ruff

SECURITY.md

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

docs/contributing/MODEL_MANAGER.md

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

docs/contributing/index.md

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

docs/nodes/defaultNodes.md

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

invokeai/app/api/routers/model_manager.py

@@ -37,7 +37,7 @@ from invokeai.backend.model_manager.config import (
     ModelFormat,
     ModelType,
 )
-from invokeai.backend.model_manager.load.model_cache.cache_stats import CacheStats
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import CacheStats
 from invokeai.backend.model_manager.metadata.fetch.huggingface import HuggingFaceMetadataFetch
 from invokeai.backend.model_manager.metadata.metadata_base import ModelMetadataWithFiles, UnknownMetadataException
 from invokeai.backend.model_manager.search import ModelSearch
@@ -751,7 +751,7 @@ async def convert_model(
 
     with TemporaryDirectory(dir=ApiDependencies.invoker.services.configuration.models_path) as tmpdir:
         convert_path = pathlib.Path(tmpdir) / pathlib.Path(model_config.path).stem
-        converted_model = loader.load_model(model_config)
+        converted_model = loader.load_model(model_config, queue_id="default")
         # write the converted file to the convert path
         raw_model = converted_model.model
         assert hasattr(raw_model, "save_pretrained")

invokeai/app/api/routers/session_queue.py

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

invokeai/app/api/sockets.py

@@ -31,6 +31,7 @@ from invokeai.app.services.events.events_common import (
     ModelInstallErrorEvent,
     ModelInstallStartedEvent,
     ModelLoadCompleteEvent,
+    ModelLoadEventBase,
     ModelLoadStartedEvent,
     QueueClearedEvent,
     QueueEventBase,
@@ -53,6 +54,13 @@ class BulkDownloadSubscriptionEvent(BaseModel):
     bulk_download_id: str
 
 
+class ModelLoadSubscriptionEvent(BaseModel):
+    """Event data for subscribing to the socket.io model loading room.
+    This is a pydantic model to ensure the data is in the correct format."""
+
+    queue_id: str
+
+
 QUEUE_EVENTS = {
     InvocationStartedEvent,
     InvocationProgressEvent,
@@ -69,8 +77,6 @@ MODEL_EVENTS = {
     DownloadErrorEvent,
     DownloadProgressEvent,
     DownloadStartedEvent,
-    ModelLoadStartedEvent,
-    ModelLoadCompleteEvent,
     ModelInstallDownloadProgressEvent,
     ModelInstallDownloadsCompleteEvent,
     ModelInstallStartedEvent,
@@ -79,6 +85,11 @@ MODEL_EVENTS = {
     ModelInstallErrorEvent,
 }
 
+MODEL_LOAD_EVENTS = {
+    ModelLoadStartedEvent,
+    ModelLoadCompleteEvent,
+}
+
 BULK_DOWNLOAD_EVENTS = {BulkDownloadStartedEvent, BulkDownloadCompleteEvent, BulkDownloadErrorEvent}
 
 
@@ -101,6 +112,7 @@ class SocketIO:
 
         register_events(QUEUE_EVENTS, self._handle_queue_event)
         register_events(MODEL_EVENTS, self._handle_model_event)
+        register_events(MODEL_LOAD_EVENTS, self._handle_model_load_event)
         register_events(BULK_DOWNLOAD_EVENTS, self._handle_bulk_image_download_event)
 
     async def _handle_sub_queue(self, sid: str, data: Any) -> None:
@@ -115,9 +127,18 @@ class SocketIO:
     async def _handle_unsub_bulk_download(self, sid: str, data: Any) -> None:
         await self._sio.leave_room(sid, BulkDownloadSubscriptionEvent(**data).bulk_download_id)
 
+    async def _handle_sub_model_load(self, sid: str, data: Any) -> None:
+        await self._sio.enter_room(sid, ModelLoadSubscriptionEvent(**data).queue_id)
+
+    async def _handle_unsub_model_load(self, sid: str, data: Any) -> None:
+        await self._sio.leave_room(sid, ModelLoadSubscriptionEvent(**data).queue_id)
+
     async def _handle_queue_event(self, event: FastAPIEvent[QueueEventBase]):
         await self._sio.emit(event=event[0], data=event[1].model_dump(mode="json"), room=event[1].queue_id)
 
+    async def _handle_model_load_event(self, event: FastAPIEvent[ModelLoadEventBase]) -> None:
+        await self._sio.emit(event=event[0], data=event[1].model_dump(mode="json"), room=event[1].queue_id)
+
     async def _handle_model_event(self, event: FastAPIEvent[ModelEventBase | DownloadEventBase]) -> None:
         await self._sio.emit(event=event[0], data=event[1].model_dump(mode="json"))
 

invokeai/app/invocations/baseinvocation.py

@@ -63,7 +63,6 @@ class Classification(str, Enum, metaclass=MetaEnum):
     - `Prototype`: The invocation is not yet stable and may be removed from the application at any time. Workflows built around this invocation may break, and we are *not* committed to supporting this invocation.
     - `Deprecated`: The invocation is deprecated and may be removed in a future version.
     - `Internal`: The invocation is not intended for use by end-users. It may be changed or removed at any time, but is exposed for users to play with.
-    - `Special`: The invocation is a special case and does not fit into any of the other classifications.
     """
 
     Stable = "stable"
@@ -71,7 +70,6 @@ class Classification(str, Enum, metaclass=MetaEnum):
     Prototype = "prototype"
     Deprecated = "deprecated"
     Internal = "internal"
-    Special = "special"
 
 
 class UIConfigBase(BaseModel):

invokeai/app/invocations/blend_latents.py

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

invokeai/app/invocations/compel.py

@@ -63,12 +63,12 @@ class CompelInvocation(BaseInvocation):
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        tokenizer_info = context.models.load(self.clip.tokenizer)
-        text_encoder_info = context.models.load(self.clip.text_encoder)
+        tokenizer_info = context.models.load(self.clip.tokenizer, queue_id=context.util.get_queue_id())
+        text_encoder_info = context.models.load(self.clip.text_encoder, queue_id=context.util.get_queue_id())
 
         def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in self.clip.loras:
-                lora_info = context.models.load(lora.lora)
+                lora_info = context.models.load(lora.lora, queue_id=context.util.get_queue_id())
                 assert isinstance(lora_info.model, LoRAModelRaw)
                 yield (lora_info.model, lora.weight)
                 del lora_info
@@ -95,7 +95,6 @@ class CompelInvocation(BaseInvocation):
                 ti_manager,
             ),
         ):
-            context.util.signal_progress("Building conditioning")
             assert isinstance(text_encoder, CLIPTextModel)
             assert isinstance(tokenizer, CLIPTokenizer)
             compel = Compel(
@@ -138,8 +137,8 @@ class SDXLPromptInvocationBase:
         lora_prefix: str,
         zero_on_empty: bool,
     ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
-        tokenizer_info = context.models.load(clip_field.tokenizer)
-        text_encoder_info = context.models.load(clip_field.text_encoder)
+        tokenizer_info = context.models.load(clip_field.tokenizer, queue_id=context.util.get_queue_id())
+        text_encoder_info = context.models.load(clip_field.text_encoder, queue_id=context.util.get_queue_id())
 
         # return zero on empty
         if prompt == "" and zero_on_empty:
@@ -164,7 +163,7 @@ class SDXLPromptInvocationBase:
 
         def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in clip_field.loras:
-                lora_info = context.models.load(lora.lora)
+                lora_info = context.models.load(lora.lora, context.util.get_queue_id())
                 lora_model = lora_info.model
                 assert isinstance(lora_model, LoRAModelRaw)
                 yield (lora_model, lora.weight)
@@ -192,7 +191,6 @@ class SDXLPromptInvocationBase:
                 ti_manager,
             ),
         ):
-            context.util.signal_progress("Building conditioning")
             assert isinstance(text_encoder, (CLIPTextModel, CLIPTextModelWithProjection))
             assert isinstance(tokenizer, CLIPTokenizer)
 

invokeai/app/invocations/controlnet_image_processors.py

@@ -649,7 +649,9 @@ class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
             return DepthAnythingPipeline(depth_anything_pipeline)
 
         with self._context.models.load_remote_model(
-            source=DEPTH_ANYTHING_MODELS[self.model_size], loader=load_depth_anything
+            source=DEPTH_ANYTHING_MODELS[self.model_size],
+            queue_id=self._context.util.get_queue_id(),
+            loader=load_depth_anything,
         ) as depth_anything_detector:
             assert isinstance(depth_anything_detector, DepthAnythingPipeline)
             depth_map = depth_anything_detector.generate_depth(image)

invokeai/app/invocations/create_denoise_mask.py

@@ -60,12 +60,11 @@ class CreateDenoiseMaskInvocation(BaseInvocation):
         )
 
         if image_tensor is not None:
-            vae_info = context.models.load(self.vae.vae)
+            vae_info = context.models.load(self.vae.vae, context.util.get_queue_id())
 
             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

@@ -124,14 +124,13 @@ class CreateGradientMaskInvocation(BaseInvocation):
             assert isinstance(main_model_config, MainConfigBase)
             if main_model_config.variant is ModelVariantType.Inpaint:
                 mask = blur_tensor
-                vae_info: LoadedModel = context.models.load(self.vae.vae)
+                vae_info: LoadedModel = context.models.load(self.vae.vae, context.util.get_queue_id())
                 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 = image_tensor.unsqueeze(0)
                 img_mask = tv_resize(mask, image_tensor.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
                 masked_image = image_tensor * torch.where(img_mask < 0.5, 0.0, 1.0)
-                context.util.signal_progress("Running VAE encoder")
                 masked_latents = ImageToLatentsInvocation.vae_encode(
                     vae_info, self.fp32, self.tiled, masked_image.clone()
                 )

invokeai/app/invocations/denoise_latents.py

@@ -88,7 +88,7 @@ def get_scheduler(
     # TODO(ryand): Silently falling back to ddim seems like a bad idea. Look into why this was added and remove if
     # possible.
     scheduler_class, scheduler_extra_config = SCHEDULER_MAP.get(scheduler_name, SCHEDULER_MAP["ddim"])
-    orig_scheduler_info = context.models.load(scheduler_info)
+    orig_scheduler_info = context.models.load(scheduler_info, context.util.get_queue_id())
     with orig_scheduler_info as orig_scheduler:
         scheduler_config = orig_scheduler.config
 
@@ -435,7 +435,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         controlnet_data: list[ControlNetData] = []
         for control_info in control_list:
-            control_model = exit_stack.enter_context(context.models.load(control_info.control_model))
+            control_model = exit_stack.enter_context(
+                context.models.load(control_info.control_model, context.util.get_queue_id())
+            )
             assert isinstance(control_model, ControlNetModel)
 
             control_image_field = control_info.image
@@ -492,7 +494,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
             raise ValueError(f"Unexpected control_input type: {type(control_input)}")
 
         for control_info in control_list:
-            model = exit_stack.enter_context(context.models.load(control_info.control_model))
+            model = exit_stack.enter_context(
+                context.models.load(control_info.control_model, context.util.get_queue_id())
+            )
             ext_manager.add_extension(
                 ControlNetExt(
                     model=model,
@@ -545,9 +549,13 @@ class DenoiseLatentsInvocation(BaseInvocation):
         """Run the IPAdapter CLIPVisionModel, returning image prompt embeddings."""
         image_prompts = []
         for single_ip_adapter in ip_adapters:
-            with context.models.load(single_ip_adapter.ip_adapter_model) as ip_adapter_model:
+            with context.models.load(
+                single_ip_adapter.ip_adapter_model, context.util.get_queue_id()
+            ) as ip_adapter_model:
                 assert isinstance(ip_adapter_model, IPAdapter)
-                image_encoder_model_info = context.models.load(single_ip_adapter.image_encoder_model)
+                image_encoder_model_info = context.models.load(
+                    single_ip_adapter.image_encoder_model, context.util.get_queue_id()
+                )
                 # `single_ip_adapter.image` could be a list or a single ImageField. Normalize to a list here.
                 single_ipa_image_fields = single_ip_adapter.image
                 if not isinstance(single_ipa_image_fields, list):
@@ -581,7 +589,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
         for single_ip_adapter, (image_prompt_embeds, uncond_image_prompt_embeds) in zip(
             ip_adapters, image_prompts, strict=True
         ):
-            ip_adapter_model = exit_stack.enter_context(context.models.load(single_ip_adapter.ip_adapter_model))
+            ip_adapter_model = exit_stack.enter_context(
+                context.models.load(single_ip_adapter.ip_adapter_model, context.util.get_queue_id())
+            )
 
             mask_field = single_ip_adapter.mask
             mask = context.tensors.load(mask_field.tensor_name) if mask_field is not None else None
@@ -621,7 +631,9 @@ class DenoiseLatentsInvocation(BaseInvocation):
         t2i_adapter_data = []
         for t2i_adapter_field in t2i_adapter:
             t2i_adapter_model_config = context.models.get_config(t2i_adapter_field.t2i_adapter_model.key)
-            t2i_adapter_loaded_model = context.models.load(t2i_adapter_field.t2i_adapter_model)
+            t2i_adapter_loaded_model = context.models.load(
+                t2i_adapter_field.t2i_adapter_model, context.util.get_queue_id()
+            )
             image = context.images.get_pil(t2i_adapter_field.image.image_name, mode="RGB")
 
             # The max_unet_downscale is the maximum amount that the UNet model downscales the latent image internally.
@@ -926,7 +938,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
             # ext: t2i/ip adapter
             ext_manager.run_callback(ExtensionCallbackType.SETUP, denoise_ctx)
 
-            unet_info = context.models.load(self.unet.unet)
+            unet_info = context.models.load(self.unet.unet, context.util.get_queue_id())
             assert isinstance(unet_info.model, UNet2DConditionModel)
             with (
                 unet_info.model_on_device() as (cached_weights, unet),
@@ -989,13 +1001,13 @@ class DenoiseLatentsInvocation(BaseInvocation):
 
         def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in self.unet.loras:
-                lora_info = context.models.load(lora.lora)
+                lora_info = context.models.load(lora.lora, context.util.get_queue_id())
                 assert isinstance(lora_info.model, LoRAModelRaw)
                 yield (lora_info.model, lora.weight)
                 del lora_info
             return
 
-        unet_info = context.models.load(self.unet.unet)
+        unet_info = context.models.load(self.unet.unet, context.util.get_queue_id())
         assert isinstance(unet_info.model, UNet2DConditionModel)
         with (
             ExitStack() as exit_stack,

invokeai/app/invocations/depth_anything.py

@@ -35,7 +35,9 @@ class DepthAnythingDepthEstimationInvocation(BaseInvocation, WithMetadata, WithB
         model_url = DEPTH_ANYTHING_MODELS[self.model_size]
         image = context.images.get_pil(self.image.image_name, "RGB")
 
-        loaded_model = context.models.load_remote_model(model_url, DepthAnythingPipeline.load_model)
+        loaded_model = context.models.load_remote_model(
+            model_url, context.util.get_queue_id(), DepthAnythingPipeline.load_model
+        )
 
         with loaded_model as depth_anything_detector:
             assert isinstance(depth_anything_detector, DepthAnythingPipeline)

invokeai/app/invocations/dw_openpose.py

@@ -29,10 +29,10 @@ class DWOpenposeDetectionInvocation(BaseInvocation, WithMetadata, WithBoard):
         onnx_pose_path = context.models.download_and_cache_model(DWOpenposeDetector2.get_model_url_pose())
 
         loaded_session_det = context.models.load_local_model(
-            onnx_det_path, DWOpenposeDetector2.create_onnx_inference_session
+            onnx_det_path, context.util.get_queue_id(), DWOpenposeDetector2.create_onnx_inference_session
         )
         loaded_session_pose = context.models.load_local_model(
-            onnx_pose_path, DWOpenposeDetector2.create_onnx_inference_session
+            onnx_pose_path, context.util.get_queue_id(), DWOpenposeDetector2.create_onnx_inference_session
         )
 
         with loaded_session_det as session_det, loaded_session_pose as session_pose:

invokeai/app/invocations/fields.py

@@ -250,11 +250,6 @@ class FluxConditioningField(BaseModel):
     """A conditioning tensor primitive value"""
 
     conditioning_name: str = Field(description="The name of conditioning tensor")
-    mask: Optional[TensorField] = Field(
-        default=None,
-        description="The mask associated with this conditioning tensor. Excluded regions should be set to False, "
-        "included regions should be set to True.",
-    )
 
 
 class SD3ConditioningField(BaseModel):

invokeai/app/invocations/flux_denoise.py

@@ -30,7 +30,6 @@ from invokeai.backend.flux.controlnet.xlabs_controlnet_flux import XLabsControlN
 from invokeai.backend.flux.denoise import denoise
 from invokeai.backend.flux.extensions.inpaint_extension import InpaintExtension
 from invokeai.backend.flux.extensions.instantx_controlnet_extension import InstantXControlNetExtension
-from invokeai.backend.flux.extensions.regional_prompting_extension import RegionalPromptingExtension
 from invokeai.backend.flux.extensions.xlabs_controlnet_extension import XLabsControlNetExtension
 from invokeai.backend.flux.extensions.xlabs_ip_adapter_extension import XLabsIPAdapterExtension
 from invokeai.backend.flux.ip_adapter.xlabs_ip_adapter_flux import XlabsIpAdapterFlux
@@ -43,7 +42,6 @@ from invokeai.backend.flux.sampling_utils import (
     pack,
     unpack,
 )
-from invokeai.backend.flux.text_conditioning import FluxTextConditioning
 from invokeai.backend.lora.conversions.flux_lora_constants import FLUX_LORA_TRANSFORMER_PREFIX
 from invokeai.backend.lora.lora_model_raw import LoRAModelRaw
 from invokeai.backend.lora.lora_patcher import LoRAPatcher
@@ -58,7 +56,7 @@ from invokeai.backend.util.devices import TorchDevice
     title="FLUX Denoise",
     tags=["image", "flux"],
     category="image",
-    version="3.2.2",
+    version="3.2.0",
     classification=Classification.Prototype,
 )
 class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
@@ -83,16 +81,15 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         description=FieldDescriptions.denoising_start,
     )
     denoising_end: float = InputField(default=1.0, ge=0, le=1, description=FieldDescriptions.denoising_end)
-    add_noise: bool = InputField(default=True, description="Add noise based on denoising start.")
     transformer: TransformerField = InputField(
         description=FieldDescriptions.flux_model,
         input=Input.Connection,
         title="Transformer",
     )
-    positive_text_conditioning: FluxConditioningField | list[FluxConditioningField] = InputField(
+    positive_text_conditioning: FluxConditioningField = InputField(
         description=FieldDescriptions.positive_cond, input=Input.Connection
     )
-    negative_text_conditioning: FluxConditioningField | list[FluxConditioningField] | None = InputField(
+    negative_text_conditioning: FluxConditioningField | None = InputField(
         default=None,
         description="Negative conditioning tensor. Can be None if cfg_scale is 1.0.",
         input=Input.Connection,
@@ -141,12 +138,36 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         name = context.tensors.save(tensor=latents)
         return LatentsOutput.build(latents_name=name, latents=latents, seed=None)
 
