangeBoardModal />
@@ -121,6 +108,8 @@ const App = ({ config = DEFAULT_CONFIG, studioInitAction }: Props) => {
       <NewGallerySessionDialog />
       <NewCanvasSessionDialog />
       <ImageContextMenu />
+      <FullscreenDropzone />
+      <VideosModal />
     </ErrorBoundary>
   );
 };

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

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

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

@@ -19,7 +19,6 @@ import { $workflowCategories } from 'app/store/nanostores/workflowCategories';
 import { createStore } from 'app/store/store';
 import type { PartialAppConfig } from 'app/types/invokeai';
 import Loading from 'common/components/Loading/Loading';
-import AppDndContext from 'features/dnd/components/AppDndContext';
 import type { WorkflowCategory } from 'features/nodes/types/workflow';
 import type { PropsWithChildren, ReactNode } from 'react';
 import React, { lazy, memo, useEffect, useLayoutEffect, useMemo } from 'react';
@@ -237,9 +236,7 @@ const InvokeAIUI = ({
       <Provider store={store}>
         <React.Suspense fallback={<Loading />}>
           <ThemeLocaleProvider>
-            <AppDndContext>
-              <App config={config} studioInitAction={studioInitAction} />
-            </AppDndContext>
+            <App config={config} studioInitAction={studioInitAction} />
           </ThemeLocaleProvider>
         </React.Suspense>
       </Provider>

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

@@ -1,3 +1,4 @@
+import { useStore } from '@nanostores/react';
 import { useAppStore } from 'app/store/storeHooks';
 import { useAssertSingleton } from 'common/hooks/useAssertSingleton';
 import { withResultAsync } from 'common/util/result';
@@ -9,6 +10,7 @@ import { imageDTOToImageObject } from 'features/controlLayers/store/util';
 import { $imageViewer } from 'features/gallery/components/ImageViewer/useImageViewer';
 import { sentImageToCanvas } from 'features/gallery/store/actions';
 import { parseAndRecallAllMetadata } from 'features/metadata/util/handlers';
+import { $hasTemplates } from 'features/nodes/store/nodesSlice';
 import { $isWorkflowListMenuIsOpen } from 'features/nodes/store/workflowListMenu';
 import { $isStylePresetsMenuOpen, activeStylePresetIdChanged } from 'features/stylePresets/store/stylePresetSlice';
 import { toast } from 'features/toast/toast';
@@ -51,6 +53,7 @@ export const useStudioInitAction = (action?: StudioInitAction) => {
   const { t } = useTranslation();
   // Use a ref to ensure that we only perform the action once
   const didInit = useRef(false);
+  const didParseOpenAPISchema = useStore($hasTemplates);
   const store = useAppStore();
   const { getAndLoadWorkflow } = useGetAndLoadLibraryWorkflow();
 
@@ -174,7 +177,7 @@ export const useStudioInitAction = (action?: StudioInitAction) => {
   );
 
   useEffect(() => {
-    if (didInit.current || !action) {
+    if (didInit.current || !action || !didParseOpenAPISchema) {
       return;
     }
 
@@ -187,22 +190,29 @@ export const useStudioInitAction = (action?: StudioInitAction) => {
       case 'selectStylePreset':
         handleSelectStylePreset(action.data.stylePresetId);
         break;
+
       case 'sendToCanvas':
         handleSendToCanvas(action.data.imageName);
         break;
+
       case 'useAllParameters':
         handleUseAllMetadata(action.data.imageName);
         break;
+
       case 'goToDestination':
         handleGoToDestination(action.data.destination);
         break;
+
+      default:
+        break;
     }
   }, [
     handleSendToCanvas,
     handleUseAllMetadata,
     action,
-    handleLoadWorkflow,
     handleSelectStylePreset,
     handleGoToDestination,
+    handleLoadWorkflow,
+    didParseOpenAPISchema,
   ]);
 };

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

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

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

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

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

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

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

@@ -1,12 +1,12 @@
 import { createAction } from '@reduxjs/toolkit';
 import { logger } from 'app/logging/logger';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
-import type { SerializableObject } from 'common/types';
 import { buildAdHocPostProcessingGraph } from 'features/nodes/util/graph/buildAdHocPostProcessingGraph';
 import { toast } from 'features/toast/toast';
 import { t } from 'i18next';
-import { queueApi } from 'services/api/endpoints/queue';
+import { enqueueMutationFixedCacheKeyOptions, queueApi } from 'services/api/endpoints/queue';
 import type { BatchConfig, ImageDTO } from 'services/api/types';
+import type { JsonObject } from 'type-fest';
 
 const log = logger('queue');
 
