add missing import

* Update deps to their lastest versions

* missed huggingface_hub

* bump accelerate

---------

Co-authored-by: Lincoln Stein <lincoln.stein@gmail.com>

docs/features/GALLERY.md

@@ -0,0 +1,92 @@
+---
+title: InvokeAI Gallery Panel
+---
+
+# :material-web: InvokeAI Gallery Panel
+
+## Quick guided walkthrough of the Gallery Panel's features
+
+The Gallery Panel is a fast way to review, find, and make use of images you've
+generated and loaded. The Gallery is divided into Boards. The Uncategorized board is always 
+present but you can create your own for better organization.
+
+![image](../assets/gallery/gallery.png)
+
+### Board Display and Settings
+
+At the very top of the Gallery Panel are the boards disclosure and settings buttons.
+
+![image](../assets/gallery/top_controls.png)
+
+The disclosure button shows the name of the currently selected board and allows you to show and hide the board thumbnails (shown in the image below).
+
+![image](../assets/gallery/board_thumbnails.png)
+
+The settings button opens a list of options.
+
+![image](../assets/gallery/board_settings.png)
+
+- ***Image Size*** this slider lets you control the size of the image previews (images of three different sizes).
+- ***Auto-Switch to New Images*** if you turn this on, whenever a new image is generated, it will automatically be loaded into the current image panel on the Text to Image tab and into the result panel on the [Image to Image](IMG2IMG.md) tab. This will happen invisibly if you are on any other tab when the image is generated.
+- ***Auto-Assign Board on Click*** whenever an image is generated or saved, it always gets put in a board. The board it gets put into is marked with AUTO (image of board marked). Turning on Auto-Assign Board on Click will make whichever board you last selected be the destination when you click Invoke. That means you can click Invoke, select a different board, and then click Invoke again and the two images will be put in two different boards. (bold)It's the board selected when Invoke is clicked that's used, not the board that's selected when the image is finished generating.(bold) Turning this off, enables the Auto-Add Board drop down which lets you set one specific board to always put generated images into. This also enables and disables the Auto-add to this Board menu item described below.
+- ***Always Show Image Size Badge*** this toggles whether to show image sizes for each image preview (show two images, one with sizes shown, one without)
+
+Below these two buttons, you'll see the Search Boards text entry area. You use this to search for specific boards by the name of the board.
+Next to it is the Add Board (+) button which lets you add new boards. Boards can be renamed by clicking on the name of the board under its thumbnail and typing in the new name.
+
+### Board Thumbnail Menu
+
+Each board has a context menu (ctrl+click / right-click).
+
+![image](../assets/gallery/thumbnail_menu.png)
+
+- ***Auto-add to this Board*** if you've disabled Auto-Assign Board on Click in the board settings, you can use this option to set this board to be where new images are put.
+- ***Download Board*** this will add all the images in the board into a zip file and provide a link to it in a notification (image of notification)
+- ***Delete Board*** this will delete the board
+> [!CAUTION]
+> This will delete all the images in the board and the board itself.
+
+### Board Contents
+
+Every board is organized by two tabs, Images and Assets.
+
+![image](../assets/gallery/board_tabs.png)
+
+Images are the Invoke-generated images that are placed into the board. Assets are images that you upload into Invoke to be used as an [Image Prompt](https://support.invoke.ai/support/solutions/articles/151000159340-using-the-image-prompt-adapter-ip-adapter-) or in the [Image to Image](IMG2IMG.md) tab.
+
+### Image Thumbnail Menu
+
+Every image generated by Invoke has its generation information stored as text inside the image file itself. This can be read directly by selecting the image and clicking on the Info button ![image](../assets/gallery/info_button.png) in any of the image result panels. 
+
+Each image also has a context menu (ctrl+click / right-click).
+
+![image](../assets/gallery/image_menu.png)
+
+ The options are (items marked with an * will not work with images that lack generation information):
+- ***Open in New Tab*** this will open the image alone in a new browser tab, separate from the Invoke interface.
+- ***Download Image*** this will trigger your browser to download the image.
+- ***Load Workflow **** this will load any workflow settings into the Workflow tab and automatically open it.
+- ***Remix Image **** this will load all of the image's generation information, (bold)excluding its Seed, into the left hand control panel
+- ***Use Prompt **** this will load only the image's text prompts into the left-hand control panel
+- ***Use Seed **** this will load only the image's Seed into the left-hand control panel
+- ***Use All **** this will load all of the image's generation information into the left-hand control panel
+- ***Send to Image to Image*** this will put the image into the left-hand panel in the Image to Image tab ana automatically open it
+- ***Send to Unified Canvas*** This will (bold)replace whatever is already present(bold) in the Unified Canvas tab with the image and automatically open the tab
+- ***Change Board*** this will oipen a small window that will let you move the image to a different board. This is the same as dragging the image to that board's thumbnail.
+- ***Star Image*** this will add the image to the board's list of starred images that are always kept at the top of the gallery. This is the same as clicking on the star on the top right-hand side of the image that appears when you hover over the image with the mouse
+- ***Delete Image*** this will delete the image from the board
+> [!CAUTION] 
+> This will delete the image entirely from Invoke.
+
+## Summary
+
+This walkthrough only covers the Gallery interface and Boards. Actually generating images is handled by [Prompts](PROMPTS.md), the [Image to Image](IMG2IMG.md) tab, and the [Unified Canvas](UNIFIED_CANVAS.md).
+
+## Acknowledgements
+
+A huge shout-out to the core team working to make the Web GUI a reality,
+including [psychedelicious](https://github.com/psychedelicious),
+[Kyle0654](https://github.com/Kyle0654) and
+[blessedcoolant](https://github.com/blessedcoolant).
+[hipsterusername](https://github.com/hipsterusername) was the team's unofficial
+cheerleader and added tooltips/docs.