+    def _load_text_conditioning(
+        self, context: InvocationContext, conditioning_name: str, dtype: torch.dtype
+    ) -> Tuple[torch.Tensor, torch.Tensor]:
+        # Load the conditioning data.
+        cond_data = context.conditioning.load(conditioning_name)
+        assert len(cond_data.conditionings) == 1
+        flux_conditioning = cond_data.conditionings[0]
+        assert isinstance(flux_conditioning, FLUXConditioningInfo)
+        flux_conditioning = flux_conditioning.to(dtype=dtype)
+        t5_embeddings = flux_conditioning.t5_embeds
+        clip_embeddings = flux_conditioning.clip_embeds
+        return t5_embeddings, clip_embeddings
+
     def _run_diffusion(
         self,
         context: InvocationContext,
     ):
         inference_dtype = torch.bfloat16
 
+        # Load the conditioning data.
+        pos_t5_embeddings, pos_clip_embeddings = self._load_text_conditioning(
+            context, self.positive_text_conditioning.conditioning_name, inference_dtype
+        )
+        neg_t5_embeddings: torch.Tensor | None = None
+        neg_clip_embeddings: torch.Tensor | None = None
+        if self.negative_text_conditioning is not None:
+            neg_t5_embeddings, neg_clip_embeddings = self._load_text_conditioning(
+                context, self.negative_text_conditioning.conditioning_name, inference_dtype
+            )
+
         # Load the input latents, if provided.
         init_latents = context.tensors.load(self.latents.latents_name) if self.latents else None
         if init_latents is not None:
@@ -161,45 +182,15 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
             dtype=inference_dtype,
             seed=self.seed,
         )
-        b, _c, latent_h, latent_w = noise.shape
-        packed_h = latent_h // 2
-        packed_w = latent_w // 2
 
-        # Load the conditioning data.
-        pos_text_conditionings = self._load_text_conditioning(
-            context=context,
-            cond_field=self.positive_text_conditioning,
-            packed_height=packed_h,
-            packed_width=packed_w,
-            dtype=inference_dtype,
-            device=TorchDevice.choose_torch_device(),
-        )
-        neg_text_conditionings: list[FluxTextConditioning] | None = None
-        if self.negative_text_conditioning is not None:
-            neg_text_conditionings = self._load_text_conditioning(
-                context=context,
-                cond_field=self.negative_text_conditioning,
-                packed_height=packed_h,
-                packed_width=packed_w,
-                dtype=inference_dtype,
-                device=TorchDevice.choose_torch_device(),
-            )
-        pos_regional_prompting_extension = RegionalPromptingExtension.from_text_conditioning(
-            pos_text_conditionings, img_seq_len=packed_h * packed_w
-        )
-        neg_regional_prompting_extension = (
-            RegionalPromptingExtension.from_text_conditioning(neg_text_conditionings, img_seq_len=packed_h * packed_w)
-            if neg_text_conditionings
-            else None
-        )
-
-        transformer_info = context.models.load(self.transformer.transformer)
+        transformer_info = context.models.load(self.transformer.transformer, context.util.get_queue_id())
         is_schnell = "schnell" in transformer_info.config.config_path
 
         # Calculate the timestep schedule.
+        image_seq_len = noise.shape[-1] * noise.shape[-2] // 4
         timesteps = get_schedule(
             num_steps=self.num_steps,
-            image_seq_len=packed_h * packed_w,
+            image_seq_len=image_seq_len,
             shift=not is_schnell,
         )
 
@@ -216,12 +207,9 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
                     "to be poor. Consider using a FLUX dev model instead."
                 )
 
-            if self.add_noise:
-                # Noise the orig_latents by the appropriate amount for the first timestep.
-                t_0 = timesteps[0]
-                x = t_0 * noise + (1.0 - t_0) * init_latents
-            else:
-                x = init_latents
+            # Noise the orig_latents by the appropriate amount for the first timestep.
+            t_0 = timesteps[0]
+            x = t_0 * noise + (1.0 - t_0) * init_latents
         else:
             # init_latents are not provided, so we are not doing image-to-image (i.e. we are starting from pure noise).
             if self.denoising_start > 1e-5:
@@ -236,17 +224,28 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
 
         inpaint_mask = self._prep_inpaint_mask(context, x)
 
+        b, _c, latent_h, latent_w = x.shape
         img_ids = generate_img_ids(h=latent_h, w=latent_w, batch_size=b, device=x.device, dtype=x.dtype)
 
+        pos_bs, pos_t5_seq_len, _ = pos_t5_embeddings.shape
+        pos_txt_ids = torch.zeros(
+            pos_bs, pos_t5_seq_len, 3, dtype=inference_dtype, device=TorchDevice.choose_torch_device()
+        )
+        neg_txt_ids: torch.Tensor | None = None
+        if neg_t5_embeddings is not None:
+            neg_bs, neg_t5_seq_len, _ = neg_t5_embeddings.shape
+            neg_txt_ids = torch.zeros(
+                neg_bs, neg_t5_seq_len, 3, dtype=inference_dtype, device=TorchDevice.choose_torch_device()
+            )
+
         # Pack all latent tensors.
         init_latents = pack(init_latents) if init_latents is not None else None
         inpaint_mask = pack(inpaint_mask) if inpaint_mask is not None else None
         noise = pack(noise)
         x = pack(x)
 
-        # Now that we have 'packed' the latent tensors, verify that we calculated the image_seq_len, packed_h, and
-        # packed_w correctly.
-        assert packed_h * packed_w == x.shape[1]
+        # Now that we have 'packed' the latent tensors, verify that we calculated the image_seq_len correctly.
+        assert image_seq_len == x.shape[1]
 
         # Prepare inpaint extension.
         inpaint_extension: InpaintExtension | None = None
@@ -335,8 +334,12 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
                 model=transformer,
                 img=x,
                 img_ids=img_ids,
-                pos_regional_prompting_extension=pos_regional_prompting_extension,
-                neg_regional_prompting_extension=neg_regional_prompting_extension,
+                txt=pos_t5_embeddings,
+                txt_ids=pos_txt_ids,
+                vec=pos_clip_embeddings,
+                neg_txt=neg_t5_embeddings,
+                neg_txt_ids=neg_txt_ids,
+                neg_vec=neg_clip_embeddings,
                 timesteps=timesteps,
                 step_callback=self._build_step_callback(context),
                 guidance=self.guidance,
@@ -350,43 +353,6 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         x = unpack(x.float(), self.height, self.width)
         return x
 
-    def _load_text_conditioning(
-        self,
-        context: InvocationContext,
-        cond_field: FluxConditioningField | list[FluxConditioningField],
-        packed_height: int,
-        packed_width: int,
-        dtype: torch.dtype,
-        device: torch.device,
-    ) -> list[FluxTextConditioning]:
-        """Load text conditioning data from a FluxConditioningField or a list of FluxConditioningFields."""
-        # Normalize to a list of FluxConditioningFields.
-        cond_list = [cond_field] if isinstance(cond_field, FluxConditioningField) else cond_field
-
-        text_conditionings: list[FluxTextConditioning] = []
-        for cond_field in cond_list:
-            # Load the text embeddings.
-            cond_data = context.conditioning.load(cond_field.conditioning_name)
-            assert len(cond_data.conditionings) == 1
-            flux_conditioning = cond_data.conditionings[0]
-            assert isinstance(flux_conditioning, FLUXConditioningInfo)
-            flux_conditioning = flux_conditioning.to(dtype=dtype, device=device)
-            t5_embeddings = flux_conditioning.t5_embeds
-            clip_embeddings = flux_conditioning.clip_embeds
-
-            # Load the mask, if provided.
-            mask: Optional[torch.Tensor] = None
-            if cond_field.mask is not None:
-                mask = context.tensors.load(cond_field.mask.tensor_name)
-                mask = mask.to(device=device)
-                mask = RegionalPromptingExtension.preprocess_regional_prompt_mask(
-                    mask, packed_height, packed_width, dtype, device
-                )
-
-            text_conditionings.append(FluxTextConditioning(t5_embeddings, clip_embeddings, mask))
-
-        return text_conditionings
-
     @classmethod
     def prep_cfg_scale(
         cls, cfg_scale: float | list[float], timesteps: list[float], cfg_scale_start_step: int, cfg_scale_end_step: int
@@ -502,7 +468,9 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         # minimize peak memory.
 
         # First, load the ControlNet models so that we can determine the ControlNet types.
-        controlnet_models = [context.models.load(controlnet.control_model) for controlnet in controlnets]
+        controlnet_models = [
+            context.models.load(controlnet.control_model, context.util.get_queue_id()) for controlnet in controlnets
+        ]
 
         # Calculate the controlnet conditioning tensors.
         # We do this before loading the ControlNet models because it may require running the VAE, and we are trying to
@@ -513,7 +481,7 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
             if isinstance(controlnet_model.model, InstantXControlNetFlux):
                 if self.controlnet_vae is None:
                     raise ValueError("A ControlNet VAE is required when using an InstantX FLUX ControlNet.")
-                vae_info = context.models.load(self.controlnet_vae.vae)
+                vae_info = context.models.load(self.controlnet_vae.vae, context.util.get_queue_id())
                 controlnet_conds.append(
                     InstantXControlNetExtension.prepare_controlnet_cond(
                         controlnet_image=image,
@@ -624,7 +592,9 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
                 pos_images.append(pos_image)
                 neg_images.append(neg_image)
 
-            with context.models.load(ip_adapter_field.image_encoder_model) as image_encoder_model:
+            with context.models.load(
+                ip_adapter_field.image_encoder_model, context.util.get_queue_id()
+            ) as image_encoder_model:
                 assert isinstance(image_encoder_model, CLIPVisionModelWithProjection)
 
                 clip_image: torch.Tensor = clip_image_processor(images=pos_images, return_tensors="pt").pixel_values
@@ -654,7 +624,9 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         for ip_adapter_field, pos_image_prompt_clip_embed, neg_image_prompt_clip_embed in zip(
             ip_adapter_fields, pos_image_prompt_clip_embeds, neg_image_prompt_clip_embeds, strict=True
         ):
-            ip_adapter_model = exit_stack.enter_context(context.models.load(ip_adapter_field.ip_adapter_model))
+            ip_adapter_model = exit_stack.enter_context(
+                context.models.load(ip_adapter_field.ip_adapter_model, context.util.get_queue_id())
+            )
             assert isinstance(ip_adapter_model, XlabsIpAdapterFlux)
             ip_adapter_model = ip_adapter_model.to(dtype=dtype)
             if ip_adapter_field.mask is not None:
@@ -683,7 +655,7 @@ class FluxDenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
 
     def _lora_iterator(self, context: InvocationContext) -> Iterator[Tuple[LoRAModelRaw, float]]:
         for lora in self.transformer.loras:
-            lora_info = context.models.load(lora.lora)
+            lora_info = context.models.load(lora.lora, context.util.get_queue_id())
             assert isinstance(lora_info.model, LoRAModelRaw)
             yield (lora_info.model, lora.weight)
             del lora_info

invokeai/app/invocations/flux_text_encoder.py

@@ -1,18 +1,11 @@
 from contextlib import ExitStack
-from typing import Iterator, Literal, Optional, Tuple
+from typing import Iterator, Literal, Tuple
 
 import torch
 from transformers import CLIPTextModel, CLIPTokenizer, T5EncoderModel, T5Tokenizer
 
 from invokeai.app.invocations.baseinvocation import BaseInvocation, Classification, invocation
-from invokeai.app.invocations.fields import (
-    FieldDescriptions,
-    FluxConditioningField,
-    Input,
-    InputField,
-    TensorField,
-    UIComponent,
-)
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField
 from invokeai.app.invocations.model import CLIPField, T5EncoderField
 from invokeai.app.invocations.primitives import FluxConditioningOutput
 from invokeai.app.services.shared.invocation_context import InvocationContext
@@ -29,7 +22,7 @@ from invokeai.backend.stable_diffusion.diffusion.conditioning_data import Condit
     title="FLUX Text Encoding",
     tags=["prompt", "conditioning", "flux"],
     category="conditioning",
-    version="1.1.1",
+    version="1.1.0",
     classification=Classification.Prototype,
 )
 class FluxTextEncoderInvocation(BaseInvocation):
@@ -48,10 +41,7 @@ class FluxTextEncoderInvocation(BaseInvocation):
     t5_max_seq_len: Literal[256, 512] = InputField(
         description="Max sequence length for the T5 encoder. Expected to be 256 for FLUX schnell models and 512 for FLUX dev models."
     )
-    prompt: str = InputField(description="Text prompt to encode.", ui_component=UIComponent.Textarea)
-    mask: Optional[TensorField] = InputField(
-        default=None, description="A mask defining the region that this conditioning prompt applies to."
-    )
+    prompt: str = InputField(description="Text prompt to encode.")
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> FluxConditioningOutput:
@@ -64,13 +54,11 @@ class FluxTextEncoderInvocation(BaseInvocation):
         )
 
         conditioning_name = context.conditioning.save(conditioning_data)
-        return FluxConditioningOutput(
-            conditioning=FluxConditioningField(conditioning_name=conditioning_name, mask=self.mask)
-        )
+        return FluxConditioningOutput.build(conditioning_name)
 
     def _t5_encode(self, context: InvocationContext) -> torch.Tensor:
-        t5_tokenizer_info = context.models.load(self.t5_encoder.tokenizer)
-        t5_text_encoder_info = context.models.load(self.t5_encoder.text_encoder)
+        t5_tokenizer_info = context.models.load(self.t5_encoder.tokenizer, context.util.get_queue_id())
+        t5_text_encoder_info = context.models.load(self.t5_encoder.text_encoder, context.util.get_queue_id())
 
         prompt = [self.prompt]
 
@@ -83,15 +71,14 @@ 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)
         return prompt_embeds
 
     def _clip_encode(self, context: InvocationContext) -> torch.Tensor:
-        clip_tokenizer_info = context.models.load(self.clip.tokenizer)
-        clip_text_encoder_info = context.models.load(self.clip.text_encoder)
+        clip_tokenizer_info = context.models.load(self.clip.tokenizer, context.util.get_queue_id())
+        clip_text_encoder_info = context.models.load(self.clip.text_encoder, context.util.get_queue_id())
 
         prompt = [self.prompt]
 
@@ -124,7 +111,6 @@ class FluxTextEncoderInvocation(BaseInvocation):
 
             clip_encoder = HFEncoder(clip_text_encoder, clip_tokenizer, True, 77)
 
-            context.util.signal_progress("Running CLIP encoder")
             pooled_prompt_embeds = clip_encoder(prompt)
 
         assert isinstance(pooled_prompt_embeds, torch.Tensor)
@@ -132,7 +118,7 @@ class FluxTextEncoderInvocation(BaseInvocation):
 
     def _clip_lora_iterator(self, context: InvocationContext) -> Iterator[Tuple[LoRAModelRaw, float]]:
         for lora in self.clip.loras:
-            lora_info = context.models.load(lora.lora)
+            lora_info = context.models.load(lora.lora, context.util.get_queue_id())
             assert isinstance(lora_info.model, LoRAModelRaw)
             yield (lora_info.model, lora.weight)
             del lora_info

invokeai/app/invocations/flux_vae_decode.py

@@ -41,8 +41,7 @@ class FluxVaeDecodeInvocation(BaseInvocation, WithMetadata, WithBoard):
     def _vae_decode(self, vae_info: LoadedModel, latents: torch.Tensor) -> Image.Image:
         with vae_info as vae:
             assert isinstance(vae, AutoEncoder)
-            vae_dtype = next(iter(vae.parameters())).dtype
-            latents = latents.to(device=TorchDevice.choose_torch_device(), dtype=vae_dtype)
+            latents = latents.to(device=TorchDevice.choose_torch_device(), dtype=TorchDevice.choose_torch_dtype())
             img = vae.decode(latents)
 
         img = img.clamp(-1, 1)
@@ -53,8 +52,7 @@ class FluxVaeDecodeInvocation(BaseInvocation, WithMetadata, WithBoard):
     @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)
-        context.util.signal_progress("Running VAE")
+        vae_info = context.models.load(self.vae.vae, context.util.get_queue_id())
         image = self._vae_decode(vae_info=vae_info, latents=latents)
 
         TorchDevice.empty_cache()

invokeai/app/invocations/flux_vae_encode.py

@@ -44,8 +44,9 @@ class FluxVaeEncodeInvocation(BaseInvocation):
         generator = torch.Generator(device=TorchDevice.choose_torch_device()).manual_seed(0)
         with vae_info as vae:
             assert isinstance(vae, AutoEncoder)
-            vae_dtype = next(iter(vae.parameters())).dtype
-            image_tensor = image_tensor.to(device=TorchDevice.choose_torch_device(), dtype=vae_dtype)
+            image_tensor = image_tensor.to(
+                device=TorchDevice.choose_torch_device(), dtype=TorchDevice.choose_torch_dtype()
+            )
             latents = vae.encode(image_tensor, sample=True, generator=generator)
             return latents
 