@@ -32,16 +32,14 @@ export const addAdHocPostProcessingRequestedListener = (startAppListening: AppSt
 
       try {
         const req = dispatch(
-          queueApi.endpoints.enqueueBatch.initiate(enqueueBatchArg, {
-            fixedCacheKey: 'enqueueBatch',
-          })
+          queueApi.endpoints.enqueueBatch.initiate(enqueueBatchArg, enqueueMutationFixedCacheKeyOptions)
         );
 
         const enqueueResult = await req.unwrap();
         req.reset();
-        log.debug({ enqueueResult } as SerializableObject, t('queue.graphQueued'));
+        log.debug({ enqueueResult } as JsonObject, t('queue.graphQueued'));
       } catch (error) {
-        log.error({ enqueueBatchArg } as SerializableObject, t('queue.graphFailedToQueue'));
+        log.error({ enqueueBatchArg } as JsonObject, t('queue.graphFailedToQueue'));
 
         if (error instanceof Object && 'status' in error && error.status === 403) {
           return;

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

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

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

@@ -1,19 +1,22 @@
 import { logger } from 'app/logging/logger';
 import { enqueueRequested } from 'app/store/actions';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
-import type { SerializableObject } from 'common/types';
+import { extractMessageFromAssertionError } from 'common/util/extractMessageFromAssertionError';
 import type { Result } from 'common/util/result';
 import { withResult, withResultAsync } from 'common/util/result';
 import { $canvasManager } from 'features/controlLayers/store/ephemeral';
 import { prepareLinearUIBatch } from 'features/nodes/util/graph/buildLinearBatchConfig';
 import { buildFLUXGraph } from 'features/nodes/util/graph/generation/buildFLUXGraph';
 import { buildSD1Graph } from 'features/nodes/util/graph/generation/buildSD1Graph';
+import { buildSD3Graph } from 'features/nodes/util/graph/generation/buildSD3Graph';
 import { buildSDXLGraph } from 'features/nodes/util/graph/generation/buildSDXLGraph';
 import type { Graph } from 'features/nodes/util/graph/generation/Graph';
+import { toast } from 'features/toast/toast';
 import { serializeError } from 'serialize-error';
-import { queueApi } from 'services/api/endpoints/queue';
+import { enqueueMutationFixedCacheKeyOptions, queueApi } from 'services/api/endpoints/queue';
 import type { Invocation } from 'services/api/types';
-import { assert } from 'tsafe';
+import { assert, AssertionError } from 'tsafe';
+import type { JsonObject } from 'type-fest';
 
 const log = logger('generation');
 
@@ -32,8 +35,8 @@ export const addEnqueueRequestedLinear = (startAppListening: AppStartListening)
       let buildGraphResult: Result<
         {
           g: Graph;
-          noise: Invocation<'noise' | 'flux_denoise'>;
-          posCond: Invocation<'compel' | 'sdxl_compel_prompt' | 'flux_text_encoder'>;
+          noise: Invocation<'noise' | 'flux_denoise' | 'sd3_denoise'>;
+          posCond: Invocation<'compel' | 'sdxl_compel_prompt' | 'flux_text_encoder' | 'sd3_text_encoder'>;
         },
         Error
       >;
@@ -49,6 +52,9 @@ export const addEnqueueRequestedLinear = (startAppListening: AppStartListening)
         case `sd-2`:
           buildGraphResult = await withResultAsync(() => buildSD1Graph(state, manager));
           break;
+        case `sd-3`:
+          buildGraphResult = await withResultAsync(() => buildSD3Graph(state, manager));
+          break;
         case `flux`:
           buildGraphResult = await withResultAsync(() => buildFLUXGraph(state, manager));
           break;
@@ -57,7 +63,17 @@ export const addEnqueueRequestedLinear = (startAppListening: AppStartListening)
       }
 
       if (buildGraphResult.isErr()) {
-        log.error({ error: serializeError(buildGraphResult.error) }, 'Failed to build graph');
+        let description: string | null = null;
+        if (buildGraphResult.error instanceof AssertionError) {
+          description = extractMessageFromAssertionError(buildGraphResult.error);
+        }
+        const error = serializeError(buildGraphResult.error);
+        log.error({ error }, 'Failed to build graph');
+        toast({
+          status: 'error',
+          title: 'Failed to build graph',
+          description,
+        });
         return;
       }
 