docs/features/PROMPTS.md

@@ -108,40 +108,6 @@ Can be used with .and():
 Each will give you different results - try them out and see what you prefer!
 
 
-
-### Cross-Attention Control ('prompt2prompt')
-
-Sometimes an image you generate is almost right, and you just want to change one
-detail without affecting the rest. You could use a photo editor and inpainting
-to overpaint the area, but that's a pain. Here's where `prompt2prompt` comes in
-handy.
-
-Generate an image with a given prompt, record the seed of the image, and then
-use the `prompt2prompt` syntax to substitute words in the original prompt for
-words in a new prompt. This works for `img2img` as well.
-
-For example, consider the prompt `a cat.swap(dog) playing with a ball in the forest`. Normally, because the words interact with each other when doing a stable diffusion image generation, these two prompts would generate different compositions:
-  - `a cat playing with a ball in the forest`
-  - `a dog playing with a ball in the forest`
-
-| `a cat playing with a ball in the forest` | `a dog playing with a ball in the forest` |
-| --- | --- |
-| img | img |
-
-
-      - For multiple word swaps, use parentheses: `a (fluffy cat).swap(barking dog) playing with a ball in the forest`.
-      - To swap a comma, use quotes: `a ("fluffy, grey cat").swap("big, barking dog") playing with a ball in the forest`.
-- Supports options `t_start` and `t_end` (each 0-1) loosely corresponding to (bloc97's)[(https://github.com/bloc97/CrossAttentionControl)] `prompt_edit_tokens_start/_end` but with the math swapped to make it easier to
-  intuitively understand. `t_start` and `t_end` are used to control on which steps cross-attention control should run. With the default values `t_start=0` and `t_end=1`, cross-attention control is active on every step of image generation. Other values can be used to turn cross-attention control off for part of the image generation process.
-    - For example, if doing a diffusion with 10 steps for the prompt is `a cat.swap(dog, t_start=0.3, t_end=1.0) playing with a ball in the forest`, the first 3 steps will be run as `a cat playing with a ball in the forest`, while the last 7 steps will run as `a dog playing with a ball in the forest`, but the pixels that represent `dog` will be locked to the pixels that would have represented `cat` if the `cat` prompt had been used instead.
-    - Conversely, for `a cat.swap(dog, t_start=0, t_end=0.7) playing with a ball in the forest`, the first 7 steps will run as `a dog playing with a ball in the forest` with the pixels that represent `dog` locked to the same pixels that would have represented `cat` if the `cat` prompt was being used instead. The final 3 steps will just run `a cat playing with a ball in the forest`.
-    > For img2img, the step sequence does not start at 0 but instead at `(1.0-strength)` - so if the img2img `strength` is `0.7`, `t_start` and `t_end` must both be greater than `0.3` (`1.0-0.7`) to have any effect.
-
-Prompt2prompt `.swap()` is not compatible with xformers, which will be temporarily disabled when doing a `.swap()` - so you should expect to use more VRAM and run slower that with xformers enabled.
-
-The `prompt2prompt` code is based off
-[bloc97's colab](https://github.com/bloc97/CrossAttentionControl).
-
 ### Escaping parentheses and speech marks 
 