@@ -53,13 +54,12 @@ class FluxVaeEncodeInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         image = context.images.get_pil(self.image.image_name)
 
-        vae_info = context.models.load(self.vae.vae)
+        vae_info = context.models.load(self.vae.vae, context.util.get_queue_id())
 
         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")
 
-        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/grounding_dino.py

@@ -94,7 +94,9 @@ class GroundingDinoInvocation(BaseInvocation):
         labels = [label if label.endswith(".") else label + "." for label in labels]
 
         with context.models.load_remote_model(
-            source=GROUNDING_DINO_MODEL_IDS[self.model], loader=GroundingDinoInvocation._load_grounding_dino
+            source=GROUNDING_DINO_MODEL_IDS[self.model],
+            queue_id=context.util.get_queue_id(),
+            loader=GroundingDinoInvocation._load_grounding_dino,
         ) as detector:
             assert isinstance(detector, GroundingDinoPipeline)
             return detector.detect(image=image, candidate_labels=labels, threshold=threshold)

invokeai/app/invocations/hed.py

@@ -22,7 +22,9 @@ class HEDEdgeDetectionInvocation(BaseInvocation, WithMetadata, WithBoard):
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.images.get_pil(self.image.image_name, "RGB")
-        loaded_model = context.models.load_remote_model(HEDEdgeDetector.get_model_url(), HEDEdgeDetector.load_model)
+        loaded_model = context.models.load_remote_model(
+            HEDEdgeDetector.get_model_url(), context.util.get_queue_id(), HEDEdgeDetector.load_model
+        )
 
         with loaded_model as model:
             assert isinstance(model, ControlNetHED_Apache2)

invokeai/app/invocations/image_panels.py

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

invokeai/app/invocations/image_to_latents.py

@@ -111,13 +111,12 @@ class ImageToLatentsInvocation(BaseInvocation):
     def invoke(self, context: InvocationContext) -> LatentsOutput:
         image = context.images.get_pil(self.image.image_name)
 
-        vae_info = context.models.load(self.vae.vae)
+        vae_info = context.models.load(self.vae.vae, context.util.get_queue_id())
 
         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")
 
-        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/infill.py

@@ -36,7 +36,7 @@ class InfillImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
     image: ImageField = InputField(description="The image to process")
 
     @abstractmethod
-    def infill(self, image: Image.Image) -> Image.Image:
+    def infill(self, image: Image.Image, queue_id: str) -> Image.Image:
         """Infill the image with the specified method"""
         pass
 
@@ -56,7 +56,7 @@ class InfillImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
             return ImageOutput.build(context.images.get_dto(self.image.image_name))
 
         # Perform Infill action
-        infilled_image = self.infill(input_image)
+        infilled_image = self.infill(input_image, context.util.get_queue_id())
 
         # Create ImageDTO for Infilled Image
         infilled_image_dto = context.images.save(image=infilled_image)
@@ -74,7 +74,7 @@ class InfillColorInvocation(InfillImageProcessorInvocation):
         description="The color to use to infill",
     )
 
-    def infill(self, image: Image.Image):
+    def infill(self, image: Image.Image, queue_id: str):
         solid_bg = Image.new("RGBA", image.size, self.color.tuple())
         infilled = Image.alpha_composite(solid_bg, image.convert("RGBA"))
         infilled.paste(image, (0, 0), image.split()[-1])
@@ -93,7 +93,7 @@ class InfillTileInvocation(InfillImageProcessorInvocation):
         description="The seed to use for tile generation (omit for random)",
     )
 
-    def infill(self, image: Image.Image):
+    def infill(self, image: Image.Image, queue_id: str):
         output = infill_tile(image, seed=self.seed, tile_size=self.tile_size)
         return output.infilled
 
@@ -107,7 +107,7 @@ class InfillPatchMatchInvocation(InfillImageProcessorInvocation):
     downscale: float = InputField(default=2.0, gt=0, description="Run patchmatch on downscaled image to speedup infill")
     resample_mode: PIL_RESAMPLING_MODES = InputField(default="bicubic", description="The resampling mode")
 
-    def infill(self, image: Image.Image):
+    def infill(self, image: Image.Image, queue_id: str):
         resample_mode = PIL_RESAMPLING_MAP[self.resample_mode]
 
         width = int(image.width / self.downscale)
@@ -131,9 +131,10 @@ class InfillPatchMatchInvocation(InfillImageProcessorInvocation):
 class LaMaInfillInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image using the LaMa model"""
 
-    def infill(self, image: Image.Image):
+    def infill(self, image: Image.Image, queue_id: str):
         with self._context.models.load_remote_model(
             source="https://github.com/Sanster/models/releases/download/add_big_lama/big-lama.pt",
+            queue_id=queue_id,
             loader=LaMA.load_jit_model,
         ) as model:
             lama = LaMA(model)
@@ -144,7 +145,7 @@ class LaMaInfillInvocation(InfillImageProcessorInvocation):
 class CV2InfillInvocation(InfillImageProcessorInvocation):
     """Infills transparent areas of an image using OpenCV Inpainting"""
 
-    def infill(self, image: Image.Image):
+    def infill(self, image: Image.Image, queue_id: str):
         return cv2_inpaint(image)
 
 
@@ -166,5 +167,5 @@ class MosaicInfillInvocation(InfillImageProcessorInvocation):
         description="The max threshold for color",
     )
 
-    def infill(self, image: Image.Image):
+    def infill(self, image: Image.Image, queue_id: str):
         return infill_mosaic(image, (self.tile_width, self.tile_height), self.min_color.tuple(), self.max_color.tuple())

invokeai/app/invocations/latents_to_image.py

@@ -57,10 +57,9 @@ class LatentsToImageInvocation(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)
+        vae_info = context.models.load(self.vae.vae, context.util.get_queue_id())
         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/lineart.py

@@ -23,7 +23,9 @@ class LineartEdgeDetectionInvocation(BaseInvocation, WithMetadata, WithBoard):
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.images.get_pil(self.image.image_name, "RGB")
         model_url = LineartEdgeDetector.get_model_url(self.coarse)
-        loaded_model = context.models.load_remote_model(model_url, LineartEdgeDetector.load_model)
+        loaded_model = context.models.load_remote_model(
+            model_url, context.util.get_queue_id(), LineartEdgeDetector.load_model
+        )
 
         with loaded_model as model:
             assert isinstance(model, Generator)

invokeai/app/invocations/lineart_anime.py

@@ -20,7 +20,9 @@ class LineartAnimeEdgeDetectionInvocation(BaseInvocation, WithMetadata, WithBoar
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.images.get_pil(self.image.image_name, "RGB")
         model_url = LineartAnimeEdgeDetector.get_model_url()
-        loaded_model = context.models.load_remote_model(model_url, LineartAnimeEdgeDetector.load_model)
+        loaded_model = context.models.load_remote_model(
+            model_url, context.util.get_queue_id(), LineartAnimeEdgeDetector.load_model
+        )
 
         with loaded_model as model:
             assert isinstance(model, UnetGenerator)

invokeai/app/invocations/metadata.py

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

invokeai/app/invocations/mlsd.py

@@ -28,7 +28,9 @@ class MLSDDetectionInvocation(BaseInvocation, WithMetadata, WithBoard):
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.images.get_pil(self.image.image_name, "RGB")
-        loaded_model = context.models.load_remote_model(MLSDDetector.get_model_url(), MLSDDetector.load_model)
+        loaded_model = context.models.load_remote_model(
+            MLSDDetector.get_model_url(), context.util.get_queue_id(), MLSDDetector.load_model
+        )
 
         with loaded_model as model:
             assert isinstance(model, MobileV2_MLSD_Large)

invokeai/app/invocations/normal_bae.py

@@ -20,7 +20,9 @@ class NormalMapInvocation(BaseInvocation, WithMetadata, WithBoard):
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.images.get_pil(self.image.image_name, "RGB")
-        loaded_model = context.models.load_remote_model(NormalMapDetector.get_model_url(), NormalMapDetector.load_model)
+        loaded_model = context.models.load_remote_model(
+            NormalMapDetector.get_model_url(), context.util.get_queue_id(), NormalMapDetector.load_model
+        )
 
         with loaded_model as model:
             assert isinstance(model, NNET)

invokeai/app/invocations/param_easing.py

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

invokeai/app/invocations/pidi.py

@@ -22,7 +22,9 @@ class PiDiNetEdgeDetectionInvocation(BaseInvocation, WithMetadata, WithBoard):
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
         image = context.images.get_pil(self.image.image_name, "RGB")
-        loaded_model = context.models.load_remote_model(PIDINetDetector.get_model_url(), PIDINetDetector.load_model)
+        loaded_model = context.models.load_remote_model(
+            PIDINetDetector.get_model_url(), context.util.get_queue_id(), PIDINetDetector.load_model
+        )
 
         with loaded_model as model:
             assert isinstance(model, PiDiNet)

invokeai/app/invocations/primitives.py

@@ -4,13 +4,7 @@ from typing import Optional
 
 import torch
 
-from invokeai.app.invocations.baseinvocation import (
-    BaseInvocation,
-    BaseInvocationOutput,
-    Classification,
-    invocation,
-    invocation_output,
-)
+from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
 from invokeai.app.invocations.constants import LATENT_SCALE_FACTOR
 from invokeai.app.invocations.fields import (
     BoundingBoxField,
@@ -539,23 +533,3 @@ class BoundingBoxInvocation(BaseInvocation):
 
 
 # endregion
-
-
-@invocation(
-    "image_batch",
-    title="Image Batch",
-    tags=["primitives", "image", "batch", "internal"],
-    category="primitives",
-    version="1.0.0",
-    classification=Classification.Special,
-)
-class ImageBatchInvocation(BaseInvocation):
-    """Create a batched generation, where the workflow is executed once for each image in the batch."""
-
-    images: list[ImageField] = InputField(min_length=1, description="The images to batch over", input=Input.Direct)
-
-    def __init__(self):
-        raise NotImplementedError("This class should never be executed or instantiated directly.")
-
-    def invoke(self, context: InvocationContext) -> ImageOutput:
-        raise NotImplementedError("This class should never be executed or instantiated directly.")

invokeai/app/invocations/sd3_denoise.py

@@ -1,19 +1,16 @@
-from typing import Callable, Optional, Tuple
+from typing import Callable, 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 diffusers.schedulers.scheduling_flow_match_euler_discrete import FlowMatchEulerDiscreteScheduler
 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,
@@ -22,9 +19,7 @@ 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
@@ -35,24 +30,16 @@ from invokeai.backend.util.devices import TorchDevice
     title="SD3 Denoise",
     tags=["image", "sd3"],
     category="image",
-    version="1.1.0",
+    version="1.0.0",
     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"
+        description=FieldDescriptions.sd3_model,
+        input=Input.Connection,
+        title="Transformer",
     )
     positive_conditioning: SD3ConditioningField = InputField(
         description=FieldDescriptions.positive_cond, input=Input.Connection
@@ -74,41 +61,6 @@ class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         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,
@@ -195,7 +147,7 @@ class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         inference_dtype = TorchDevice.choose_torch_dtype()
         device = TorchDevice.choose_torch_device()
 
-        transformer_info = context.models.load(self.transformer.transformer)
+        transformer_info = context.models.load(self.transformer.transformer, context.util.get_queue_id())
 
         # Load/process the conditioning data.
         # TODO(ryand): Make CFG optional.
@@ -218,20 +170,14 @@ class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
         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 scheduler.
+        scheduler = FlowMatchEulerDiscreteScheduler()
+        scheduler.set_timesteps(num_inference_steps=self.steps, device=device)
+        timesteps = scheduler.timesteps
+        assert isinstance(timesteps, torch.Tensor)
 
         # 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)
+        cfg_scale = self._prepare_cfg_scale(len(timesteps))
 
         # Generate initial latent noise.
         num_channels_latents = transformer_info.model.config.in_channels
@@ -245,34 +191,9 @@ class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
             device=device,
             seed=self.seed,
         )
+        latents: torch.Tensor = noise
 
-        # 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,
-            )
-
+        total_steps = len(timesteps)
         step_callback = self._build_step_callback(context)
 
         step_callback(
@@ -289,12 +210,11 @@ class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
             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)))):
+            for step_idx, t in tqdm(list(enumerate(timesteps))):
                 # 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])
+                timestep = t.expand(latent_model_input.shape[0])
 
                 noise_pred = transformer(
                     hidden_states=latent_model_input,
@@ -312,19 +232,21 @@ class SD3DenoiseInvocation(BaseInvocation, WithMetadata, WithBoard):
 
                 # 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)
+                latents = scheduler.step(model_output=noise_pred, timestep=t, sample=latents, return_dict=False)[0]
 
-                if inpaint_extension is not None:
-                    latents = inpaint_extension.merge_intermediate_latents_with_init_latents(latents, t_prev)
+                # TODO(ryand): This MPS dtype handling was copied from diffusers, I haven't tested to see if it's
+                # needed.
+                if latents.dtype != latents_dtype:
+                    if torch.backends.mps.is_available():
+                        # some platforms (eg. apple mps) misbehave due to a pytorch bug: https://github.com/pytorch/pytorch/pull/99272
+                        latents = latents.to(latents_dtype)
 
                 step_callback(
                     PipelineIntermediateState(
                         step=step_idx + 1,
                         order=1,
                         total_steps=total_steps,
-                        timestep=int(t_curr),
+                        timestep=int(t),
                         latents=latents,
                     ),
                 )

invokeai/app/invocations/sd3_image_to_latents.py

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

invokeai/app/invocations/sd3_latents_to_image.py

@@ -44,10 +44,9 @@ class SD3LatentsToImageInvocation(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)
+        vae_info = context.models.load(self.vae.vae, context.util.get_queue_id())
         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)
 

invokeai/app/invocations/sd3_text_encoder.py

@@ -86,8 +86,8 @@ class Sd3TextEncoderInvocation(BaseInvocation):
 
     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)
+        t5_tokenizer_info = context.models.load(self.t5_encoder.tokenizer, context.util.get_queue_id())
+        t5_text_encoder_info = context.models.load(self.t5_encoder.text_encoder, context.util.get_queue_id())
 
         prompt = [self.prompt]
 
@@ -95,7 +95,6 @@ class Sd3TextEncoderInvocation(BaseInvocation):
             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))
 
@@ -128,8 +127,8 @@ class Sd3TextEncoderInvocation(BaseInvocation):
     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)
+        clip_tokenizer_info = context.models.load(clip_model.tokenizer, context.util.get_queue_id())
+        clip_text_encoder_info = context.models.load(clip_model.text_encoder, context.util.get_queue_id())
 
         prompt = [self.prompt]
 
@@ -138,7 +137,6 @@ class Sd3TextEncoderInvocation(BaseInvocation):
             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)
 
@@ -195,7 +193,7 @@ class Sd3TextEncoderInvocation(BaseInvocation):
         self, context: InvocationContext, clip_model: CLIPField
     ) -> Iterator[Tuple[LoRAModelRaw, float]]:
         for lora in clip_model.loras:
-            lora_info = context.models.load(lora.lora)
+            lora_info = context.models.load(lora.lora, context.util.get_queue_id())
             assert isinstance(lora_info.model, LoRAModelRaw)
             yield (lora_info.model, lora.weight)
             del lora_info

invokeai/app/invocations/segment_anything.py

@@ -125,7 +125,9 @@ class SegmentAnythingInvocation(BaseInvocation):
 
         with (
             context.models.load_remote_model(
-                source=SEGMENT_ANYTHING_MODEL_IDS[self.model], loader=SegmentAnythingInvocation._load_sam_model
+                source=SEGMENT_ANYTHING_MODEL_IDS[self.model],
+                queue_id=context.util.get_queue_id(),
+                loader=SegmentAnythingInvocation._load_sam_model,
             ) as sam_pipeline,
         ):
             assert isinstance(sam_pipeline, SegmentAnythingPipeline)

invokeai/app/invocations/spandrel_image_to_image.py

@@ -158,7 +158,7 @@ class SpandrelImageToImageInvocation(BaseInvocation, WithMetadata, WithBoard):
         image = context.images.get_pil(self.image.image_name, mode="RGB")
 
         # Load the model.
-        spandrel_model_info = context.models.load(self.image_to_image_model)
+        spandrel_model_info = context.models.load(self.image_to_image_model, context.util.get_queue_id())
 
         def step_callback(step: int, total_steps: int) -> None:
             context.util.signal_progress(
@@ -207,7 +207,7 @@ class SpandrelImageToImageAutoscaleInvocation(SpandrelImageToImageInvocation):
         image = context.images.get_pil(self.image.image_name, mode="RGB")
 
         # Load the model.
-        spandrel_model_info = context.models.load(self.image_to_image_model)
+        spandrel_model_info = context.models.load(self.image_to_image_model, context.util.get_queue_id())
 
         # The target size of the image, determined by the provided scale. We'll run the upscaler until we hit this size.
         # Later, we may mutate this value if the model doesn't upscale the image or if the user requested a multiple of 8.

invokeai/app/invocations/tiled_multi_diffusion_denoise_latents.py

@@ -196,13 +196,13 @@ class TiledMultiDiffusionDenoiseLatents(BaseInvocation):
         # Prepare an iterator that yields the UNet's LoRA models and their weights.
         def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in self.unet.loras:
-                lora_info = context.models.load(lora.lora)
+                lora_info = context.models.load(lora.lora, context.util.get_queue_id())
                 assert isinstance(lora_info.model, LoRAModelRaw)
                 yield (lora_info.model, lora.weight)
                 del lora_info
 