@@ -75,9 +91,7 @@ export const addEnqueueRequestedLinear = (startAppListening: AppStartListening)
       }
 
       const req = dispatch(
-        queueApi.endpoints.enqueueBatch.initiate(prepareBatchResult.value, {
-          fixedCacheKey: 'enqueueBatch',
-        })
+        queueApi.endpoints.enqueueBatch.initiate(prepareBatchResult.value, enqueueMutationFixedCacheKeyOptions)
       );
       req.reset();
 
@@ -88,7 +102,7 @@ export const addEnqueueRequestedLinear = (startAppListening: AppStartListening)
         return;
       }
 
-      log.debug({ batchConfig: prepareBatchResult.value } as SerializableObject, 'Enqueued batch');
+      log.debug({ batchConfig: prepareBatchResult.value } as JsonObject, 'Enqueued batch');
     },
   });
 };

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

@@ -1,10 +1,15 @@
+import { logger } from 'app/logging/logger';
 import { enqueueRequested } from 'app/store/actions';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
 import { selectNodesSlice } from 'features/nodes/store/selectors';
+import { isImageFieldCollectionInputInstance } from 'features/nodes/types/field';
+import { isInvocationNode } from 'features/nodes/types/invocation';
 import { buildNodesGraph } from 'features/nodes/util/graph/buildNodesGraph';
 import { buildWorkflowWithValidation } from 'features/nodes/util/workflow/buildWorkflow';
-import { queueApi } from 'services/api/endpoints/queue';
-import type { BatchConfig } from 'services/api/types';
+import { enqueueMutationFixedCacheKeyOptions, queueApi } from 'services/api/endpoints/queue';
+import type { Batch, BatchConfig } from 'services/api/types';
+
+const log = logger('workflows');
 
 export const addEnqueueRequestedNodes = (startAppListening: AppStartListening) => {
   startAppListening({
@@ -26,6 +31,33 @@ export const addEnqueueRequestedNodes = (startAppListening: AppStartListening) =
         delete builtWorkflow.id;
       }
 
+      const data: Batch['data'] = [];
+
+      // Skip edges from batch nodes - these should not be in the graph, they exist only in the UI
+      const imageBatchNodes = nodes.nodes.filter(isInvocationNode).filter((node) => node.data.type === 'image_batch');
+      for (const node of imageBatchNodes) {
+        const images = node.data.inputs['images'];
+        if (!isImageFieldCollectionInputInstance(images)) {
+          log.warn({ nodeId: node.id }, 'Image batch images field is not an image collection');
+          break;
+        }
+        const edgesFromImageBatch = nodes.edges.filter((e) => e.source === node.id && e.sourceHandle === 'image');
+        const batchDataCollectionItem: NonNullable<Batch['data']>[number] = [];
+        for (const edge of edgesFromImageBatch) {
+          if (!edge.targetHandle) {
+            break;
+          }
+          batchDataCollectionItem.push({
+            node_path: edge.target,
+            field_name: edge.targetHandle,
+            items: images.value,
+          });
+        }
+        if (batchDataCollectionItem.length > 0) {
+          data.push(batchDataCollectionItem);
+        }
+      }
+
       const batchConfig: BatchConfig = {
         batch: {
           graph,
@@ -33,15 +65,12 @@ export const addEnqueueRequestedNodes = (startAppListening: AppStartListening) =
           runs: state.params.iterations,
           origin: 'workflows',
           destination: 'gallery',
+          data,
         },
         prepend: action.payload.prepend,
       };
 
-      const req = dispatch(
-        queueApi.endpoints.enqueueBatch.initiate(batchConfig, {
-          fixedCacheKey: 'enqueueBatch',
-        })
-      );
+      const req = dispatch(queueApi.endpoints.enqueueBatch.initiate(batchConfig, enqueueMutationFixedCacheKeyOptions));
       try {
         await req.unwrap();
       } finally {