 If the model you are using has parentheses () or speech marks "" as part of its

docs/features/WEB.md

@@ -54,7 +54,7 @@ main sections:
    of buttons at the top lets you modify and manipulate the image in
    various ways.
 
-3. A **gallery** section on the left that contains a history of the images you
+3. A **gallery** section on the right that contains a history of the images you
    have generated. These images are read and written to the directory specified
    in the `INVOKEAIROOT/invokeai.yaml` initialization file, usually a directory
    named `outputs` in `INVOKEAIROOT`.

docs/help/FAQ.md

@@ -40,6 +40,25 @@ Follow the same steps to scan and import the missing models.
 - Check the `ram` setting in `invokeai.yaml`. This setting tells Invoke how much of your system RAM can be used to cache models. Having this too high or too low can slow things down. That said, it's generally safest to not set this at all and instead let Invoke manage it.
 - Check the `vram` setting in `invokeai.yaml`. This setting tells Invoke how much of your GPU VRAM can be used to cache models. Counter-intuitively, if this setting is too high, Invoke will need to do a lot of shuffling of models as it juggles the VRAM cache and the currently-loaded model. The default value of 0.25 is generally works well for GPUs without 16GB or more VRAM. Even on a 24GB card, the default works well.
 - Check that your generations are happening on your GPU (if you have one). InvokeAI will log what is being used for generation upon startup. If your GPU isn't used, re-install to ensure the correct versions of torch get installed.
+- If you are on Windows, you may have exceeded your GPU's VRAM capacity and are using slower [shared GPU memory](#shared-gpu-memory-windows). There's a guide to opt out of this behaviour in the linked FAQ entry.
+
+## Shared GPU Memory (Windows)
+
+!!! tip "Nvidia GPUs with driver 536.40"
+
+    This only applies to current Nvidia cards with driver 536.40 or later, released in June 2023.
+
+When the GPU doesn't have enough VRAM for a task, Windows is able to allocate some of its CPU RAM to the GPU. This is much slower than VRAM, but it does allow the system to generate when it otherwise might no have enough VRAM.
+
+When shared GPU memory is used, generation slows down dramatically - but at least it doesn't crash.
+
+If you'd like to opt out of this behavior and instead get an error when you exceed your GPU's VRAM, follow [this guide from Nvidia](https://nvidia.custhelp.com/app/answers/detail/a_id/5490).
+
+Here's how to get the python path required in the linked guide:
+
+- Run `invoke.bat`.
+- Select option 2 for developer console.
+- At least one python path will be printed. Copy the path that includes your invoke installation directory (typically the first).
 