         # Load the UNet model.
-        unet_info = context.models.load(self.unet.unet)
+        unet_info = context.models.load(self.unet.unet, context.util.get_queue_id())
 
         with (
             ExitStack() as exit_stack,

invokeai/app/invocations/upscale.py

@@ -90,7 +90,7 @@ class ESRGANInvocation(BaseInvocation, WithMetadata, WithBoard):
             raise ValueError(msg)
 
         loadnet = context.models.load_remote_model(
-            source=ESRGAN_MODEL_URLS[self.model_name],
+            source=ESRGAN_MODEL_URLS[self.model_name], queue_id=context.util.get_queue_id()
         )
 
         with loadnet as loadnet_model:

invokeai/app/services/events/events_base.py

@@ -131,15 +131,17 @@ class EventServiceBase:
 
     # region Model loading
 
-    def emit_model_load_started(self, config: "AnyModelConfig", submodel_type: Optional["SubModelType"] = None) -> None:
+    def emit_model_load_started(
+        self, config: "AnyModelConfig", queue_id: str, submodel_type: Optional["SubModelType"] = None
+    ) -> None:
         """Emitted when a model load is started."""
-        self.dispatch(ModelLoadStartedEvent.build(config, submodel_type))
+        self.dispatch(ModelLoadStartedEvent.build(config, queue_id, submodel_type))
 
     def emit_model_load_complete(
-        self, config: "AnyModelConfig", submodel_type: Optional["SubModelType"] = None
+        self, config: "AnyModelConfig", queue_id: str, submodel_type: Optional["SubModelType"] = None
     ) -> None:
         """Emitted when a model load is complete."""
-        self.dispatch(ModelLoadCompleteEvent.build(config, submodel_type))
+        self.dispatch(ModelLoadCompleteEvent.build(config, queue_id, submodel_type))
 
     # endregion
 

invokeai/app/services/events/events_common.py

@@ -383,12 +383,14 @@ class DownloadErrorEvent(DownloadEventBase):
         return cls(source=str(job.source), error_type=job.error_type, error=job.error)
 
 
-class ModelEventBase(EventBase):
-    """Base class for events associated with a model"""
+class ModelLoadEventBase(EventBase):
+    """Base class for queue events"""
+
+    queue_id: str = Field(description="The ID of the queue")
 
 
 @payload_schema.register
-class ModelLoadStartedEvent(ModelEventBase):
+class ModelLoadStartedEvent(ModelLoadEventBase):
     """Event model for model_load_started"""
 
     __event_name__ = "model_load_started"
@@ -397,12 +399,14 @@ class ModelLoadStartedEvent(ModelEventBase):
     submodel_type: Optional[SubModelType] = Field(default=None, description="The submodel type, if any")
 
     @classmethod
-    def build(cls, config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> "ModelLoadStartedEvent":
-        return cls(config=config, submodel_type=submodel_type)
+    def build(
+        cls, config: AnyModelConfig, queue_id: str, submodel_type: Optional[SubModelType] = None
+    ) -> "ModelLoadStartedEvent":
+        return cls(config=config, queue_id=queue_id, submodel_type=submodel_type)
 
 
 @payload_schema.register
-class ModelLoadCompleteEvent(ModelEventBase):
+class ModelLoadCompleteEvent(ModelLoadEventBase):
     """Event model for model_load_complete"""
 
     __event_name__ = "model_load_complete"
@@ -411,8 +415,14 @@ class ModelLoadCompleteEvent(ModelEventBase):
     submodel_type: Optional[SubModelType] = Field(default=None, description="The submodel type, if any")
 
     @classmethod
-    def build(cls, config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> "ModelLoadCompleteEvent":
-        return cls(config=config, submodel_type=submodel_type)
+    def build(
+        cls, config: AnyModelConfig, queue_id: str, submodel_type: Optional[SubModelType] = None
+    ) -> "ModelLoadCompleteEvent":
+        return cls(config=config, queue_id=queue_id, submodel_type=submodel_type)
+
+
+class ModelEventBase(EventBase):
+    """Base class for model events"""
 
 
 @payload_schema.register

invokeai/app/services/invocation_stats/invocation_stats_default.py

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

invokeai/app/services/model_load/model_load_base.py

@@ -7,14 +7,16 @@ from typing import Callable, Optional
 
 from invokeai.backend.model_manager import AnyModel, AnyModelConfig, SubModelType
 from invokeai.backend.model_manager.load import LoadedModel, LoadedModelWithoutConfig
-from invokeai.backend.model_manager.load.model_cache.model_cache import ModelCache
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
 
 
 class ModelLoadServiceBase(ABC):
     """Wrapper around AnyModelLoader."""
 
     @abstractmethod
-    def load_model(self, model_config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> LoadedModel:
+    def load_model(
+        self, model_config: AnyModelConfig, queue_id: str, submodel_type: Optional[SubModelType] = None
+    ) -> LoadedModel:
         """
         Given a model's configuration, load it and return the LoadedModel object.
 
@@ -24,12 +26,12 @@ class ModelLoadServiceBase(ABC):
 
     @property
     @abstractmethod
-    def ram_cache(self) -> ModelCache:
+    def ram_cache(self) -> ModelCacheBase[AnyModel]:
         """Return the RAM cache used by this loader."""
 
     @abstractmethod
     def load_model_from_path(
-        self, model_path: Path, loader: Optional[Callable[[Path], AnyModel]] = None
+        self, model_path: Path, queue_id: str, loader: Optional[Callable[[Path], AnyModel]] = None
     ) -> LoadedModelWithoutConfig:
         """
         Load the model file or directory located at the indicated Path.

invokeai/app/services/model_load/model_load_default.py

@@ -18,7 +18,7 @@ from invokeai.backend.model_manager.load import (
     ModelLoaderRegistry,
     ModelLoaderRegistryBase,
 )
-from invokeai.backend.model_manager.load.model_cache.model_cache import ModelCache
+from invokeai.backend.model_manager.load.model_cache.model_cache_base import ModelCacheBase
 from invokeai.backend.model_manager.load.model_loaders.generic_diffusers import GenericDiffusersLoader
 from invokeai.backend.util.devices import TorchDevice
 from invokeai.backend.util.logging import InvokeAILogger
@@ -30,7 +30,7 @@ class ModelLoadService(ModelLoadServiceBase):
     def __init__(
         self,
         app_config: InvokeAIAppConfig,
-        ram_cache: ModelCache,
+        ram_cache: ModelCacheBase[AnyModel],
         registry: Optional[Type[ModelLoaderRegistryBase]] = ModelLoaderRegistry,
     ):
         """Initialize the model load service."""
@@ -45,11 +45,13 @@ class ModelLoadService(ModelLoadServiceBase):
         self._invoker = invoker
 
     @property
-    def ram_cache(self) -> ModelCache:
+    def ram_cache(self) -> ModelCacheBase[AnyModel]:
         """Return the RAM cache used by this loader."""
         return self._ram_cache
 
-    def load_model(self, model_config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> LoadedModel:
+    def load_model(
+        self, model_config: AnyModelConfig, queue_id: str, submodel_type: Optional[SubModelType] = None
+    ) -> LoadedModel:
         """
         Given a model's configuration, load it and return the LoadedModel object.
 
@@ -60,7 +62,7 @@ class ModelLoadService(ModelLoadServiceBase):
         # We don't have an invoker during testing
         # TODO(psyche): Mock this method on the invoker in the tests
         if hasattr(self, "_invoker"):
-            self._invoker.services.events.emit_model_load_started(model_config, submodel_type)
+            self._invoker.services.events.emit_model_load_started(model_config, queue_id, submodel_type)
 
         implementation, model_config, submodel_type = self._registry.get_implementation(model_config, submodel_type)  # type: ignore
         loaded_model: LoadedModel = implementation(
@@ -70,22 +72,23 @@ class ModelLoadService(ModelLoadServiceBase):
         ).load_model(model_config, submodel_type)
 
         if hasattr(self, "_invoker"):
-            self._invoker.services.events.emit_model_load_complete(model_config, submodel_type)
+            self._invoker.services.events.emit_model_load_complete(model_config, queue_id, submodel_type)
 
         return loaded_model
 
     def load_model_from_path(
-        self, model_path: Path, loader: Optional[Callable[[Path], AnyModel]] = None
+        self, model_path: Path, queue_id: str, loader: Optional[Callable[[Path], AnyModel]] = None
     ) -> LoadedModelWithoutConfig:
         cache_key = str(model_path)
+        ram_cache = self.ram_cache
         try:
-            return LoadedModelWithoutConfig(cache_record=self._ram_cache.get(key=cache_key), cache=self._ram_cache)
+            return LoadedModelWithoutConfig(_locker=ram_cache.get(key=cache_key))
         except IndexError:
             pass
 
         def torch_load_file(checkpoint: Path) -> AnyModel:
             scan_result = scan_file_path(checkpoint)
-            if scan_result.infected_files != 0 or scan_result.scan_err:
+            if scan_result.infected_files != 0:
                 raise Exception("The model at {checkpoint} is potentially infected by malware. Aborting load.")
             result = torch_load(checkpoint, map_location="cpu")
             return result
@@ -108,5 +111,5 @@ class ModelLoadService(ModelLoadServiceBase):
         )
         assert loader is not None
         raw_model = loader(model_path)
-        self._ram_cache.put(key=cache_key, model=raw_model)
-        return LoadedModelWithoutConfig(cache_record=self._ram_cache.get(key=cache_key), cache=self._ram_cache)
+        ram_cache.put(key=cache_key, model=raw_model)
+        return LoadedModelWithoutConfig(_locker=ram_cache.get(key=cache_key))

invokeai/app/services/model_manager/model_manager_default.py

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

invokeai/app/services/session_queue/session_queue_common.py

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

invokeai/app/services/shared/invocation_context.py

@@ -160,10 +160,6 @@ class LoggerInterface(InvocationContextInterface):
 
 
 class ImagesInterface(InvocationContextInterface):
-    def __init__(self, services: InvocationServices, data: InvocationContextData, util: "UtilInterface") -> None:
-        super().__init__(services, data)
-        self._util = util
-
     def save(
         self,
         image: Image,
@@ -190,8 +186,6 @@ class ImagesInterface(InvocationContextInterface):
             The saved image DTO.
         """
 
-        self._util.signal_progress("Saving image")
-
         # If `metadata` is provided directly, use that. Else, use the metadata provided by `WithMetadata`, falling back to None.
         metadata_ = None
         if metadata:
@@ -342,10 +336,6 @@ class ConditioningInterface(InvocationContextInterface):
 class ModelsInterface(InvocationContextInterface):
     """Common API for loading, downloading and managing models."""
 
-    def __init__(self, services: InvocationServices, data: InvocationContextData, util: "UtilInterface") -> None:
-        super().__init__(services, data)
-        self._util = util
-
     def exists(self, identifier: Union[str, "ModelIdentifierField"]) -> bool:
         """Check if a model exists.
 
@@ -361,7 +351,10 @@ class ModelsInterface(InvocationContextInterface):
             return self._services.model_manager.store.exists(identifier.key)
 
     def load(
-        self, identifier: Union[str, "ModelIdentifierField"], submodel_type: Optional[SubModelType] = None
+        self,
+        identifier: Union[str, "ModelIdentifierField"],
+        queue_id: str,
+        submodel_type: Optional[SubModelType] = None,
     ) -> LoadedModel:
         """Load a model.
 
@@ -378,18 +371,19 @@ 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, queue_id, submodel_type)
         else:
-            submodel_type = submodel_type or identifier.submodel_type
+            _submodel_type = submodel_type or identifier.submodel_type
             model = self._services.model_manager.store.get_model(identifier.key)
-
-        message = f"Loading model {model.name}"
-        if submodel_type:
-            message += f" ({submodel_type.value})"
-        self._util.signal_progress(message)
-        return self._services.model_manager.load.load_model(model, submodel_type)
+            return self._services.model_manager.load.load_model(model, queue_id, _submodel_type)
 
     def load_by_attrs(
-        self, name: str, base: BaseModelType, type: ModelType, submodel_type: Optional[SubModelType] = None
+        self,
+        name: str,
+        base: BaseModelType,
+        type: ModelType,
+        queue_id: str,
+        submodel_type: Optional[SubModelType] = None,
     ) -> LoadedModel:
         """Load a model by its attributes.
 
@@ -411,11 +405,7 @@ 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)
+        return self._services.model_manager.load.load_model(configs[0], queue_id, submodel_type)
 
     def get_config(self, identifier: Union[str, "ModelIdentifierField"]) -> AnyModelConfig:
         """Get a model's config.
@@ -485,12 +475,12 @@ 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(
         self,
         model_path: Path,
+        queue_id: str,
         loader: Optional[Callable[[Path], AnyModel]] = None,
     ) -> LoadedModelWithoutConfig:
         """
@@ -508,13 +498,14 @@ 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)
+        return self._services.model_manager.load.load_model_from_path(
+            model_path=model_path, queue_id=queue_id, loader=loader
+        )
 
     def load_remote_model(
         self,
         source: str | AnyHttpUrl,
+        queue_id: str,
         loader: Optional[Callable[[Path], AnyModel]] = None,
     ) -> LoadedModelWithoutConfig:
         """
@@ -535,9 +526,9 @@ 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)
+        return self._services.model_manager.load.load_model_from_path(
+            model_path=model_path, queue_id=queue_id, loader=loader
+        )
 
 
 class ConfigInterface(InvocationContextInterface):
@@ -558,6 +549,14 @@ class UtilInterface(InvocationContextInterface):
         super().__init__(services, data)
         self._is_canceled = is_canceled
 
+    def get_queue_id(self) -> str:
+        """Checks if the current session has been canceled.
+
+        Returns:
+            True if the current session has been canceled, False if not.
+        """
+        return self._data.queue_item.queue_id
+
     def is_canceled(self) -> bool:
         """Checks if the current session has been canceled.
 
@@ -730,12 +729,12 @@ 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/util/ti_utils.py

@@ -22,7 +22,7 @@ def generate_ti_list(
     for trigger in extract_ti_triggers_from_prompt(prompt):
         name_or_key = trigger[1:-1]
         try:
-            loaded_model = context.models.load(name_or_key)
+            loaded_model = context.models.load(name_or_key, queue_id=context.util.get_queue_id())
             model = loaded_model.model
             assert isinstance(model, TextualInversionModelRaw)
             assert loaded_model.config.base == base
@@ -30,7 +30,7 @@ def generate_ti_list(
         except UnknownModelException:
             try:
                 loaded_model = context.models.load_by_attrs(
-                    name=name_or_key, base=base, type=ModelType.TextualInversion
+                    name=name_or_key, base=base, type=ModelType.TextualInversion, queue_id=context.util.get_queue_id()
                 )
                 model = loaded_model.model
                 assert isinstance(model, TextualInversionModelRaw)

invokeai/backend/flux/custom_block_processor.py

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

invokeai/backend/flux/denoise.py

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

invokeai/backend/flux/extensions/regional_prompting_extension.py

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

invokeai/backend/flux/ip_adapter/state_dict_utils.py

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

invokeai/backend/flux/ip_adapter/xlabs_ip_adapter_flux.py

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

invokeai/backend/flux/math.py

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

invokeai/backend/flux/model.py

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

invokeai/backend/flux/modules/layers.py

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

invokeai/backend/flux/text_conditioning.py

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

invokeai/backend/lora/conversions/flux_diffusers_lora_conversion_utils.py

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

invokeai/backend/model_manager/config.py

@@ -165,8 +165,6 @@ class SubmodelDefinition(BaseModel):
     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)")

invokeai/backend/model_manager/load/__init__.py

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

invokeai/backend/model_manager/load/load_base.py

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

invokeai/backend/model_manager/load/load_default.py

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

@@ -84,15 +84,7 @@ class FluxVAELoader(ModelLoader):
             model = AutoEncoder(ae_params[config.config_path])
             sd = load_file(model_path)
             model.load_state_dict(sd, assign=True)
-            # VAE is broken in float16, which mps defaults to
-            if self._torch_dtype == torch.float16:
-                try:
-                    vae_dtype = torch.tensor([1.0], dtype=torch.bfloat16, device=self._torch_device).dtype
-                except TypeError:
-                    vae_dtype = torch.float32
-            else:
-                vae_dtype = self._torch_dtype
-            model.to(vae_dtype)
+            model.to(dtype=self._torch_dtype)
 
         return model
 

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

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

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

@@ -25,7 +25,6 @@ from invokeai.backend.model_manager.config import (
     DiffusersConfigBase,
     MainCheckpointConfig,
 )
-from invokeai.backend.model_manager.load.model_cache.model_cache import get_model_cache_key
 from invokeai.backend.model_manager.load.model_loader_registry import ModelLoaderRegistry
 from invokeai.backend.model_manager.load.model_loaders.generic_diffusers import GenericDiffusersLoader
 from invokeai.backend.util.silence_warnings import SilenceWarnings
@@ -133,5 +132,5 @@ class StableDiffusionDiffusersModel(GenericDiffusersLoader):
             if subtype == submodel_type:
                 continue
             if submodel := getattr(pipeline, subtype.value, None):
-                self._ram_cache.put(get_model_cache_key(config.key, subtype), model=submodel)
+                self._ram_cache.put(config.key, submodel_type=subtype, model=submodel)
         return getattr(pipeline, submodel_type.value)

invokeai/backend/model_manager/probe.py

@@ -469,7 +469,7 @@ class ModelProbe(object):
         """
         # scan model
         scan_result = scan_file_path(checkpoint)
-        if scan_result.infected_files != 0 or scan_result.scan_err:
+        if scan_result.infected_files != 0:
             raise Exception("The model {model_name} is potentially infected by malware. Aborting import.")
 