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

@@ -2,7 +2,7 @@ import { enqueueRequested } from 'app/store/actions';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
 import { prepareLinearUIBatch } from 'features/nodes/util/graph/buildLinearBatchConfig';
 import { buildMultidiffusionUpscaleGraph } from 'features/nodes/util/graph/buildMultidiffusionUpscaleGraph';
-import { queueApi } from 'services/api/endpoints/queue';
+import { enqueueMutationFixedCacheKeyOptions, queueApi } from 'services/api/endpoints/queue';
 
 export const addEnqueueRequestedUpscale = (startAppListening: AppStartListening) => {
   startAppListening({
@@ -16,11 +16,7 @@ export const addEnqueueRequestedUpscale = (startAppListening: AppStartListening)
 
       const batchConfig = prepareLinearUIBatch(state, g, prepend, noise, posCond, 'upscaling', 'gallery');
 
-      const req = dispatch(
-        queueApi.endpoints.enqueueBatch.initiate(batchConfig, {
-          fixedCacheKey: 'enqueueBatch',
-        })
-      );
+      const req = dispatch(queueApi.endpoints.enqueueBatch.initiate(batchConfig, enqueueMutationFixedCacheKeyOptions));
       try {
         await req.unwrap();
       } finally {

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

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

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

@@ -1,334 +0,0 @@
-import { createAction } from '@reduxjs/toolkit';
-import { logger } from 'app/logging/logger';
-import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
-import { deepClone } from 'common/util/deepClone';
-import { selectDefaultControlAdapter, selectDefaultIPAdapter } from 'features/controlLayers/hooks/addLayerHooks';
-import { getPrefixedId } from 'features/controlLayers/konva/util';
-import {
-  controlLayerAdded,
-  entityRasterized,
-  entitySelected,
-  inpaintMaskAdded,
-  rasterLayerAdded,
-  referenceImageAdded,
-  referenceImageIPAdapterImageChanged,
-  rgAdded,
-  rgIPAdapterImageChanged,
-} from 'features/controlLayers/store/canvasSlice';
-import { selectCanvasSlice } from 'features/controlLayers/store/selectors';
-import type {
-  CanvasControlLayerState,
-  CanvasInpaintMaskState,
-  CanvasRasterLayerState,
-  CanvasReferenceImageState,
-  CanvasRegionalGuidanceState,
-} from 'features/controlLayers/store/types';
-import { imageDTOToImageObject, imageDTOToImageWithDims } from 'features/controlLayers/store/util';
-import type { TypesafeDraggableData, TypesafeDroppableData } from 'features/dnd/types';
-import { isValidDrop } from 'features/dnd/util/isValidDrop';
-import { imageToCompareChanged, selectionChanged } from 'features/gallery/store/gallerySlice';
-import { fieldImageValueChanged } from 'features/nodes/store/nodesSlice';
-import { upscaleInitialImageChanged } from 'features/parameters/store/upscaleSlice';
-import { imagesApi } from 'services/api/endpoints/images';
-
-export const dndDropped = createAction<{
-  overData: TypesafeDroppableData;
-  activeData: TypesafeDraggableData;
-}>('dnd/dndDropped');
-
-const log = logger('system');
-
-export const addImageDroppedListener = (startAppListening: AppStartListening) => {
-  startAppListening({
-    actionCreator: dndDropped,
-    effect: (action, { dispatch, getState }) => {
-      const { activeData, overData } = action.payload;
-      if (!isValidDrop(overData, activeData)) {
-        return;
-      }
-
-      if (activeData.payloadType === 'IMAGE_DTO') {
-        log.debug({ activeData, overData }, 'Image dropped');
-      } else if (activeData.payloadType === 'GALLERY_SELECTION') {
-        log.debug({ activeData, overData }, `Images (${getState().gallery.selection.length}) dropped`);
-      } else if (activeData.payloadType === 'NODE_FIELD') {
-        log.debug({ activeData, overData }, 'Node field dropped');
-      } else {
-        log.debug({ activeData, overData }, `Unknown payload dropped`);
-      }
-
-      /**
-       * Image dropped on IP Adapter Layer