 ## Installer cannot find python (Windows)
 

docs/installation/INSTALL_DEVELOPMENT.md

@@ -23,6 +23,7 @@ If you have an interest in how InvokeAI works, or you would like to add features
 
 1. [Fork and clone] the [InvokeAI repo].
 1. Follow the [manual installation] docs to create a new virtual environment for the development install.
+   - Create a new folder outside the repo root for the installation and create the venv inside that folder.
    - When installing the InvokeAI package, add `-e` to the command so you get an [editable install].
 1. Install the [frontend dev toolchain] and do a production build of the UI as described.
 1. You can now run the app as described in the [manual installation] docs.

invokeai/app/invocations/compel.py

@@ -5,7 +5,15 @@ from compel import Compel, ReturnedEmbeddingsType
 from compel.prompt_parser import Blend, Conjunction, CrossAttentionControlSubstitute, FlattenedPrompt, Fragment
 from transformers import CLIPTextModel, CLIPTextModelWithProjection, CLIPTokenizer
 
-from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIComponent
+from invokeai.app.invocations.fields import (
+    ConditioningField,
+    FieldDescriptions,
+    Input,
+    InputField,
+    OutputField,
+    TensorField,
+    UIComponent,
+)
 from invokeai.app.invocations.primitives import ConditioningOutput
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.ti_utils import generate_ti_list
@@ -14,7 +22,6 @@ from invokeai.backend.model_patcher import ModelPatcher
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     BasicConditioningInfo,
     ConditioningFieldData,
-    ExtraConditioningInfo,
     SDXLConditioningInfo,
 )
 from invokeai.backend.util.devices import torch_dtype
@@ -36,7 +43,7 @@ from .model import CLIPField
     title="Prompt",
     tags=["prompt", "compel"],
     category="conditioning",
-    version="1.1.1",
+    version="1.2.0",
 )
 class CompelInvocation(BaseInvocation):
     """Parse prompt using compel package to conditioning."""
@@ -51,6 +58,9 @@ class CompelInvocation(BaseInvocation):
         description=FieldDescriptions.clip,
         input=Input.Connection,
     )
+    mask: Optional[TensorField] = InputField(
+        default=None, description="A mask defining the region that this conditioning prompt applies to."
+    )
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
@@ -98,27 +108,19 @@ class CompelInvocation(BaseInvocation):
             if context.config.get().log_tokenization:
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
-            c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
-
-            ec = ExtraConditioningInfo(
-                tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
-                cross_attention_control_args=options.get("cross_attention_control", None),
-            )
+            c, _options = compel.build_conditioning_tensor_for_conjunction(conjunction)
 
         c = c.detach().to("cpu")
 
-        conditioning_data = ConditioningFieldData(
-            conditionings=[
-                BasicConditioningInfo(
-                    embeds=c,
-                    extra_conditioning=ec,
-                )
-            ]
-        )
+        conditioning_data = ConditioningFieldData(conditionings=[BasicConditioningInfo(embeds=c)])
 
         conditioning_name = context.conditioning.save(conditioning_data)
-
-        return ConditioningOutput.build(conditioning_name)
+        return ConditioningOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+                mask=self.mask,
+            )
+        )
 
 
 class SDXLPromptInvocationBase:
@@ -132,7 +134,7 @@ class SDXLPromptInvocationBase:
         get_pooled: bool,
         lora_prefix: str,
         zero_on_empty: bool,
-    ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[ExtraConditioningInfo]]:
+    ) -> Tuple[torch.Tensor, Optional[torch.Tensor]]:
         tokenizer_info = context.models.load(clip_field.tokenizer)
         tokenizer_model = tokenizer_info.model
         assert isinstance(tokenizer_model, CLIPTokenizer)
@@ -159,7 +161,7 @@ class SDXLPromptInvocationBase:
                 )
             else:
                 c_pooled = None
-            return c, c_pooled, None
+            return c, c_pooled
 
         def _lora_loader() -> Iterator[Tuple[LoRAModelRaw, float]]:
             for lora in clip_field.loras:
@@ -204,17 +206,12 @@ class SDXLPromptInvocationBase:
                 log_tokenization_for_conjunction(conjunction, tokenizer)
 