 
@@ -485,7 +485,6 @@ MODEL_NAME_TO_PREPROCESSOR = {
     "lineart anime": "lineart_anime_image_processor",
     "lineart_anime": "lineart_anime_image_processor",
     "lineart": "lineart_image_processor",
-    "soft": "hed_image_processor",
     "softedge": "hed_image_processor",
     "hed": "hed_image_processor",
     "shuffle": "content_shuffle_image_processor",

invokeai/backend/model_manager/starter_models.py

@@ -298,12 +298,13 @@ ip_adapter_sdxl = StarterModel(
     previous_names=["IP Adapter SDXL"],
 )
 ip_adapter_flux = StarterModel(
-    name="Standard Reference (XLabs FLUX IP-Adapter v2)",
+    name="Standard Reference (XLabs FLUX IP-Adapter)",
     base=BaseModelType.Flux,
-    source="https://huggingface.co/XLabs-AI/flux-ip-adapter-v2/resolve/main/ip_adapter.safetensors",
+    source="https://huggingface.co/XLabs-AI/flux-ip-adapter/resolve/main/flux-ip-adapter.safetensors",
     description="References images with a more generalized/looser degree of precision.",
     type=ModelType.IPAdapter,
     dependencies=[clip_vit_l_image_encoder],
+    previous_names=["XLabs FLUX IP-Adapter"],
 )
 # endregion
 # region ControlNet

invokeai/backend/model_manager/util/model_util.py

@@ -44,7 +44,7 @@ def _fast_safetensors_reader(path: str) -> Dict[str, torch.Tensor]:
     return checkpoint
 
 
-def read_checkpoint_meta(path: Union[str, Path], scan: bool = True) -> Dict[str, torch.Tensor]:
+def read_checkpoint_meta(path: Union[str, Path], scan: bool = False) -> Dict[str, torch.Tensor]:
     if str(path).endswith(".safetensors"):
         try:
             path_str = path.as_posix() if isinstance(path, Path) else path
@@ -55,7 +55,7 @@ def read_checkpoint_meta(path: Union[str, Path], scan: bool = True) -> Dict[str,
     else:
         if scan:
             scan_result = scan_file_path(path)
-            if scan_result.infected_files != 0 or scan_result.scan_err:
+            if scan_result.infected_files != 0:
                 raise Exception(f'The model file "{path}" is potentially infected by malware. Aborting import.')
         if str(path).endswith(".gguf"):
             # The GGUF reader used here uses numpy memmap, so these tensors are not loaded into memory during this function
@@ -172,8 +172,6 @@ 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:

invokeai/backend/model_manager/util/select_hf_files.py

@@ -85,7 +85,6 @@ def _filter_by_variant(files: List[Path], variant: ModelRepoVariant) -> Set[Path
     """Select the proper variant files from a list of HuggingFace repo_id paths."""
     result: set[Path] = set()
     subfolder_weights: dict[Path, list[SubfolderCandidate]] = {}
-    safetensors_detected = False
     for path in files:
         if path.suffix in [".onnx", ".pb", ".onnx_data"]:
             if variant == ModelRepoVariant.ONNX:
@@ -120,16 +119,10 @@ 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

invokeai/backend/sd3/extensions/inpaint_extension.py

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

invokeai/backend/stable_diffusion/extensions/lora.py

@@ -29,7 +29,7 @@ class LoRAExt(ExtensionBase):
 
     @contextmanager
     def patch_unet(self, unet: UNet2DConditionModel, original_weights: OriginalWeightsStorage):
-        lora_model = self._node_context.models.load(self._model_id).model
+        lora_model = self._node_context.models.load(self._model_id, self._node_context.util.get_queue_id()).model
         assert isinstance(lora_model, LoRAModelRaw)
         LoRAPatcher.apply_lora_patch(
             model=unet,

invokeai/backend/stable_diffusion/extensions/t2i_adapter.py

@@ -54,7 +54,7 @@ class T2IAdapterExt(ExtensionBase):
     @callback(ExtensionCallbackType.SETUP)
     def setup(self, ctx: DenoiseContext):
         t2i_model: T2IAdapter
-        with self._node_context.models.load(self._model_id) as t2i_model:
+        with self._node_context.models.load(self._model_id, self._node_context.util.get_queue_id()) as t2i_model:
             _, _, latents_height, latents_width = ctx.inputs.orig_latents.shape
 
             self._adapter_state = self._run_model(

invokeai/backend/util/prefix_logger_adapter.py

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

invokeai/frontend/web/package.json

@@ -52,13 +52,13 @@
     }
   },
   "dependencies": {
-    "@atlaskit/pragmatic-drag-and-drop": "^1.4.0",
-    "@atlaskit/pragmatic-drag-and-drop-auto-scroll": "^1.4.0",
-    "@atlaskit/pragmatic-drag-and-drop-hitbox": "^1.0.3",
     "@dagrejs/dagre": "^1.1.4",
     "@dagrejs/graphlib": "^2.2.4",
+    "@dnd-kit/core": "^6.1.0",
+    "@dnd-kit/sortable": "^8.0.0",
+    "@dnd-kit/utilities": "^3.2.2",
     "@fontsource-variable/inter": "^5.1.0",
-    "@invoke-ai/ui-library": "^0.0.44",
+    "@invoke-ai/ui-library": "^0.0.43",
     "@nanostores/react": "^0.7.3",
     "@reduxjs/toolkit": "2.2.3",
     "@roarr/browser-log-writer": "^1.3.0",

invokeai/frontend/web/pnpm-lock.yaml

@@ -5,27 +5,27 @@ settings:
   excludeLinksFromLockfile: false
 
 dependencies:
-  '@atlaskit/pragmatic-drag-and-drop':
-    specifier: ^1.4.0
-    version: 1.4.0
-  '@atlaskit/pragmatic-drag-and-drop-auto-scroll':
-    specifier: ^1.4.0
-    version: 1.4.0
-  '@atlaskit/pragmatic-drag-and-drop-hitbox':
-    specifier: ^1.0.3
-    version: 1.0.3
   '@dagrejs/dagre':
     specifier: ^1.1.4
     version: 1.1.4
   '@dagrejs/graphlib':
     specifier: ^2.2.4
     version: 2.2.4
+  '@dnd-kit/core':
+    specifier: ^6.1.0
+    version: 6.1.0(react-dom@18.3.1)(react@18.3.1)
+  '@dnd-kit/sortable':
+    specifier: ^8.0.0
+    version: 8.0.0(@dnd-kit/core@6.1.0)(react@18.3.1)
+  '@dnd-kit/utilities':
+    specifier: ^3.2.2
+    version: 3.2.2(react@18.3.1)
   '@fontsource-variable/inter':
     specifier: ^5.1.0
     version: 5.1.0
   '@invoke-ai/ui-library':
-    specifier: ^0.0.44
-    version: 0.0.44(@chakra-ui/form-control@2.2.0)(@chakra-ui/icon@3.2.0)(@chakra-ui/media-query@3.3.0)(@chakra-ui/menu@2.2.1)(@chakra-ui/spinner@2.1.0)(@chakra-ui/system@2.6.2)(@fontsource-variable/inter@5.1.0)(@types/react@18.3.11)(i18next@23.15.1)(react-dom@18.3.1)(react@18.3.1)
+    specifier: ^0.0.43
+    version: 0.0.43(@chakra-ui/form-control@2.2.0)(@chakra-ui/icon@3.2.0)(@chakra-ui/media-query@3.3.0)(@chakra-ui/menu@2.2.1)(@chakra-ui/spinner@2.1.0)(@chakra-ui/system@2.6.2)(@fontsource-variable/inter@5.1.0)(@types/react@18.3.11)(i18next@23.15.1)(react-dom@18.3.1)(react@18.3.1)
   '@nanostores/react':
     specifier: ^0.7.3
     version: 0.7.3(nanostores@0.11.3)(react@18.3.1)
@@ -319,28 +319,6 @@ packages:
       '@jridgewell/trace-mapping': 0.3.25
     dev: true
 
-  /@atlaskit/pragmatic-drag-and-drop-auto-scroll@1.4.0:
-    resolution: {integrity: sha512-5GoikoTSW13UX76F9TDeWB8x3jbbGlp/Y+3aRkHe1MOBMkrWkwNpJ42MIVhhX/6NSeaZiPumP0KbGJVs2tOWSQ==}
-    dependencies:
-      '@atlaskit/pragmatic-drag-and-drop': 1.4.0
-      '@babel/runtime': 7.25.7
-    dev: false
-
-  /@atlaskit/pragmatic-drag-and-drop-hitbox@1.0.3:
-    resolution: {integrity: sha512-/Sbu/HqN2VGLYBhnsG7SbRNg98XKkbF6L7XDdBi+izRybfaK1FeMfodPpm/xnBHPJzwYMdkE0qtLyv6afhgMUA==}
-    dependencies:
-      '@atlaskit/pragmatic-drag-and-drop': 1.4.0
-      '@babel/runtime': 7.25.7
-    dev: false
-
-  /@atlaskit/pragmatic-drag-and-drop@1.4.0:
-    resolution: {integrity: sha512-qRY3PTJIcxfl/QB8Gwswz+BRvlmgAC5pB+J2hL6dkIxgqAgVwOhAamMUKsrOcFU/axG2Q7RbNs1xfoLKDuhoPg==}
-    dependencies:
-      '@babel/runtime': 7.25.7
-      bind-event-listener: 3.0.0
-      raf-schd: 4.0.3
-    dev: false
-
   /@babel/code-frame@7.25.7:
     resolution: {integrity: sha512-0xZJFNE5XMpENsgfHYTw8FbX4kv53mFLn2i3XPoq69LyhYSCBJtitaHx9QnsVTrsogI4Z3+HtEfZ2/GFPOtf5g==}
     engines: {node: '>=6.9.0'}
@@ -515,8 +493,8 @@ packages:
     resolution: {integrity: sha512-MV6D4VLRIHr4PkW4zMyqfrNS1mPlCTiCXwvYGtDFQYr+xHFfonhAuf9WjsSc0nyp2m0OdkSLnzmVKkZFLo25Tg==}
     dev: false
 
-  /@chakra-ui/anatomy@2.3.5:
-    resolution: {integrity: sha512-3im33cUOxCbISjaBlINE2u8BOwJSCdzpjCX0H+0JxK2xz26UaVA5xeI3NYHUoxDnr/QIrgfrllGxS0szYwOcyg==}
+  /@chakra-ui/anatomy@2.3.4:
+    resolution: {integrity: sha512-fFIYN7L276gw0Q7/ikMMlZxP7mvnjRaWJ7f3Jsf9VtDOi6eAYIBRrhQe6+SZ0PGmoOkRaBc7gSE5oeIbgFFyrw==}
     dev: false
 
   /@chakra-ui/breakpoint-utils@2.0.8:
@@ -573,12 +551,12 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/hooks@2.4.3(react@18.3.1):
-    resolution: {integrity: sha512-Sr2zsoTZw3p7HbrUy4aLpTIkE2XXUelAUgg3NGwMzrmx75bE0qVyiuuTFOuyEzGxYVV2Fe8QtcKKilm6RwzTGg==}
+  /@chakra-ui/hooks@2.4.2(react@18.3.1):
+    resolution: {integrity: sha512-LRKiVE1oA7afT5tbbSKAy7Uas2xFHE6IkrQdbhWCHmkHBUtPvjQQDgwtnd4IRZPmoEfNGwoJ/MQpwOM/NRTTwA==}
     peerDependencies:
       react: '>=18'
     dependencies:
-      '@chakra-ui/utils': 2.2.3(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
       '@zag-js/element-size': 0.31.1
       copy-to-clipboard: 3.3.3
       framesync: 6.1.2
@@ -596,13 +574,13 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/icons@2.2.4(@chakra-ui/react@2.10.4)(react@18.3.1):
+  /@chakra-ui/icons@2.2.4(@chakra-ui/react@2.10.2)(react@18.3.1):
     resolution: {integrity: sha512-l5QdBgwrAg3Sc2BRqtNkJpfuLw/pWRDwwT58J6c4PqQT6wzXxyNa8Q0PForu1ltB5qEiFb1kxr/F/HO1EwNa6g==}
     peerDependencies:
       '@chakra-ui/react': '>=2.0.0'
       react: '>=18'
     dependencies:
-      '@chakra-ui/react': 2.10.4(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1)
+      '@chakra-ui/react': 2.10.2(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1)
       react: 18.3.1
     dev: false
 
@@ -825,8 +803,8 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/react@2.10.4(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1):
-    resolution: {integrity: sha512-XyRWnuZ1Uw7Mlj5pKUGO5/WhnIHP/EOrpy6lGZC1yWlkd0eIfIpYMZ1ALTZx4KPEdbBaes48dgiMT2ROCqLhkA==}
+  /@chakra-ui/react@2.10.2(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1):
+    resolution: {integrity: sha512-TfIHTqTlxTHYJZBtpiR5EZasPUrLYKJxdbHkdOJb5G1OQ+2c5kKl5XA7c2pMtsEptzb7KxAAIB62t3hxdfWp1w==}
     peerDependencies:
       '@emotion/react': '>=11'
       '@emotion/styled': '>=11'
@@ -834,10 +812,10 @@ packages:
       react: '>=18'
       react-dom: '>=18'
     dependencies:
-      '@chakra-ui/hooks': 2.4.3(react@18.3.1)
-      '@chakra-ui/styled-system': 2.12.1(react@18.3.1)
-      '@chakra-ui/theme': 3.4.7(@chakra-ui/styled-system@2.12.1)(react@18.3.1)
-      '@chakra-ui/utils': 2.2.3(react@18.3.1)
+      '@chakra-ui/hooks': 2.4.2(react@18.3.1)
+      '@chakra-ui/styled-system': 2.11.2(react@18.3.1)
+      '@chakra-ui/theme': 3.4.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
       '@emotion/react': 11.13.3(@types/react@18.3.11)(react@18.3.1)
       '@emotion/styled': 11.13.0(@emotion/react@11.13.3)(@types/react@18.3.11)(react@18.3.1)
       '@popperjs/core': 2.11.8
@@ -868,10 +846,10 @@ packages:
       react: 18.3.1
     dev: false
 
-  /@chakra-ui/styled-system@2.12.1(react@18.3.1):
-    resolution: {integrity: sha512-DQph1nDiCPtgze7nDe0a36530ByXb5VpPosKGyWMvKocVeZJcDtYG6XM0+V5a0wKuFBXsViBBRIFUTiUesJAcg==}
+  /@chakra-ui/styled-system@2.11.2(react@18.3.1):
+    resolution: {integrity: sha512-y++z2Uop+hjfZX9mbH88F1ikazPv32asD2er56zMJBemUAzweXnHTpiCQbluEDSUDhqmghVZAdb+5L4XLbsRxA==}
     dependencies:
-      '@chakra-ui/utils': 2.2.3(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
       csstype: 3.1.3
     transitivePeerDependencies:
       - react
@@ -915,14 +893,14 @@ packages:
       color2k: 2.0.3
     dev: false
 
-  /@chakra-ui/theme-tools@2.2.7(@chakra-ui/styled-system@2.12.1)(react@18.3.1):
-    resolution: {integrity: sha512-K/VJd0QcnKik7m+qZTkggqNLep6+MPUu8IP5TUpHsnSM5R/RVjsJIR7gO8IZVAIMIGLLTIhGshHxeMekqv6LcQ==}
+  /@chakra-ui/theme-tools@2.2.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1):
+    resolution: {integrity: sha512-3UhKPyzKbV3l/bg1iQN9PBvffYp+EBOoYMUaeTUdieQRPFzo2jbYR0lNCxqv8h5aGM/k54nCHU2M/GStyi9F2A==}
     peerDependencies:
       '@chakra-ui/styled-system': '>=2.0.0'
     dependencies:
-      '@chakra-ui/anatomy': 2.3.5
-      '@chakra-ui/styled-system': 2.12.1(react@18.3.1)
-      '@chakra-ui/utils': 2.2.3(react@18.3.1)
+      '@chakra-ui/anatomy': 2.3.4
+      '@chakra-ui/styled-system': 2.11.2(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
       color2k: 2.0.3
     transitivePeerDependencies:
       - react
@@ -948,15 +926,15 @@ packages:
       '@chakra-ui/theme-tools': 2.1.2(@chakra-ui/styled-system@2.9.2)
     dev: false
 
-  /@chakra-ui/theme@3.4.7(@chakra-ui/styled-system@2.12.1)(react@18.3.1):
-    resolution: {integrity: sha512-pfewthgZTFNUYeUwGvhPQO/FTIyf375cFV1AT8N1y0aJiw4KDe7YTGm7p0aFy4AwAjH2ydMgeEx/lua4tx8qyQ==}
+  /@chakra-ui/theme@3.4.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1):
+    resolution: {integrity: sha512-ZwFBLfiMC3URwaO31ONXoKH9k0TX0OW3UjdPF3EQkQpYyrk/fm36GkkzajjtdpWEd7rzDLRsQjPmvwNaSoNDtg==}
     peerDependencies:
       '@chakra-ui/styled-system': '>=2.8.0'
     dependencies:
-      '@chakra-ui/anatomy': 2.3.5
-      '@chakra-ui/styled-system': 2.12.1(react@18.3.1)
-      '@chakra-ui/theme-tools': 2.2.7(@chakra-ui/styled-system@2.12.1)(react@18.3.1)
-      '@chakra-ui/utils': 2.2.3(react@18.3.1)
+      '@chakra-ui/anatomy': 2.3.4
+      '@chakra-ui/styled-system': 2.11.2(react@18.3.1)
+      '@chakra-ui/theme-tools': 2.2.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1)
+      '@chakra-ui/utils': 2.2.2(react@18.3.1)
     transitivePeerDependencies:
       - react
     dev: false
@@ -981,8 +959,8 @@ packages:
       lodash.mergewith: 4.6.2
     dev: false
 
-  /@chakra-ui/utils@2.2.3(react@18.3.1):
-    resolution: {integrity: sha512-cldoCQuexZ6e07/9hWHKD4l1QXXlM1Nax9tuQOBvVf/EgwNZt3nZu8zZRDFlhAOKCTQDkmpLTTu+eXXjChNQOw==}
+  /@chakra-ui/utils@2.2.2(react@18.3.1):
+    resolution: {integrity: sha512-jUPLT0JzRMWxpdzH6c+t0YMJYrvc5CLericgITV3zDSXblkfx3DsYXqU11DJTSGZI9dUKzM1Wd0Wswn4eJwvFQ==}
     peerDependencies:
       react: '>=16.8.0'
     dependencies:
@@ -1002,6 +980,49 @@ packages:
     engines: {node: '>17.0.0'}
     dev: false
 