-       */
-      if (
-        overData.actionType === 'SET_IPA_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { id } = overData.context;
-        dispatch(
-          referenceImageIPAdapterImageChanged({
-            entityIdentifier: { id, type: 'reference_image' },
-            imageDTO: activeData.payload.imageDTO,
-          })
-        );
-        return;
-      }
-
-      /**
-       * Image dropped on RG Layer IP Adapter
-       */
-      if (
-        overData.actionType === 'SET_RG_IP_ADAPTER_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { id, referenceImageId } = overData.context;
-        dispatch(
-          rgIPAdapterImageChanged({
-            entityIdentifier: { id, type: 'regional_guidance' },
-            referenceImageId,
-            imageDTO: activeData.payload.imageDTO,
-          })
-        );
-        return;
-      }
-
-      /**
-       * Image dropped on Raster layer
-       */
-      if (
-        overData.actionType === 'ADD_RASTER_LAYER_FROM_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const imageObject = imageDTOToImageObject(activeData.payload.imageDTO);
-        const { x, y } = selectCanvasSlice(getState()).bbox.rect;
-        const overrides: Partial<CanvasRasterLayerState> = {
-          objects: [imageObject],
-          position: { x, y },
-        };
-        dispatch(rasterLayerAdded({ overrides, isSelected: true }));
-        return;
-      }
-
-      /**
-
-      /**
-       * Image dropped on Inpaint Mask
-       */
-      if (
-        overData.actionType === 'ADD_INPAINT_MASK_FROM_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const imageObject = imageDTOToImageObject(activeData.payload.imageDTO);
-        const { x, y } = selectCanvasSlice(getState()).bbox.rect;
-        const overrides: Partial<CanvasInpaintMaskState> = {
-          objects: [imageObject],
-          position: { x, y },
-        };
-        dispatch(inpaintMaskAdded({ overrides, isSelected: true }));
-        return;
-      }
-
-      /**
-
-      /**
-       * Image dropped on Regional Guidance
-       */
-      if (
-        overData.actionType === 'ADD_REGIONAL_GUIDANCE_FROM_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const imageObject = imageDTOToImageObject(activeData.payload.imageDTO);
-        const { x, y } = selectCanvasSlice(getState()).bbox.rect;
-        const overrides: Partial<CanvasRegionalGuidanceState> = {
-          objects: [imageObject],
-          position: { x, y },
-        };
-        dispatch(rgAdded({ overrides, isSelected: true }));
-        return;
-      }
-
-      /**
-       * Image dropped on Raster layer
-       */
-      if (
-        overData.actionType === 'ADD_CONTROL_LAYER_FROM_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const state = getState();
-        const imageObject = imageDTOToImageObject(activeData.payload.imageDTO);
-        const { x, y } = selectCanvasSlice(state).bbox.rect;
-        const defaultControlAdapter = selectDefaultControlAdapter(state);
-        const overrides: Partial<CanvasControlLayerState> = {
-          objects: [imageObject],
-          position: { x, y },
-          controlAdapter: defaultControlAdapter,
-        };
-        dispatch(controlLayerAdded({ overrides, isSelected: true }));
-        return;
-      }
-
-      if (
-        overData.actionType === 'ADD_REGIONAL_REFERENCE_IMAGE_FROM_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const state = getState();
-        const ipAdapter = deepClone(selectDefaultIPAdapter(state));
-        ipAdapter.image = imageDTOToImageWithDims(activeData.payload.imageDTO);
-        const overrides: Partial<CanvasRegionalGuidanceState> = {
-          referenceImages: [{ id: getPrefixedId('regional_guidance_reference_image'), ipAdapter }],
-        };
-        dispatch(rgAdded({ overrides, isSelected: true }));
-        return;
-      }
-
-      if (
-        overData.actionType === 'ADD_GLOBAL_REFERENCE_IMAGE_FROM_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const state = getState();