             # TODO: ask for optimizations? to not run text_encoder twice
-            c, options = compel.build_conditioning_tensor_for_conjunction(conjunction)
+            c, _options = compel.build_conditioning_tensor_for_conjunction(conjunction)
             if get_pooled:
                 c_pooled = compel.conditioning_provider.get_pooled_embeddings([prompt])
             else:
                 c_pooled = None
 
-            ec = ExtraConditioningInfo(
-                tokens_count_including_eos_bos=get_max_token_count(tokenizer, conjunction),
-                cross_attention_control_args=options.get("cross_attention_control", None),
-            )
-
         del tokenizer
         del text_encoder
         del tokenizer_info
@@ -224,7 +221,7 @@ class SDXLPromptInvocationBase:
         if c_pooled is not None:
             c_pooled = c_pooled.detach().to("cpu")
 
-        return c, c_pooled, ec
+        return c, c_pooled
 
 
 @invocation(
@@ -232,7 +229,7 @@ class SDXLPromptInvocationBase:
     title="SDXL Prompt",
     tags=["sdxl", "compel", "prompt"],
     category="conditioning",
-    version="1.1.1",
+    version="1.2.0",
 )
 class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     """Parse prompt using compel package to conditioning."""
@@ -255,20 +252,19 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
     target_height: int = InputField(default=1024, description="")
     clip: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 1")
     clip2: CLIPField = InputField(description=FieldDescriptions.clip, input=Input.Connection, title="CLIP 2")
+    mask: Optional[TensorField] = InputField(
+        default=None, description="A mask defining the region that this conditioning prompt applies to."
+    )
 
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
-        c1, c1_pooled, ec1 = self.run_clip_compel(
-            context, self.clip, self.prompt, False, "lora_te1_", zero_on_empty=True
-        )
+        c1, c1_pooled = self.run_clip_compel(context, self.clip, self.prompt, False, "lora_te1_", zero_on_empty=True)
         if self.style.strip() == "":
-            c2, c2_pooled, ec2 = self.run_clip_compel(
+            c2, c2_pooled = self.run_clip_compel(
                 context, self.clip2, self.prompt, True, "lora_te2_", zero_on_empty=True
             )
         else:
-            c2, c2_pooled, ec2 = self.run_clip_compel(
-                context, self.clip2, self.style, True, "lora_te2_", zero_on_empty=True
-            )
+            c2, c2_pooled = self.run_clip_compel(context, self.clip2, self.style, True, "lora_te2_", zero_on_empty=True)
 
         original_size = (self.original_height, self.original_width)
         crop_coords = (self.crop_top, self.crop_left)
@@ -307,17 +303,19 @@ class SDXLCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase):
         conditioning_data = ConditioningFieldData(
             conditionings=[
                 SDXLConditioningInfo(
-                    embeds=torch.cat([c1, c2], dim=-1),
-                    pooled_embeds=c2_pooled,
-                    add_time_ids=add_time_ids,
-                    extra_conditioning=ec1,
+                    embeds=torch.cat([c1, c2], dim=-1), pooled_embeds=c2_pooled, add_time_ids=add_time_ids
                 )
             ]
         )
 
         conditioning_name = context.conditioning.save(conditioning_data)
 
-        return ConditioningOutput.build(conditioning_name)
+        return ConditioningOutput(
+            conditioning=ConditioningField(
+                conditioning_name=conditioning_name,
+                mask=self.mask,
+            )
+        )
 
 
 @invocation(
@@ -345,7 +343,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
     @torch.no_grad()
     def invoke(self, context: InvocationContext) -> ConditioningOutput:
         # TODO: if there will appear lora for refiner - write proper prefix
-        c2, c2_pooled, ec2 = self.run_clip_compel(context, self.clip2, self.style, True, "<NONE>", zero_on_empty=False)
+        c2, c2_pooled = self.run_clip_compel(context, self.clip2, self.style, True, "<NONE>", zero_on_empty=False)
 
         original_size = (self.original_height, self.original_width)
         crop_coords = (self.crop_top, self.crop_left)
@@ -354,14 +352,7 @@ class SDXLRefinerCompelPromptInvocation(BaseInvocation, SDXLPromptInvocationBase
 