+  /@dnd-kit/accessibility@3.1.0(react@18.3.1):
+    resolution: {integrity: sha512-ea7IkhKvlJUv9iSHJOnxinBcoOI3ppGnnL+VDJ75O45Nss6HtZd8IdN8touXPDtASfeI2T2LImb8VOZcL47wjQ==}
+    peerDependencies:
+      react: '>=16.8.0'
+    dependencies:
+      react: 18.3.1
+      tslib: 2.7.0
+    dev: false
+
+  /@dnd-kit/core@6.1.0(react-dom@18.3.1)(react@18.3.1):
+    resolution: {integrity: sha512-J3cQBClB4TVxwGo3KEjssGEXNJqGVWx17aRTZ1ob0FliR5IjYgTxl5YJbKTzA6IzrtelotH19v6y7uoIRUZPSg==}
+    peerDependencies:
+      react: '>=16.8.0'
+      react-dom: '>=16.8.0'
+    dependencies:
+      '@dnd-kit/accessibility': 3.1.0(react@18.3.1)
+      '@dnd-kit/utilities': 3.2.2(react@18.3.1)
+      react: 18.3.1
+      react-dom: 18.3.1(react@18.3.1)
+      tslib: 2.7.0
+    dev: false
+
+  /@dnd-kit/sortable@8.0.0(@dnd-kit/core@6.1.0)(react@18.3.1):
+    resolution: {integrity: sha512-U3jk5ebVXe1Lr7c2wU7SBZjcWdQP+j7peHJfCspnA81enlu88Mgd7CC8Q+pub9ubP7eKVETzJW+IBAhsqbSu/g==}
+    peerDependencies:
+      '@dnd-kit/core': ^6.1.0
+      react: '>=16.8.0'
+    dependencies:
+      '@dnd-kit/core': 6.1.0(react-dom@18.3.1)(react@18.3.1)
+      '@dnd-kit/utilities': 3.2.2(react@18.3.1)
+      react: 18.3.1
+      tslib: 2.7.0
+    dev: false
+
+  /@dnd-kit/utilities@3.2.2(react@18.3.1):
+    resolution: {integrity: sha512-+MKAJEOfaBe5SmV6t34p80MMKhjvUz0vRrvVJbPT0WElzaOJ/1xs+D+KDv+tD/NE5ujfrChEcshd4fLn0wpiqg==}
+    peerDependencies:
+      react: '>=16.8.0'
+    dependencies:
+      react: 18.3.1
+      tslib: 2.7.0
+    dev: false
+
   /@emotion/babel-plugin@11.12.0:
     resolution: {integrity: sha512-y2WQb+oP8Jqvvclh8Q55gLUyb7UFvgv7eJfsj7td5TToBrIUtPay2kMrZi4xjq9qw2vD0ZR5fSho0yqoFgX7Rw==}
     dependencies:
@@ -1675,20 +1696,20 @@ packages:
       prettier: 3.3.3
     dev: true
 
-  /@invoke-ai/ui-library@0.0.44(@chakra-ui/form-control@2.2.0)(@chakra-ui/icon@3.2.0)(@chakra-ui/media-query@3.3.0)(@chakra-ui/menu@2.2.1)(@chakra-ui/spinner@2.1.0)(@chakra-ui/system@2.6.2)(@fontsource-variable/inter@5.1.0)(@types/react@18.3.11)(i18next@23.15.1)(react-dom@18.3.1)(react@18.3.1):
-    resolution: {integrity: sha512-PDseHmdr8oi8cmrpx3UwIYHn4NduAJX2R0pM0pyM54xrCMPMgYiCbC/eOs8Gt4fBc2ziiPZ9UGoW4evnE3YJsg==}
+  /@invoke-ai/ui-library@0.0.43(@chakra-ui/form-control@2.2.0)(@chakra-ui/icon@3.2.0)(@chakra-ui/media-query@3.3.0)(@chakra-ui/menu@2.2.1)(@chakra-ui/spinner@2.1.0)(@chakra-ui/system@2.6.2)(@fontsource-variable/inter@5.1.0)(@types/react@18.3.11)(i18next@23.15.1)(react-dom@18.3.1)(react@18.3.1):
+    resolution: {integrity: sha512-t3fPYyks07ue3dEBPJuTHbeDLnDckDCOrtvc07mMDbLOnlPEZ0StaeiNGH+oO8qLzAuMAlSTdswgHfzTc2MmPw==}
     peerDependencies:
       '@fontsource-variable/inter': ^5.0.16
       react: ^18.2.0
       react-dom: ^18.2.0
     dependencies:
-      '@chakra-ui/anatomy': 2.2.2
-      '@chakra-ui/icons': 2.2.4(@chakra-ui/react@2.10.4)(react@18.3.1)
+      '@chakra-ui/anatomy': 2.3.4
+      '@chakra-ui/icons': 2.2.4(@chakra-ui/react@2.10.2)(react@18.3.1)
       '@chakra-ui/layout': 2.3.1(@chakra-ui/system@2.6.2)(react@18.3.1)
       '@chakra-ui/portal': 2.1.0(react-dom@18.3.1)(react@18.3.1)
-      '@chakra-ui/react': 2.10.4(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1)
-      '@chakra-ui/styled-system': 2.9.2
-      '@chakra-ui/theme-tools': 2.1.2(@chakra-ui/styled-system@2.9.2)
+      '@chakra-ui/react': 2.10.2(@emotion/react@11.13.3)(@emotion/styled@11.13.0)(@types/react@18.3.11)(framer-motion@11.10.0)(react-dom@18.3.1)(react@18.3.1)
+      '@chakra-ui/styled-system': 2.11.2(react@18.3.1)
+      '@chakra-ui/theme-tools': 2.2.6(@chakra-ui/styled-system@2.11.2)(react@18.3.1)
       '@emotion/react': 11.13.3(@types/react@18.3.11)(react@18.3.1)
       '@emotion/styled': 11.13.0(@emotion/react@11.13.3)(@types/react@18.3.11)(react@18.3.1)
       '@fontsource-variable/inter': 5.1.0
@@ -4292,10 +4313,6 @@ packages:
       open: 8.4.2
     dev: true
 
-  /bind-event-listener@3.0.0:
-    resolution: {integrity: sha512-PJvH288AWQhKs2v9zyfYdPzlPqf5bXbGMmhmUIY9x4dAUGIWgomO771oBQNwJnMQSnUIXhKu6sgzpBRXTlvb8Q==}
-    dev: false
-
   /bl@4.1.0:
     resolution: {integrity: sha512-1W07cM9gS6DcLperZfFSj+bWLtaPGSOHWhPiGzXmvVJbRLdG82sH/Kn8EtW1VqWVA54AKf2h5k5BbnIbwF3h6w==}
     dependencies:
@@ -7540,10 +7557,6 @@ packages:
     resolution: {integrity: sha512-NuaNSa6flKT5JaSYQzJok04JzTL1CA6aGhv5rfLW3PgqA+M2ChpZQnAC8h8i4ZFkBS8X5RqkDBHA7r4hej3K9A==}
     dev: true
 
-  /raf-schd@4.0.3:
-    resolution: {integrity: sha512-tQkJl2GRWh83ui2DiPTJz9wEiMN20syf+5oKfB03yYP7ioZcJwsIK8FjrtLwH1m7C7e+Tt2yYBlrOpdT+dyeIQ==}
-    dev: false
-
   /raf-throttle@2.0.6:
     resolution: {integrity: sha512-C7W6hy78A+vMmk5a/B6C5szjBHrUzWJkVyakjKCK59Uy2CcA7KhO1JUvvH32IXYFIcyJ3FMKP3ZzCc2/71I6Vg==}
     dev: false

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

@@ -96,9 +96,7 @@
         "new": "Neu",
         "ok": "OK",
         "close": "Schließen",
-        "clipboard": "Zwischenablage",
-        "generating": "Generieren",
-        "loadingModel": "Lade Modell"
+        "clipboard": "Zwischenablage"
     },
     "gallery": {
         "galleryImageSize": "Bildgröße",
@@ -593,15 +591,7 @@
         "loraTriggerPhrases": "LoRA-Auslösephrasen",
         "installingBundle": "Bündel wird installiert",
         "triggerPhrases": "Auslösephrasen",
-        "mainModelTriggerPhrases": "Hauptmodell-Auslösephrasen",
-        "noDefaultSettings": "Für dieses Modell sind keine Standardeinstellungen konfiguriert. Besuchen Sie den Modell-Manager, um Standardeinstellungen hinzuzufügen.",
-        "defaultSettingsOutOfSync": "Einige Einstellungen stimmen nicht mit den Standardeinstellungen des Modells überein:",
-        "clipLEmbed": "CLIP-L einbetten",
-        "clipGEmbed": "CLIP-G einbetten",
-        "hfTokenLabel": "HuggingFace-Token (für einige Modelle erforderlich)",
-        "hfTokenHelperText": "Für die Nutzung einiger Modelle ist ein HF-Token erforderlich. Klicken Sie hier, um Ihr Token zu erstellen oder zu erhalten.",
-        "hfForbidden": "Sie haben keinen Zugriff auf dieses HF-Modell",
-        "hfTokenInvalid": "Ungültiges oder fehlendes HF-Token"
+        "mainModelTriggerPhrases": "Hauptmodell-Auslösephrasen"
     },
     "parameters": {
         "images": "Bilder",
@@ -778,8 +768,7 @@
         "deletedPrivateBoardsCannotbeRestored": "Gelöschte Boards können nicht wiederhergestellt werden. Wenn Sie „Nur Board löschen“ wählen, werden die Bilder in einen privaten, nicht kategorisierten Status für den Ersteller des Bildes versetzt.",
         "assetsWithCount_one": "{{count}} in der Sammlung",
         "assetsWithCount_other": "{{count}} in der Sammlung",
-        "deletedBoardsCannotbeRestored": "Gelöschte Ordner können nicht wiederhergestellt werden. Die Auswahl von \"Nur Ordner löschen\" verschiebt Bilder in einen unkategorisierten Zustand.",
-        "updateBoardError": "Fehler beim Aktualisieren des Ordners"
+        "deletedBoardsCannotbeRestored": "Gelöschte Ordner können nicht wiederhergestellt werden. Die Auswahl von \"Nur Ordner löschen\" verschiebt Bilder in einen unkategorisierten Zustand."
     },
     "queue": {
         "status": "Status",
@@ -851,8 +840,7 @@
         "upscaling": "Hochskalierung",
         "canvas": "Leinwand",
         "prompts_one": "Prompt",
-        "prompts_other": "Prompts",
-        "batchSize": "Stapelgröße"
+        "prompts_other": "Prompts"
     },
     "metadata": {
         "negativePrompt": "Negativ Beschreibung",
@@ -883,9 +871,7 @@
         "recallParameter": "{{label}} Abrufen",
         "parsingFailed": "Parsing Fehlgeschlagen",
         "canvasV2Metadata": "Leinwand",
-        "guidance": "Führung",
-        "seamlessXAxis": "Nahtlose X Achse",
-        "seamlessYAxis": "Nahtlose Y Achse"
+        "guidance": "Führung"
     },
     "popovers": {
         "noiseUseCPU": {
@@ -1092,21 +1078,6 @@
         },
         "patchmatchDownScaleSize": {
             "heading": "Herunterskalieren"
-        },
-        "paramHeight": {
-            "heading": "Höhe",
-            "paragraphs": [
-                "Höhe des generierten Bildes. Muss ein Vielfaches von 8 sein."
-            ]
-        },
-        "paramUpscaleMethod": {
-            "heading": "Vergrößerungsmethode",
-            "paragraphs": [
-                "Methode zum Hochskalieren des Bildes für High Resolution Fix."
-            ]
-        },
-        "paramHrf": {
-            "heading": "High Resolution Fix aktivieren"
         }
     },
     "invocationCache": {
@@ -1421,13 +1392,7 @@
         "pullBboxIntoLayerOk": "Bbox in die Ebene gezogen",
         "saveBboxToGallery": "Bbox in Galerie speichern",
         "tool": {
-            "bbox": "Bbox",
-            "brush": "Pinsel",
-            "eraser": "Radiergummi",
-            "colorPicker": "Farbwähler",
-            "view": "Ansicht",
-            "rectangle": "Rechteck",
-            "move": "Verschieben"
+            "bbox": "Bbox"
         },
         "transform": {
             "fitToBbox": "An Bbox anpassen",
@@ -1469,6 +1434,7 @@
         "deleteReferenceImage": "Referenzbild löschen",
         "referenceImage": "Referenzbild",
         "opacity": "Opazität",
+        "resetCanvas": "Leinwand zurücksetzen",
         "removeBookmark": "Lesezeichen entfernen",
         "rasterLayer": "Raster-Ebene",
         "rasterLayers_withCount_visible": "Raster-Ebenen ({{count}})",
@@ -1545,30 +1511,7 @@
         "layer_one": "Ebene",
         "layer_other": "Ebenen",
         "layer_withCount_one": "Ebene ({{count}})",
-        "layer_withCount_other": "Ebenen ({{count}})",
-        "fill": {
-            "fillStyle": "Füllstil",
-            "diagonal": "Diagonal",
-            "vertical": "Vertikal",
-            "fillColor": "Füllfarbe",
-            "grid": "Raster",
-            "solid": "Solide",
-            "crosshatch": "Kreuzschraffur",
-            "horizontal": "Horizontal"
-        },
-        "filter": {
-            "apply": "Anwenden",
-            "reset": "Zurücksetzen",
-            "cancel": "Abbrechen",
-            "spandrel_filter": {
-                "label": "Bild-zu-Bild Modell",
-                "description": "Ein Bild-zu-Bild Modell auf der ausgewählten Ebene ausführen.",
-                "model": "Modell"
-            },
-            "filters": "Filter",
-            "filterType": "Filtertyp",
-            "filter": "Filter"
-        }
+        "layer_withCount_other": "Ebenen ({{count}})"
     },
     "upsell": {
         "shareAccess": "Zugang teilen",