-        const ipAdapter = deepClone(selectDefaultIPAdapter(state));
-        ipAdapter.image = imageDTOToImageWithDims(activeData.payload.imageDTO);
-        const overrides: Partial<CanvasReferenceImageState> = {
-          ipAdapter,
-        };
-        dispatch(referenceImageAdded({ overrides, isSelected: true }));
-        return;
-      }
-
-      /**
-       * Image dropped on Raster layer
-       */
-      if (overData.actionType === 'REPLACE_LAYER_WITH_IMAGE' && activeData.payloadType === 'IMAGE_DTO') {
-        const state = getState();
-        const { entityIdentifier } = overData.context;
-        const imageObject = imageDTOToImageObject(activeData.payload.imageDTO);
-        const { x, y } = selectCanvasSlice(state).bbox.rect;
-        dispatch(entityRasterized({ entityIdentifier, imageObject, position: { x, y }, replaceObjects: true }));
-        dispatch(entitySelected({ entityIdentifier }));
-        return;
-      }
-
-      /**
-       * Image dropped on node image field
-       */
-      if (
-        overData.actionType === 'SET_NODES_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { fieldName, nodeId } = overData.context;
-        dispatch(
-          fieldImageValueChanged({
-            nodeId,
-            fieldName,
-            value: activeData.payload.imageDTO,
-          })
-        );
-        return;
-      }
-
-      /**
-       * Image selected for compare
-       */
-      if (
-        overData.actionType === 'SELECT_FOR_COMPARE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { imageDTO } = activeData.payload;
-        dispatch(imageToCompareChanged(imageDTO));
-        return;
-      }
-
-      /**
-       * Image dropped on user board
-       */
-      if (
-        overData.actionType === 'ADD_TO_BOARD' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { imageDTO } = activeData.payload;
-        const { boardId } = overData.context;
-        dispatch(
-          imagesApi.endpoints.addImageToBoard.initiate({
-            imageDTO,
-            board_id: boardId,
-          })
-        );
-        dispatch(selectionChanged([]));
-        return;
-      }
-
-      /**
-       * Image dropped on 'none' board
-       */
-      if (
-        overData.actionType === 'REMOVE_FROM_BOARD' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { imageDTO } = activeData.payload;
-        dispatch(
-          imagesApi.endpoints.removeImageFromBoard.initiate({
-            imageDTO,
-          })
-        );
-        dispatch(selectionChanged([]));
-        return;
-      }
-
-      /**
-       * Image dropped on upscale initial image
-       */
-      if (
-        overData.actionType === 'SET_UPSCALE_INITIAL_IMAGE' &&
-        activeData.payloadType === 'IMAGE_DTO' &&
-        activeData.payload.imageDTO
-      ) {
-        const { imageDTO } = activeData.payload;
-
-        dispatch(upscaleInitialImageChanged(imageDTO));
-        return;
-      }
-
-      /**
-       * Multiple images dropped on user board
-       */
-      if (overData.actionType === 'ADD_TO_BOARD' && activeData.payloadType === 'GALLERY_SELECTION') {
-        const imageDTOs = getState().gallery.selection;
-        const { boardId } = overData.context;
-        dispatch(
-          imagesApi.endpoints.addImagesToBoard.initiate({
-            imageDTOs,
-            board_id: boardId,
-          })
-        );
-        dispatch(selectionChanged([]));
-        return;
-      }
-
-      /**
-       * Multiple images dropped on 'none' board
-       */
-      if (overData.actionType === 'REMOVE_FROM_BOARD' && activeData.payloadType === 'GALLERY_SELECTION') {
-        const imageDTOs = getState().gallery.selection;
-        dispatch(
-          imagesApi.endpoints.removeImagesFromBoard.initiate({
-            imageDTOs,
-          })
-        );
-        dispatch(selectionChanged([]));
-        return;
-      }
-    },
-  });
-};