         assert c2_pooled is not None
         conditioning_data = ConditioningFieldData(
-            conditionings=[
-                SDXLConditioningInfo(
-                    embeds=c2,
-                    pooled_embeds=c2_pooled,
-                    add_time_ids=add_time_ids,
-                    extra_conditioning=ec2,  # or None
-                )
-            ]
+            conditionings=[SDXLConditioningInfo(embeds=c2, pooled_embeds=c2_pooled, add_time_ids=add_time_ids)]
         )
 
         conditioning_name = context.conditioning.save(conditioning_data)

invokeai/app/invocations/fields.py

@@ -203,6 +203,12 @@ class DenoiseMaskField(BaseModel):
     gradient: bool = Field(default=False, description="Used for gradient inpainting")
 
 
+class TensorField(BaseModel):
+    """A tensor primitive field."""
+
+    tensor_name: str = Field(description="The name of a tensor.")
+
+
 class LatentsField(BaseModel):
     """A latents tensor primitive field"""
 
@@ -226,7 +232,11 @@ class ConditioningField(BaseModel):
     """A conditioning tensor primitive value"""
 
     conditioning_name: str = Field(description="The name of conditioning tensor")
-    # endregion
+    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 MetadataField(RootModel[dict[str, Any]]):

invokeai/app/invocations/ip_adapter.py

@@ -1,11 +1,23 @@
 from builtins import float
-from typing import List, Literal, Union
+from typing import List, Literal, Optional, Union
 
 from pydantic import BaseModel, Field, field_validator, model_validator
 from typing_extensions import Self
 
-from invokeai.app.invocations.baseinvocation import BaseInvocation, BaseInvocationOutput, invocation, invocation_output
-from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, OutputField, UIType
+from invokeai.app.invocations.baseinvocation import (
+    BaseInvocation,
+    BaseInvocationOutput,
+    invocation,
+    invocation_output,
+)
+from invokeai.app.invocations.fields import (
+    FieldDescriptions,
+    Input,
+    InputField,
+    OutputField,
+    TensorField,
+    UIType,
+)
 from invokeai.app.invocations.model import ModelIdentifierField
 from invokeai.app.invocations.primitives import ImageField
 from invokeai.app.invocations.util import validate_begin_end_step, validate_weights
@@ -23,13 +35,18 @@ class IPAdapterField(BaseModel):
     image: Union[ImageField, List[ImageField]] = Field(description="The IP-Adapter image prompt(s).")
     ip_adapter_model: ModelIdentifierField = Field(description="The IP-Adapter model to use.")
     image_encoder_model: ModelIdentifierField = Field(description="The name of the CLIP image encoder model.")
-    weight: Union[float, List[float]] = Field(default=1, description="The weight given to the ControlNet")
+    weight: Union[float, List[float]] = Field(default=1, description="The weight given to the IP-Adapter.")
     begin_step_percent: float = Field(
         default=0, ge=0, le=1, description="When the IP-Adapter is first applied (% of total steps)"
     )
     end_step_percent: float = Field(
         default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
     )
+    mask: Optional[TensorField] = Field(
+        default=None,
+        description="The bool mask associated with this IP-Adapter. Excluded regions should be set to False, included "
+        "regions should be set to True.",
+    )
 
     @field_validator("weight")
     @classmethod
@@ -52,7 +69,7 @@ class IPAdapterOutput(BaseInvocationOutput):
 CLIP_VISION_MODEL_MAP = {"ViT-H": "ip_adapter_sd_image_encoder", "ViT-G": "ip_adapter_sdxl_image_encoder"}
 
 
-@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.2.2")
+@invocation("ip_adapter", title="IP-Adapter", tags=["ip_adapter", "control"], category="ip_adapter", version="1.3.0")
 class IPAdapterInvocation(BaseInvocation):
     """Collects IP-Adapter info to pass to other nodes."""
 