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

@@ -122,7 +122,6 @@
         "goTo": "Go to",
         "hotkeysLabel": "Hotkeys",
         "loadingImage": "Loading Image",
-        "loadingModel": "Loading Model",
         "imageFailedToLoad": "Unable to Load Image",
         "img2img": "Image To Image",
         "inpaint": "inpaint",
@@ -175,9 +174,7 @@
         "placeholderSelectAModel": "Select a model",
         "reset": "Reset",
         "none": "None",
-        "new": "New",
-        "generating": "Generating",
-        "warnings": "Warnings"
+        "new": "New"
     },
     "hrf": {
         "hrf": "High Resolution Fix",
@@ -264,8 +261,7 @@
         "iterations_one": "Iteration",
         "iterations_other": "Iterations",
         "generations_one": "Generation",
-        "generations_other": "Generations",
-        "batchSize": "Batch Size"
+        "generations_other": "Generations"
     },
     "invocationCache": {
         "invocationCache": "Invocation Cache",
@@ -708,8 +704,6 @@
         "baseModel": "Base Model",
         "cancel": "Cancel",
         "clipEmbed": "CLIP Embed",
-        "clipLEmbed": "CLIP-L Embed",
-        "clipGEmbed": "CLIP-G Embed",
         "config": "Config",
         "convert": "Convert",
         "convertingModelBegin": "Converting Model. Please wait.",
@@ -979,8 +973,6 @@
         "zoomOutNodes": "Zoom Out",
         "betaDesc": "This invocation is in beta. Until it is stable, it may have breaking changes during app updates. We plan to support this invocation long-term.",
         "prototypeDesc": "This invocation is a prototype. It may have breaking changes during app updates and may be removed at any time.",
-        "internalDesc": "This invocation is used internally by Invoke. It may have breaking changes during app updates and may be removed at any time.",
-        "specialDesc": "This invocation some special handling in the app. For example, Batch nodes are used to queue multiple graphs from a single workflow.",
         "imageAccessError": "Unable to find image {{image_name}}, resetting to default",
         "boardAccessError": "Unable to find board {{board_id}}, resetting to default",
         "modelAccessError": "Unable to find model {{key}}, resetting to default",
@@ -1005,7 +997,7 @@
         "controlNetControlMode": "Control Mode",
         "copyImage": "Copy Image",
         "denoisingStrength": "Denoising Strength",
-        "disabledNoRasterContent": "Disabled (No Raster Content)",
+        "noRasterLayers": "No Raster Layers",
         "downloadImage": "Download Image",
         "general": "General",
         "guidance": "Guidance",
@@ -1019,11 +1011,8 @@
             "addingImagesTo": "Adding images to",
             "invoke": "Invoke",
             "missingFieldTemplate": "Missing field template",
-            "missingInputForField": "{{nodeLabel}} -> {{fieldLabel}}: missing input",
+            "missingInputForField": "{{nodeLabel}} -> {{fieldLabel}} missing input",
             "missingNodeTemplate": "Missing node template",
-            "collectionEmpty": "{{nodeLabel}} -> {{fieldLabel}} empty collection",
-            "collectionTooFewItems": "{{nodeLabel}} -> {{fieldLabel}}: too few items, minimum {{minItems}}",
-            "collectionTooManyItems": "{{nodeLabel}} -> {{fieldLabel}}: too many items, maximum {{maxItems}}",
             "noModelSelected": "No model selected",
             "noT5EncoderModelSelected": "No T5 Encoder model selected for FLUX generation",
             "noFLUXVAEModelSelected": "No VAE model selected for FLUX generation",
@@ -1032,14 +1021,26 @@
             "fluxModelIncompatibleBboxHeight": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16), bbox height is {{height}}",
             "fluxModelIncompatibleScaledBboxWidth": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16), scaled bbox width is {{width}}",
             "fluxModelIncompatibleScaledBboxHeight": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16), scaled bbox height is {{height}}",
-            "canvasIsFiltering": "Canvas is busy (filtering)",
-            "canvasIsTransforming": "Canvas is busy (transforming)",
-            "canvasIsRasterizing": "Canvas is busy (rasterizing)",
-            "canvasIsCompositing": "Canvas is busy (compositing)",
-            "canvasIsSelectingObject": "Canvas is busy (selecting object)",
+            "canvasIsFiltering": "Canvas is filtering",
+            "canvasIsTransforming": "Canvas is transforming",
+            "canvasIsRasterizing": "Canvas is rasterizing",
+            "canvasIsCompositing": "Canvas is compositing",
             "noPrompts": "No prompts generated",
             "noNodesInGraph": "No nodes in graph",
-            "systemDisconnected": "System disconnected"
+            "systemDisconnected": "System disconnected",
+            "layer": {
+                "controlAdapterNoModelSelected": "no Control Adapter model selected",
+                "controlAdapterIncompatibleBaseModel": "incompatible Control Adapter base model",
+                "t2iAdapterIncompatibleBboxWidth": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, bbox width is {{width}}",
+                "t2iAdapterIncompatibleBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, bbox height is {{height}}",
+                "t2iAdapterIncompatibleScaledBboxWidth": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, scaled bbox width is {{width}}",
+                "t2iAdapterIncompatibleScaledBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, scaled bbox height is {{height}}",
+                "ipAdapterNoModelSelected": "no IP adapter selected",
+                "ipAdapterIncompatibleBaseModel": "incompatible IP Adapter base model",
+                "ipAdapterNoImageSelected": "no IP Adapter image selected",
+                "rgNoPromptsOrIPAdapters": "no text prompts or IP Adapters",
+                "rgNoRegion": "no region selected"
+            }
         },
         "maskBlur": "Mask Blur",
         "negativePromptPlaceholder": "Negative Prompt",
@@ -1136,7 +1137,6 @@
         "resetWebUI": "Reset Web UI",
         "resetWebUIDesc1": "Resetting the web UI only resets the browser's local cache of your images and remembered settings. It does not delete any images from disk.",
         "resetWebUIDesc2": "If images aren't showing up in the gallery or something else isn't working, please try resetting before submitting an issue on GitHub.",
-        "showDetailedInvocationProgress": "Show Progress Details",
         "showProgressInViewer": "Show Progress Images in Viewer",
         "ui": "User Interface",
         "clearIntermediatesDisabled": "Queue must be empty to clear intermediates",
@@ -1307,9 +1307,8 @@
         "controlNetBeginEnd": {
             "heading": "Begin / End Step Percentage",
             "paragraphs": [
-                "This setting determines which portion of the denoising (generation) process incorporates the guidance from this layer.",
-                "• Start Step (%): Specifies when to begin applying the guidance from this layer during the generation process.",
-                "• End Step (%): Specifies when to stop applying this layer's guidance and revert general guidance from the model and other settings."
+                "The part of the of the denoising process that will have the Control Adapter applied.",
+                "Generally, Control Adapters applied at the start of the process guide composition, and Control Adapters applied at the end guide details."
             ]
         },
         "controlNetControlMode": {
@@ -1319,7 +1318,7 @@
         "controlNetProcessor": {
             "heading": "Processor",
             "paragraphs": [
-                "Method of processing the input image to guide the generation process. Different processors will provide different effects or styles in your generated images."
+                "Method of processing the input image to guide the generation process. Different processors will providedifferent effects or styles in your generated images."
             ]
         },
         "controlNetResizeMode": {
@@ -1327,15 +1326,13 @@
             "paragraphs": ["Method to fit Control Adapter's input image size to the output generation size."]
         },
         "ipAdapterMethod": {
-            "heading": "Mode",
-            "paragraphs": ["The mode defines how the reference image will guide the generation process."]
+            "heading": "Method",
+            "paragraphs": ["Method by which to apply the current IP Adapter."]
         },
         "controlNetWeight": {
             "heading": "Weight",
             "paragraphs": [
-                "Adjusts how strongly the layer influences the generation process",
-                "• Higher Weight (.75-2): Creates a more significant impact on the final result.",
-                "• Lower Weight (0-.75): Creates a smaller impact on the final result."
+                "Weight of the Control Adapter. Higher weight will lead to larger impacts on the final image."
             ]
         },
         "dynamicPrompts": {
@@ -1657,6 +1654,7 @@
         "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",
@@ -1669,11 +1667,11 @@
         "mergingLayers": "Merging layers",
         "clearHistory": "Clear History",
         "bboxOverlay": "Show Bbox Overlay",
-        "newSession": "New Session",
+        "resetCanvas": "Reset Canvas",
         "clearCaches": "Clear Caches",
         "recalculateRects": "Recalculate Rects",
         "clipToBbox": "Clip Strokes to Bbox",
-        "outputOnlyMaskedRegions": "Output Only Generated Regions",
+        "outputOnlyMaskedRegions": "Output Only Masked Regions",
         "addLayer": "Add Layer",
         "duplicate": "Duplicate",
         "moveToFront": "Move to Front",
@@ -1701,12 +1699,8 @@
         "controlLayer": "Control Layer",
         "inpaintMask": "Inpaint Mask",
         "regionalGuidance": "Regional Guidance",
-        "referenceImageRegional": "Reference Image (Regional)",
-        "referenceImageGlobal": "Reference Image (Global)",
-        "asRasterLayer": "As $t(controlLayers.rasterLayer)",
-        "asRasterLayerResize": "As $t(controlLayers.rasterLayer) (Resize)",
-        "asControlLayer": "As $t(controlLayers.controlLayer)",
-        "asControlLayerResize": "As $t(controlLayers.controlLayer) (Resize)",
+        "canvasAsRasterLayer": "$t(controlLayers.canvas) as $t(controlLayers.rasterLayer)",
+        "canvasAsControlLayer": "$t(controlLayers.canvas) as $t(controlLayers.controlLayer)",
         "referenceImage": "Reference Image",
         "regionalReferenceImage": "Regional Reference Image",
         "globalReferenceImage": "Global Reference Image",
@@ -1774,7 +1768,6 @@
         "pullBboxIntoLayer": "Pull Bbox into Layer",
         "pullBboxIntoReferenceImage": "Pull Bbox into Reference Image",
         "showProgressOnCanvas": "Show Progress on Canvas",
-        "useImage": "Use Image",
         "prompt": "Prompt",
         "negativePrompt": "Negative Prompt",
         "beginEndStepPercentShort": "Begin/End %",
@@ -1783,26 +1776,8 @@
         "newGallerySessionDesc": "This will clear the canvas and all settings except for your model selection. Generations will be sent to the gallery.",
         "newCanvasSession": "New Canvas Session",
         "newCanvasSessionDesc": "This will clear the canvas and all settings except for your model selection. Generations will be staged on the canvas.",
-        "resetCanvasLayers": "Reset Canvas Layers",
-        "resetGenerationSettings": "Reset Generation Settings",
         "replaceCurrent": "Replace Current",
         "controlLayerEmptyState": "<UploadButton>Upload an image</UploadButton>, drag an image from the <GalleryButton>gallery</GalleryButton> onto this layer, or draw on the canvas to get started.",
-        "referenceImageEmptyState": "<UploadButton>Upload an image</UploadButton> or drag an image from the <GalleryButton>gallery</GalleryButton> onto this layer to get started.",
-        "warnings": {
-            "problemsFound": "Problems found",
-            "unsupportedModel": "layer not supported for selected base model",
-            "controlAdapterNoModelSelected": "no Control Layer model selected",
-            "controlAdapterIncompatibleBaseModel": "incompatible Control Layer base model",
-            "controlAdapterNoControl": "no control selected/drawn",
-            "ipAdapterNoModelSelected": "no Reference Image model selected",
-            "ipAdapterIncompatibleBaseModel": "incompatible Reference Image base model",
-            "ipAdapterNoImageSelected": "no Reference Image image selected",
-            "rgNoPromptsOrIPAdapters": "no text prompts or Reference Images",
-            "rgNegativePromptNotSupported": "Negative Prompt not supported for selected base model",
-            "rgReferenceImagesNotSupported": "regional Reference Images not supported for selected base model",
-            "rgAutoNegativeNotSupported": "Auto-Negative not supported for selected base model",
-            "rgNoRegion": "no region drawn"
-        },
         "controlMode": {
             "controlMode": "Control Mode",
             "balanced": "Balanced (recommended)",
@@ -1811,13 +1786,10 @@
             "megaControl": "Mega Control"
         },
         "ipAdapterMethod": {
-            "ipAdapterMethod": "Mode",
-            "full": "Style and Composition",
-            "fullDesc": "Applies visual style (colors, textures) & composition (layout, structure).",
+            "ipAdapterMethod": "IP Adapter Method",
+            "full": "Full",
             "style": "Style Only",
-            "styleDesc": "Applies visual style (colors, textures) without considering its layout.",
-            "composition": "Composition Only",
-            "compositionDesc": "Replicates layout & structure while ignoring the reference's style."
+            "composition": "Composition Only"
         },
         "fill": {
             "fillColor": "Fill Color",
@@ -2027,9 +1999,7 @@
         "upscaleModelDesc": "Upscale (image to image) model",
         "missingUpscaleInitialImage": "Missing initial image for upscaling",
         "missingUpscaleModel": "Missing upscale model",
-        "missingTileControlNetModel": "No valid tile ControlNet models installed",
-        "incompatibleBaseModel": "Unsupported main model architecture for upscaling",
-        "incompatibleBaseModelDesc": "Upscaling is supported for SD1.5 and SDXL architecture models only. Change the main model to enable upscaling."
+        "missingTileControlNetModel": "No valid tile ControlNet models installed"
     },
     "stylePresets": {
         "active": "Active",
@@ -2132,74 +2102,10 @@
     },
     "whatsNew": {
         "whatsNewInInvoke": "What's New in Invoke",
-        "items": [
-            "<StrongComponent>Workflows</StrongComponent>: Run a workflow for a collection of images using the new <StrongComponent>Image Batch</StrongComponent> node.",
-            "<StrongComponent>FLUX</StrongComponent>: Support for XLabs IP Adapter v2."
-        ],
+        "line1": "<StrongComponent>Layer Merging</StrongComponent>: New <StrongComponent>Merge Down</StrongComponent> and improved <StrongComponent>Merge Visible</StrongComponent> for all layers, with special handling for Regional Guidance and Control Layers.",
+        "line2": "<StrongComponent>HF Token Support</StrongComponent>: Upload models that require Hugging Face authentication.",
         "readReleaseNotes": "Read Release Notes",
         "watchRecentReleaseVideos": "Watch Recent Release Videos",
         "watchUiUpdatesOverview": "Watch UI Updates Overview"
-    },
-    "supportVideos": {
-        "supportVideos": "Support Videos",
-        "gettingStarted": "Getting Started",
-        "controlCanvas": "Control Canvas",
-        "watch": "Watch",
-        "studioSessionsDesc1": "Check out the <StudioSessionsPlaylistLink /> for Invoke deep dives.",
-        "studioSessionsDesc2": "Join our <DiscordLink /> to participate in the live sessions and ask questions. Sessions are uploaded to the playlist the following week.",
-        "videos": {
-            "creatingYourFirstImage": {
-                "title": "Creating Your First Image",
-                "description": "Introduction to creating an image from scratch using Invoke's tools."
-            },
-            "usingControlLayersAndReferenceGuides": {
-                "title": "Using Control Layers and Reference Guides",
-                "description": "Learn how to guide your image creation with control layers and reference images."
-            },
-            "understandingImageToImageAndDenoising": {
-                "title": "Understanding Image-to-Image and Denoising",
-                "description": "Overview of image-to-image transformations and denoising in Invoke."
-            },
-            "exploringAIModelsAndConceptAdapters": {
-                "title": "Exploring AI Models and Concept Adapters",
-                "description": "Dive into AI models and how to use concept adapters for creative control."
-            },
-            "creatingAndComposingOnInvokesControlCanvas": {
-                "title": "Creating and Composing on Invoke's Control Canvas",
-                "description": "Learn to compose images using Invoke's control canvas."
-            },
-            "upscaling": {
-                "title": "Upscaling",
-                "description": "How to upscale images with Invoke's tools to enhance resolution."
-            },
-            "howDoIGenerateAndSaveToTheGallery": {
-                "title": "How Do I Generate and Save to the Gallery?",
-                "description": "Steps to generate and save images to the gallery."
-            },
-            "howDoIEditOnTheCanvas": {
-                "title": "How Do I Edit on the Canvas?",
-                "description": "Guide to editing images directly on the canvas."
-            },
-            "howDoIDoImageToImageTransformation": {
-                "title": "How Do I Do Image-to-Image Transformation?",
-                "description": "Tutorial on performing image-to-image transformations in Invoke."
-            },
-            "howDoIUseControlNetsAndControlLayers": {
-                "title": "How Do I Use Control Nets and Control Layers?",
-                "description": "Learn to apply control layers and controlnets to your images."
-            },
-            "howDoIUseGlobalIPAdaptersAndReferenceImages": {
-                "title": "How Do I Use Global IP Adapters and Reference Images?",
-                "description": "Introduction to adding reference images and global IP adapters."
-            },
-            "howDoIUseInpaintMasks": {
-                "title": "How Do I Use Inpaint Masks?",
-                "description": "How to apply inpaint masks for image correction and variation."
-            },
-            "howDoIOutpaint": {
-                "title": "How Do I Outpaint?",
-                "description": "Guide to outpainting beyond the original image borders."
-            }
-        }
     }
 }

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

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

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

@@ -327,6 +327,7 @@
                 "t2iAdapterIncompatibleBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, la hauteur de la bounding box est {{height}}",
                 "t2iAdapterIncompatibleBboxWidth": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, la largeur de la bounding box est {{width}}",
                 "ipAdapterIncompatibleBaseModel": "modèle de base d'IP adapter incompatible",
+                "rgNoRegion": "aucune zone sélectionnée",
                 "controlAdapterNoModelSelected": "aucun modèle de Control Adapter sélectionné"
             },
             "noPrompts": "Aucun prompts généré",
@@ -1984,6 +1985,7 @@
         "inpaintMask_withCount_many": "Remplir les masques",
         "inpaintMask_withCount_other": "Remplir les masques",
         "newImg2ImgCanvasFromImage": "Nouvelle Img2Img à partir de l'image",
+        "resetCanvas": "Réinitialiser la Toile",
         "bboxOverlay": "Afficher la superposition des Bounding Box",
         "moveToFront": "Déplacer vers le permier plan",
         "moveToBack": "Déplacer vers l'arrière plan",
@@ -2032,6 +2034,7 @@
             "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)",
@@ -2041,7 +2044,8 @@
         "convertInpaintMaskTo": "Convertir $t(controlLayers.inpaintMask) vers",
         "copyControlLayerTo": "Copier $t(controlLayers.controlLayer) vers",
         "newInpaintMask": "Nouveau $t(controlLayers.inpaintMask)",
-        "newRasterLayer": "Nouveau $t(controlLayers.rasterLayer)"
+        "newRasterLayer": "Nouveau $t(controlLayers.rasterLayer)",
+        "canvasAsRasterLayer": "$t(controlLayers.canvas) en tant que $t(controlLayers.rasterLayer)"
     },
     "upscaling": {
         "exceedsMaxSizeDetails": "La limite maximale d'agrandissement est de {{maxUpscaleDimension}}x{{maxUpscaleDimension}} pixels. Veuillez essayer une image plus petite ou réduire votre sélection d'échelle.",