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

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

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

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

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

@@ -4,8 +4,10 @@ import { atom } from 'nanostores';
 /**
  * A fallback non-writable atom that always returns `false`, used when a nanostores atom is only conditionally available
  * in a hook or component.
+ *
+ * @knipignore
  */
-// export const $false: ReadableAtom<boolean> = atom(false);
+export const $false: ReadableAtom<boolean> = atom(false);
 /**
  * A fallback non-writable atom that always returns `true`, used when a nanostores atom is only conditionally available
  * in a hook or component.

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

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

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

@@ -26,7 +26,6 @@ export type AppFeature =
   | 'bulkDownload'
   | 'starterModels'
   | 'hfToken';
-
 /**
  * A disable-able Stable Diffusion feature
  */

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

@@ -1,5 +1,6 @@
 import type { PopoverProps } from '@invoke-ai/ui-library';
 import commercialLicenseBg from 'public/assets/images/commercial-license-bg.png';
+import denoisingStrength from 'public/assets/images/denoising-strength.png';
 
 export type Feature =
   | 'clipSkip'
@@ -125,7 +126,7 @@ export const POPOVER_DATA: { [key in Feature]?: PopoverData } = {
     href: 'https://support.invoke.ai/support/solutions/articles/151000158838-compositing-settings',
   },
   infillMethod: {
-    href: 'https://support.invoke.ai/support/solutions/articles/151000158841-infill-and-scaling',
+    href: 'https://support.invoke.ai/support/solutions/articles/151000158838-compositing-settings',
   },
   scaleBeforeProcessing: {
     href: 'https://support.invoke.ai/support/solutions/articles/151000158841',
@@ -138,6 +139,7 @@ export const POPOVER_DATA: { [key in Feature]?: PopoverData } = {
   },
   paramDenoisingStrength: {
     href: 'https://support.invoke.ai/support/solutions/articles/151000094998-image-to-image',
+    image: denoisingStrength,
   },
   paramHrf: {
     href: 'https://support.invoke.ai/support/solutions/articles/151000096700-how-can-i-get-larger-images-what-does-upscaling-do-',

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

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

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

@@ -2,6 +2,7 @@ import { deepClone } from 'common/util/deepClone';
 import { merge } from 'lodash-es';
 import { ClickScrollPlugin, OverlayScrollbars } from 'overlayscrollbars';
 import type { UseOverlayScrollbarsParams } from 'overlayscrollbars-react';
+import type { CSSProperties } from 'react';
 
 OverlayScrollbars.plugin(ClickScrollPlugin);
 
@@ -27,3 +28,8 @@ export const getOverlayScrollbarsParams = (
   merge(params, { options: { overflow: { y: overflowY, x: overflowX } } });
   return params;
 };
+
+export const overlayScrollbarsStyles: CSSProperties = {
+  height: '100%',
+  width: '100%',
+};

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

@@ -0,0 +1,42 @@
+import { MenuItem } from '@invoke-ai/ui-library';
+import { useAppDispatch } from 'app/store/storeHooks';
+import {
+  useNewCanvasSession,
+  useNewGallerySession,
+} from 'features/controlLayers/components/NewSessionConfirmationAlertDialog';
+import { canvasReset } from 'features/controlLayers/store/actions';
+import { paramsReset } from 'features/controlLayers/store/paramsSlice';
+import { memo, useCallback } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiArrowsCounterClockwiseBold, PiFilePlusBold } from 'react-icons/pi';
+
+export const SessionMenuItems = memo(() => {
+  const { t } = useTranslation();
+  const dispatch = useAppDispatch();
+  const { newGallerySessionWithDialog } = useNewGallerySession();
+  const { newCanvasSessionWithDialog } = useNewCanvasSession();
+  const resetCanvasLayers = useCallback(() => {
+    dispatch(canvasReset());
+  }, [dispatch]);
+  const resetGenerationSettings = useCallback(() => {
+    dispatch(paramsReset());
+  }, [dispatch]);
+  return (
+    <>
+      <MenuItem icon={<PiFilePlusBold />} onClick={newGallerySessionWithDialog}>
+        {t('controlLayers.newGallerySession')}
+      </MenuItem>
+      <MenuItem icon={<PiFilePlusBold />} onClick={newCanvasSessionWithDialog}>
+        {t('controlLayers.newCanvasSession')}
+      </MenuItem>
+      <MenuItem icon={<PiArrowsCounterClockwiseBold />} onClick={resetCanvasLayers}>
+        {t('controlLayers.resetCanvasLayers')}
+      </MenuItem>
+      <MenuItem icon={<PiArrowsCounterClockwiseBold />} onClick={resetGenerationSettings}>
+        {t('controlLayers.resetGenerationSettings')}
+      </MenuItem>
+    </>
+  );
+});
+
+SessionMenuItems.displayName = 'SessionMenuItems';

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

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

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

@@ -46,7 +46,7 @@ const REGION_TARGETS: Record<FocusRegionName, Set<HTMLElement>> = {
 /**
  * The currently-focused region or `null` if no region is focused.
  */
-const $focusedRegion = atom<FocusRegionName | null>(null);
+export const $focusedRegion = atom<FocusRegionName | null>(null);
 
 /**
  * A map of focus regions to atoms that indicate if that region is focused.