@@ -67,7 +84,7 @@ class IPAdapterInvocation(BaseInvocation):
     )
     clip_vision_model: Literal["ViT-H", "ViT-G"] = InputField(
         description="CLIP Vision model to use. Overrides model settings. Mandatory for checkpoint models.",
-        default="auto",
+        default="ViT-H",
         ui_order=2,
     )
     weight: Union[float, List[float]] = InputField(
@@ -79,6 +96,9 @@ class IPAdapterInvocation(BaseInvocation):
     end_step_percent: float = InputField(
         default=1, ge=0, le=1, description="When the IP-Adapter is last applied (% of total steps)"
     )
+    mask: Optional[TensorField] = InputField(
+        default=None, description="A mask defining the region that this IP-Adapter applies to."
+    )
 
     @field_validator("weight")
     @classmethod
@@ -112,6 +132,7 @@ class IPAdapterInvocation(BaseInvocation):
                 weight=self.weight,
                 begin_step_percent=self.begin_step_percent,
                 end_step_percent=self.end_step_percent,
+                mask=self.mask,
             ),
         )
 

invokeai/app/invocations/latent.py

@@ -1,5 +1,5 @@
 # Copyright (c) 2023 Kyle Schouviller (https://github.com/kyle0654)
-
+import inspect
 import math
 from contextlib import ExitStack
 from functools import singledispatchmethod
@@ -9,6 +9,7 @@ import einops
 import numpy as np
 import numpy.typing as npt
 import torch
+import torchvision
 import torchvision.transforms as T
 from diffusers import AutoencoderKL, AutoencoderTiny
 from diffusers.configuration_utils import ConfigMixin
@@ -52,12 +53,20 @@ from invokeai.backend.lora import LoRAModelRaw
 from invokeai.backend.model_manager import BaseModelType, LoadedModel
 from invokeai.backend.model_patcher import ModelPatcher
 from invokeai.backend.stable_diffusion import PipelineIntermediateState, set_seamless
-from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningData, IPAdapterConditioningInfo
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
+    BasicConditioningInfo,
+    IPAdapterConditioningInfo,
+    IPAdapterData,
+    Range,
+    SDXLConditioningInfo,
+    TextConditioningData,
+    TextConditioningRegions,
+)
+from invokeai.backend.util.mask import to_standard_float_mask
 from invokeai.backend.util.silence_warnings import SilenceWarnings
 
 from ...backend.stable_diffusion.diffusers_pipeline import (
     ControlNetData,
-    IPAdapterData,
     StableDiffusionGeneratorPipeline,
     T2IAdapterData,
     image_resized_to_grid_as_tensor,
@@ -275,10 +284,10 @@ def get_scheduler(
 class DenoiseLatentsInvocation(BaseInvocation):
     """Denoises noisy latents to decodable images"""
 
-    positive_conditioning: ConditioningField = InputField(
+    positive_conditioning: Union[ConditioningField, list[ConditioningField]] = InputField(
         description=FieldDescriptions.positive_cond, input=Input.Connection, ui_order=0
     )
-    negative_conditioning: ConditioningField = InputField(
+    negative_conditioning: Union[ConditioningField, list[ConditioningField]] = InputField(
         description=FieldDescriptions.negative_cond, input=Input.Connection, ui_order=1
     )
     noise: Optional[LatentsField] = InputField(
@@ -356,33 +365,168 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 raise ValueError("cfg_scale must be greater than 1")
         return v
 