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

@@ -94,10 +94,7 @@
         "view": "Vista",
         "close": "Chiudi",
         "clipboard": "Appunti",
-        "ok": "Ok",
-        "generating": "Generazione",
-        "loadingModel": "Caricamento del modello",
-        "warnings": "Avvisi"
+        "ok": "Ok"
     },
     "gallery": {
         "galleryImageSize": "Dimensione dell'immagine",
@@ -600,18 +597,7 @@
         "huggingFace": "HuggingFace",
         "huggingFaceRepoID": "HuggingFace Repository ID",
         "clipEmbed": "CLIP Embed",
-        "t5Encoder": "T5 Encoder",
-        "hfTokenInvalidErrorMessage": "Gettone HuggingFace non valido o mancante.",
-        "hfTokenRequired": "Stai tentando di scaricare un modello che richiede un gettone HuggingFace valido.",
-        "hfTokenUnableToVerifyErrorMessage": "Impossibile verificare il gettone HuggingFace. Ciò è probabilmente dovuto a un errore di rete. Riprova più tardi.",
-        "hfTokenHelperText": "Per utilizzare alcuni modelli è necessario un gettone HF. Fai clic qui per creare o ottenere il tuo gettone.",
-        "hfTokenInvalid": "Gettone HF non valido o mancante",
-        "hfTokenUnableToVerify": "Impossibile verificare il gettone HF",
-        "hfTokenSaved": "Gettone HF salvato",
-        "hfForbidden": "Non hai accesso a questo modello HF",
-        "hfTokenLabel": "Gettone HuggingFace (richiesto per alcuni modelli)",
-        "hfForbiddenErrorMessage": "Consigliamo di visitare la pagina del repository su HuggingFace.com. Il proprietario potrebbe richiedere l'accettazione dei termini per poter effettuare il download.",
-        "hfTokenInvalidErrorMessage2": "Aggiornalo in "
+        "t5Encoder": "T5 Encoder"
     },
     "parameters": {
         "images": "Immagini",
@@ -672,15 +658,11 @@
                 "ipAdapterIncompatibleBaseModel": "Il modello base dell'adattatore IP non è compatibile",
                 "ipAdapterNoImageSelected": "Nessuna immagine dell'adattatore IP selezionata",
                 "rgNoPromptsOrIPAdapters": "Nessun prompt o adattatore IP",
+                "rgNoRegion": "Nessuna regione selezionata",
                 "t2iAdapterIncompatibleBboxWidth": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, larghezza riquadro è {{width}}",
                 "t2iAdapterIncompatibleBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, altezza riquadro è {{height}}",
                 "t2iAdapterIncompatibleScaledBboxWidth": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, larghezza del riquadro scalato {{width}}",
-                "t2iAdapterIncompatibleScaledBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, altezza del riquadro scalato {{height}}",
-                "rgNegativePromptNotSupported": "prompt negativo non supportato per il modello base selezionato",
-                "rgAutoNegativeNotSupported": "auto-negativo non supportato per il modello base selezionato",
-                "emptyLayer": "livello vuoto",
-                "unsupportedModel": "livello non supportato per il modello base selezionato",
-                "rgReferenceImagesNotSupported": "immagini di riferimento regionali non supportate per il modello base selezionato"
+                "t2iAdapterIncompatibleScaledBboxHeight": "$t(parameters.invoke.layer.t2iAdapterRequiresDimensionsToBeMultipleOf) {{multiple}}, altezza del riquadro scalato {{height}}"
             },
             "fluxModelIncompatibleBboxHeight": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16), altezza riquadro è {{height}}",
             "fluxModelIncompatibleBboxWidth": "$t(parameters.invoke.fluxRequiresDimensionsToBeMultipleOf16), larghezza riquadro è {{width}}",
@@ -692,11 +674,7 @@
             "canvasIsTransforming": "La tela sta trasformando",
             "canvasIsRasterizing": "La tela sta rasterizzando",
             "canvasIsCompositing": "La tela è in fase di composizione",
-            "canvasIsFiltering": "La tela sta filtrando",
-            "collectionTooManyItems": "{{nodeLabel}} -> {{fieldLabel}}: troppi elementi, massimo {{maxItems}}",
-            "canvasIsSelectingObject": "La tela è occupata (selezione dell'oggetto)",
-            "collectionTooFewItems": "{{nodeLabel}} -> {{fieldLabel}}: troppi pochi elementi, minimo {{minItems}}",
-            "collectionEmpty": "{{nodeLabel}} -> {{fieldLabel}} raccolta vuota"
+            "canvasIsFiltering": "La tela sta filtrando"
         },
         "useCpuNoise": "Usa la CPU per generare rumore",
         "iterations": "Iterazioni",
@@ -721,9 +699,7 @@
         "staged": "Maschera espansa",
         "optimizedImageToImage": "Immagine-a-immagine ottimizzata",
         "sendToCanvas": "Invia alla Tela",
-        "coherenceMinDenoise": "Min rid. rumore",
-        "recallMetadata": "Richiama i metadati",
-        "disabledNoRasterContent": "Disabilitato (nessun contenuto Raster)"
+        "coherenceMinDenoise": "Riduzione minima del rumore"
     },
     "settings": {
         "models": "Modelli",
@@ -761,8 +737,7 @@
         "confirmOnNewSession": "Conferma su nuova sessione",
         "enableModelDescriptions": "Abilita le descrizioni dei modelli nei menu a discesa",
         "modelDescriptionsDisabled": "Descrizioni dei modelli nei menu a discesa disabilitate",
-        "modelDescriptionsDisabledDesc": "Le descrizioni dei modelli nei menu a discesa sono state disabilitate. Abilitale nelle Impostazioni.",
-        "showDetailedInvocationProgress": "Mostra dettagli avanzamento"
+        "modelDescriptionsDisabledDesc": "Le descrizioni dei modelli nei menu a discesa sono state disabilitate. Abilitale nelle Impostazioni."
     },
     "toast": {
         "uploadFailed": "Caricamento fallito",
@@ -981,9 +956,7 @@
         "saveToGallery": "Salva nella Galleria",
         "noMatchingWorkflows": "Nessun flusso di lavoro corrispondente",
         "noWorkflows": "Nessun flusso di lavoro",
-        "workflowHelpText": "Hai bisogno di aiuto? Consulta la nostra guida <LinkComponent>Introduzione ai flussi di lavoro</LinkComponent>.",
-        "specialDesc": "Questa invocazione comporta una gestione speciale nell'applicazione. Ad esempio, i nodi Lotto vengono utilizzati per mettere in coda più grafici da un singolo flusso di lavoro.",
-        "internalDesc": "Questa invocazione è utilizzata internamente da Invoke. Potrebbe subire modifiche significative durante gli aggiornamenti dell'app e potrebbe essere rimossa in qualsiasi momento."
+        "workflowHelpText": "Hai bisogno di aiuto? Consulta la nostra guida <LinkComponent>Introduzione ai flussi di lavoro</LinkComponent>."
     },
     "boards": {
         "autoAddBoard": "Aggiungi automaticamente bacheca",
@@ -1104,8 +1077,7 @@
         "workflows": "Flussi di lavoro",
         "generation": "Generazione",
         "other": "Altro",
-        "gallery": "Galleria",
-        "batchSize": "Dimensione del lotto"
+        "gallery": "Galleria"
     },
     "models": {
         "noMatchingModels": "Nessun modello corrispondente",
@@ -1208,8 +1180,7 @@
             "heading": "Percentuale passi Inizio / Fine",
             "paragraphs": [
                 "La parte del processo di rimozione del rumore in cui verrà applicato l'adattatore di controllo.",
-                "In genere, gli adattatori di controllo applicati all'inizio del processo guidano la composizione, mentre quelli applicati alla fine guidano i dettagli.",
-                "• Passo finale (%): specifica quando interrompere l'applicazione della guida di questo livello e ripristinare la guida generale dal modello e altre impostazioni."
+                "In genere, gli adattatori di controllo applicati all'inizio del processo guidano la composizione, mentre quelli applicati alla fine guidano i dettagli."
             ]
         },
         "noiseUseCPU": {
@@ -1292,9 +1263,8 @@
         },
         "paramDenoisingStrength": {
             "paragraphs": [
-                "Controlla la differenza tra l'immagine generata e il/i livello/i raster.",
-                "Una forza inferiore rimane più vicina ai livelli raster visibili combinati. Una forza superiore si basa maggiormente sul prompt globale.",
-                "Se non sono presenti livelli raster con contenuto visibile, questa impostazione viene ignorata."
+                "Quanto rumore viene aggiunto all'immagine in ingresso.",
+                "0 risulterà in un'immagine identica, mentre 1 risulterà in un'immagine completamente nuova."
             ],
             "heading": "Forza di riduzione del rumore"
         },
@@ -1306,16 +1276,14 @@
         },
         "infillMethod": {
             "paragraphs": [
-                "Metodo di riempimento durante il processo di Outpaint o Inpaint."
+                "Metodo di riempimento durante il processo di Outpainting o Inpainting."
             ],
             "heading": "Metodo di riempimento"
         },
         "controlNetWeight": {
             "heading": "Peso",
             "paragraphs": [
-                "Regola la forza con cui il livello influenza il processo di generazione",
-                "• Peso maggiore (0.75-2): crea un impatto più significativo sul risultato finale.",
-                "• Peso inferiore (0-0.75): crea un impatto minore sul risultato finale."
+                "Peso dell'adattatore di controllo. Un peso maggiore porterà a impatti maggiori sull'immagine finale."
             ]
         },
         "paramCFGScale": {
@@ -1476,7 +1444,7 @@
             "heading": "Livello minimo di riduzione del rumore",
             "paragraphs": [
                 "Intensità minima di riduzione rumore per la modalità di Coerenza",
-                "L'intensità minima di riduzione del rumore per la regione di coerenza durante l'inpaint o l'outpaint"
+                "L'intensità minima di riduzione del rumore per la regione di coerenza durante l'inpainting o l'outpainting"
             ]
         },
         "compositingMaskBlur": {
@@ -1530,7 +1498,7 @@
         "optimizedDenoising": {
             "heading": "Immagine-a-immagine ottimizzata",
             "paragraphs": [
-                "Abilita 'Immagine-a-immagine ottimizzata' per una scala di riduzione del rumore più graduale per le trasformazioni da immagine a immagine e di inpaint con modelli Flux. Questa impostazione migliora la capacità di controllare la quantità di modifica applicata a un'immagine, ma può essere disattivata se preferisci usare la scala di riduzione rumore standard. Questa impostazione è ancora in fase di messa a punto ed è in stato beta."
+                "Abilita 'Immagine-a-immagine ottimizzata' per una scala di riduzione del rumore più graduale per le trasformazioni da immagine a immagine e di inpainting con modelli Flux. Questa impostazione migliora la capacità di controllare la quantità di modifica applicata a un'immagine, ma può essere disattivata se preferisci usare la scala di riduzione rumore standard. Questa impostazione è ancora in fase di messa a punto ed è in stato beta."
             ]
         },
         "paramGuidance": {
@@ -1765,7 +1733,8 @@
         "newRegionalReferenceImageError": "Problema nella creazione dell'immagine di riferimento regionale",
         "newControlLayerOk": "Livello di controllo creato",
         "bboxOverlay": "Mostra sovrapposizione riquadro",
-        "outputOnlyMaskedRegions": "In uscita solo le regioni generate",
+        "resetCanvas": "Reimposta la tela",
+        "outputOnlyMaskedRegions": "Solo regioni mascherate in uscita",
         "enableAutoNegative": "Abilita Auto Negativo",
         "disableAutoNegative": "Disabilita Auto Negativo",
         "showHUD": "Mostra HUD",
@@ -1802,7 +1771,7 @@
         "globalReferenceImage_withCount_many": "Immagini di riferimento Globali",
         "globalReferenceImage_withCount_other": "Immagini di riferimento Globali",
         "controlMode": {
-            "balanced": "Bilanciato (consigliato)",
+            "balanced": "Bilanciato",
             "controlMode": "Modalità di controllo",
             "prompt": "Prompt",
             "control": "Controllo",
@@ -1813,13 +1782,10 @@
         "beginEndStepPercentShort": "Inizio/Fine %",
         "stagingOnCanvas": "Genera immagini nella",
         "ipAdapterMethod": {
-            "full": "Stile e Composizione",
+            "full": "Completo",
             "style": "Solo Stile",
             "composition": "Solo Composizione",
-            "ipAdapterMethod": "Metodo Adattatore IP",
-            "fullDesc": "Applica lo stile visivo (colori, texture) e la composizione (disposizione, struttura).",
-            "styleDesc": "Applica lo stile visivo (colori, texture) senza considerare la disposizione.",
-            "compositionDesc": "Replica disposizione e struttura ignorando lo stile di riferimento."
+            "ipAdapterMethod": "Metodo Adattatore IP"
         },
         "showingType": "Mostra {{type}}",
         "dynamicGrid": "Griglia dinamica",
@@ -1915,10 +1881,7 @@
             "lineart_anime_edge_detection": {
                 "description": "Genera una mappa dei bordi dal livello selezionato utilizzando il modello di rilevamento dei bordi Lineart Anime.",
                 "label": "Rilevamento bordi Lineart Anime"
-            },
-            "forMoreControl": "Per un maggiore controllo, fare clic su Avanzate qui sotto.",
-            "advanced": "Avanzate",
-            "processingLayerWith": "Elaborazione del livello con il filtro {{type}}."
+            }
         },
         "controlLayers_withCount_hidden": "Livelli di controllo ({{count}} nascosti)",
         "regionalGuidance_withCount_hidden": "Guida regionale ({{count}} nascosti)",
@@ -2053,6 +2016,8 @@
         "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",
@@ -2060,18 +2025,7 @@
         "newControlLayer": "Nuovo $t(controlLayers.controlLayer)",
         "newInpaintMask": "Nuova $t(controlLayers.inpaintMask)",
         "replaceCurrent": "Sostituisci corrente",
-        "mergeDown": "Unire in basso",
-        "mergingLayers": "Unione dei livelli",
-        "controlLayerEmptyState": "<UploadButton>Carica un'immagine</UploadButton>, trascina un'immagine dalla <GalleryButton>galleria</GalleryButton> su questo livello oppure disegna sulla tela per iniziare.",
-        "useImage": "Usa immagine",
-        "resetGenerationSettings": "Ripristina impostazioni di generazione",
-        "referenceImageEmptyState": "Per iniziare, <UploadButton>carica un'immagine</UploadButton> oppure trascina un'immagine dalla <GalleryButton>galleria</GalleryButton> su questo livello.",
-        "asRasterLayer": "Come $t(controlLayers.rasterLayer)",
-        "asRasterLayerResize": "Come $t(controlLayers.rasterLayer) (Ridimensiona)",
-        "asControlLayer": "Come $t(controlLayers.controlLayer)",
-        "asControlLayerResize": "Come $t(controlLayers.controlLayer) (Ridimensiona)",
-        "newSession": "Nuova sessione",
-        "resetCanvasLayers": "Ripristina livelli Tela"
+        "mergeDown": "Unire in basso"
     },
     "ui": {
         "tabs": {
@@ -2103,9 +2057,7 @@
         "postProcessingMissingModelWarning": "Visita <LinkComponent>Gestione modelli</LinkComponent> per installare un modello di post-elaborazione (da immagine a immagine).",
         "exceedsMaxSize": "Le impostazioni di ampliamento superano il limite massimo delle dimensioni",
         "exceedsMaxSizeDetails": "Il limite massimo di ampliamento è {{maxUpscaleDimension}}x{{maxUpscaleDimension}} pixel. Prova un'immagine più piccola o diminuisci la scala selezionata.",
-        "upscale": "Amplia",
-        "incompatibleBaseModel": "Architettura del modello principale non supportata per l'ampliamento",
-        "incompatibleBaseModelDesc": "L'ampliamento è supportato solo per i modelli di architettura SD1.5 e SDXL. Cambia il modello principale per abilitare l'ampliamento."
+        "upscale": "Amplia"
     },
     "upsell": {
         "inviteTeammates": "Invita collaboratori",
@@ -2167,13 +2119,12 @@
     },
     "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",
-        "watchUiUpdatesOverview": "Guarda le novità dell'interfaccia",
-        "items": [
-            "<StrongComponent>Flussi di lavoro</StrongComponent>: esegui un flusso di lavoro per una raccolta di immagini utilizzando il nuovo nodo <StrongComponent>Lotto di immagini</StrongComponent>.",
-            "<StrongComponent>Tela</StrongComponent>: elaborazione semplificata del livello di controllo e impostazioni di controllo predefinite migliorate."
-        ]
+        "line1": "Strumento <ItalicComponent>Seleziona oggetto</ItalicComponent> per la selezione e la modifica precise degli oggetti",
+        "watchUiUpdatesOverview": "Guarda le novità dell'interfaccia"
     },
     "system": {
         "logLevel": {
@@ -2199,67 +2150,5 @@
             "logNamespaces": "Elementi del registro"
         },
         "enableLogging": "Abilita la registrazione"
-    },
-    "supportVideos": {
-        "gettingStarted": "Iniziare",
-        "supportVideos": "Video di supporto",
-        "videos": {
-            "usingControlLayersAndReferenceGuides": {
-                "title": "Utilizzo di livelli di controllo e guide di riferimento",
-                "description": "Scopri come guidare la creazione delle tue immagini con livelli di controllo e immagini di riferimento."
-            },
-            "creatingYourFirstImage": {
-                "description": "Introduzione alla creazione di un'immagine da zero utilizzando gli strumenti di Invoke.",
-                "title": "Creazione della tua prima immagine"
-            },
-            "understandingImageToImageAndDenoising": {
-                "description": "Panoramica delle trasformazioni immagine-a-immagine e della riduzione del rumore in Invoke.",
-                "title": "Comprendere immagine-a-immagine e riduzione del rumore"
-            },
-            "howDoIDoImageToImageTransformation": {
-                "description": "Tutorial su come eseguire trasformazioni da immagine a immagine in Invoke.",
-                "title": "Come si esegue la trasformazione da immagine-a-immagine?"
-            },
-            "howDoIUseInpaintMasks": {
-                "title": "Come si usano le maschere Inpaint?",
-                "description": "Come applicare maschere inpaint per la correzione e la variazione delle immagini."
-            },
-            "howDoIOutpaint": {
-                "description": "Guida all'outpainting oltre i confini dell'immagine originale.",
-                "title": "Come posso eseguire l'outpainting?"
-            },
-            "exploringAIModelsAndConceptAdapters": {
-                "description": "Approfondisci i modelli di intelligenza artificiale e scopri come utilizzare gli adattatori concettuali per il controllo creativo.",
-                "title": "Esplorazione dei modelli di IA e degli adattatori concettuali"
-            },
-            "upscaling": {
-                "title": "Ampliamento",
-                "description": "Come ampliare le immagini con gli strumenti di Invoke per migliorarne la risoluzione."
-            },
-            "creatingAndComposingOnInvokesControlCanvas": {
-                "description": "Impara a comporre immagini utilizzando la tela di controllo di Invoke.",
-                "title": "Creare e comporre sulla tela di controllo di Invoke"
-            },
-            "howDoIGenerateAndSaveToTheGallery": {
-                "description": "Passaggi per generare e salvare le immagini nella galleria.",
-                "title": "Come posso generare e salvare nella Galleria?"
-            },
-            "howDoIEditOnTheCanvas": {
-                "title": "Come posso apportare modifiche sulla tela?",
-                "description": "Guida alla modifica delle immagini direttamente sulla tela."
-            },
-            "howDoIUseControlNetsAndControlLayers": {
-                "title": "Come posso utilizzare le Reti di Controllo e i Livelli di Controllo?",
-                "description": "Impara ad applicare livelli di controllo e reti di controllo alle tue immagini."
-            },
-            "howDoIUseGlobalIPAdaptersAndReferenceImages": {
-                "title": "Come si utilizzano gli adattatori IP globali e le immagini di riferimento?",
-                "description": "Introduzione all'aggiunta di immagini di riferimento e adattatori IP globali."
-            }
-        },
-        "controlCanvas": "Tela di Controllo",
-        "watch": "Guarda",
-        "studioSessionsDesc1": "Dai un'occhiata a <StudioSessionsPlaylistLink /> per approfondimenti su Invoke.",
-        "studioSessionsDesc2": "Unisciti al nostro <DiscordLink /> per partecipare alle sessioni live e fare domande. Le sessioni vengono caricate sulla playlist la settimana successiva."
     }
 }