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

@@ -1,124 +0,0 @@
-import { logger } from 'app/logging/logger';
-import { useAppSelector } from 'app/store/storeHooks';
-import { useAssertSingleton } from 'common/hooks/useAssertSingleton';
-import { selectAutoAddBoardId } from 'features/gallery/store/gallerySelectors';
-import { selectMaxImageUploadCount } from 'features/system/store/configSlice';
-import { toast } from 'features/toast/toast';
-import { selectActiveTab } from 'features/ui/store/uiSelectors';
-import { useCallback, useEffect, useState } from 'react';
-import type { Accept, FileRejection } from 'react-dropzone';
-import { useDropzone } from 'react-dropzone';
-import { useTranslation } from 'react-i18next';
-import { useUploadImageMutation } from 'services/api/endpoints/images';
-import type { PostUploadAction } from 'services/api/types';
-
-const log = logger('gallery');
-
-const accept: Accept = {
-  'image/png': ['.png'],
-  'image/jpeg': ['.jpg', '.jpeg', '.png'],
-};
-
-export const useFullscreenDropzone = () => {
-  useAssertSingleton('useFullscreenDropzone');
-  const { t } = useTranslation();
-  const autoAddBoardId = useAppSelector(selectAutoAddBoardId);
-  const [isHandlingUpload, setIsHandlingUpload] = useState<boolean>(false);
-  const [uploadImage] = useUploadImageMutation();
-  const activeTabName = useAppSelector(selectActiveTab);
-  const maxImageUploadCount = useAppSelector(selectMaxImageUploadCount);
-
-  const getPostUploadAction = useCallback((): PostUploadAction => {
-    if (activeTabName === 'upscaling') {
-      return { type: 'SET_UPSCALE_INITIAL_IMAGE' };
-    } else {
-      return { type: 'TOAST' };
-    }
-  }, [activeTabName]);
-
-  const onDrop = useCallback(
-    (acceptedFiles: Array<File>, fileRejections: Array<FileRejection>) => {
-      if (fileRejections.length > 0) {
-        const errors = fileRejections.map((rejection) => ({
-          errors: rejection.errors.map(({ message }) => message),
-          file: rejection.file.path,
-        }));
-        log.error({ errors }, 'Invalid upload');
-        const description =
-          maxImageUploadCount === undefined
-            ? t('toast.uploadFailedInvalidUploadDesc')
-            : t('toast.uploadFailedInvalidUploadDesc_withCount', { count: maxImageUploadCount });
-
-        toast({
-          id: 'UPLOAD_FAILED',
-          title: t('toast.uploadFailed'),
-          description,
-          status: 'error',
-        });
-
-        setIsHandlingUpload(false);
-        return;
-      }
-
-      for (const [i, file] of acceptedFiles.entries()) {
-        uploadImage({
-          file,
-          image_category: 'user',
-          is_intermediate: false,
-          postUploadAction: getPostUploadAction(),
-          board_id: autoAddBoardId === 'none' ? undefined : autoAddBoardId,
-          // The `imageUploaded` listener does some extra logic, like switching to the asset view on upload on the
-          // first upload of a "batch".
-          isFirstUploadOfBatch: i === 0,
-        });
-      }
-
-      setIsHandlingUpload(false);
-    },
-    [t, maxImageUploadCount, uploadImage, getPostUploadAction, autoAddBoardId]
-  );
-
-  const onDragOver = useCallback(() => {
-    setIsHandlingUpload(true);
-  }, []);
-
-  const onDragLeave = useCallback(() => {
-    setIsHandlingUpload(false);
-  }, []);
-
-  const dropzone = useDropzone({
-    accept,
-    noClick: true,
-    onDrop,
-    onDragOver,
-    onDragLeave,
-    noKeyboard: true,
-    multiple: maxImageUploadCount === undefined || maxImageUploadCount > 1,
-    maxFiles: maxImageUploadCount,
-  });
-
-  useEffect(() => {
-    // This is a hack to allow pasting images into the uploader
-    const handlePaste = (e: ClipboardEvent) => {
-      if (!dropzone.inputRef.current) {
-        return;
-      }
-
-      if (e.clipboardData?.files) {
-        // Set the files on the dropzone.inputRef
-        dropzone.inputRef.current.files = e.clipboardData.files;
-        // Dispatch the change event, dropzone catches this and we get to use its own validation
-        dropzone.inputRef.current?.dispatchEvent(new Event('change', { bubbles: true }));
-      }
-    };
-
-    // Add the paste event listener
-    document.addEventListener('paste', handlePaste);
-
-    return () => {
-      document.removeEventListener('paste', handlePaste);
-    };
-  }, [dropzone.inputRef]);
-
-  return { dropzone, isHandlingUpload, setIsHandlingUpload };
-};