+    def _get_text_embeddings_and_masks(
+        self,
+        cond_list: list[ConditioningField],
+        context: InvocationContext,
+        device: torch.device,
+        dtype: torch.dtype,
+    ) -> tuple[Union[list[BasicConditioningInfo], list[SDXLConditioningInfo]], list[Optional[torch.Tensor]]]:
+        """Get the text embeddings and masks from the input conditioning fields."""
+        text_embeddings: Union[list[BasicConditioningInfo], list[SDXLConditioningInfo]] = []
+        text_embeddings_masks: list[Optional[torch.Tensor]] = []
+        for cond in cond_list:
+            cond_data = context.conditioning.load(cond.conditioning_name)
+            text_embeddings.append(cond_data.conditionings[0].to(device=device, dtype=dtype))
+
+            mask = cond.mask
+            if mask is not None:
+                mask = context.tensors.load(mask.tensor_name)
+            text_embeddings_masks.append(mask)
+
+        return text_embeddings, text_embeddings_masks
+
+    def _preprocess_regional_prompt_mask(
+        self, mask: Optional[torch.Tensor], target_height: int, target_width: int, dtype: torch.dtype
+    ) -> 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.
+
+        Returns:
+            torch.Tensor: The processed mask. shape: (1, 1, target_height, target_width).
+        """
+
+        if mask is None:
+            return torch.ones((1, 1, target_height, target_width), dtype=dtype)
+
+        mask = to_standard_float_mask(mask, out_dtype=dtype)
+
+        tf = torchvision.transforms.Resize(
+            (target_height, target_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)
+        return resized_mask
+
+    def _concat_regional_text_embeddings(
+        self,
+        text_conditionings: Union[list[BasicConditioningInfo], list[SDXLConditioningInfo]],
+        masks: Optional[list[Optional[torch.Tensor]]],
+        latent_height: int,
+        latent_width: int,
+        dtype: torch.dtype,
+    ) -> tuple[Union[BasicConditioningInfo, SDXLConditioningInfo], Optional[TextConditioningRegions]]:
+        """Concatenate regional text embeddings into a single embedding and track the region masks accordingly."""
+        if masks is None:
+            masks = [None] * len(text_conditionings)
+        assert len(text_conditionings) == len(masks)
+
+        is_sdxl = type(text_conditionings[0]) is SDXLConditioningInfo
+
+        all_masks_are_none = all(mask is None for mask in masks)
+
+        text_embedding = []
+        pooled_embedding = None
+        add_time_ids = None
+        cur_text_embedding_len = 0
+        processed_masks = []
+        embedding_ranges = []
+
+        for prompt_idx, text_embedding_info in enumerate(text_conditionings):
+            mask = masks[prompt_idx]
+
+            if is_sdxl:
+                # We choose a random SDXLConditioningInfo's pooled_embeds and add_time_ids here, with a preference for
+                # prompts without a mask. We prefer prompts without a mask, because they are more likely to contain
+                # global prompt information.  In an ideal case, there should be exactly one global prompt without a
+                # mask, but we don't enforce this.
+
+                # HACK(ryand): The fact that we have to choose a single pooled_embedding and add_time_ids here is a
+                # fundamental interface issue. The SDXL Compel nodes are not designed to be used in the way that we use
+                # them for regional prompting. Ideally, the DenoiseLatents invocation should accept a single
+                # pooled_embeds tensor and a list of standard text embeds with region masks. This change would be a
+                # pretty major breaking change to a popular node, so for now we use this hack.
+                if pooled_embedding is None or mask is None:
+                    pooled_embedding = text_embedding_info.pooled_embeds
+                if add_time_ids is None or mask is None:
+                    add_time_ids = text_embedding_info.add_time_ids
+
+            text_embedding.append(text_embedding_info.embeds)
+            if not all_masks_are_none:
+                embedding_ranges.append(
+                    Range(
+                        start=cur_text_embedding_len, end=cur_text_embedding_len + text_embedding_info.embeds.shape[1]
+                    )
+                )
+                processed_masks.append(
+                    self._preprocess_regional_prompt_mask(mask, latent_height, latent_width, dtype=dtype)
+                )
+
+            cur_text_embedding_len += text_embedding_info.embeds.shape[1]
+
+        text_embedding = torch.cat(text_embedding, dim=1)
+        assert len(text_embedding.shape) == 3  # batch_size, seq_len, token_len
+
+        regions = None
+        if not all_masks_are_none:
+            regions = TextConditioningRegions(
+                masks=torch.cat(processed_masks, dim=1),
+                ranges=embedding_ranges,
+            )
+
+        if is_sdxl:
+            return SDXLConditioningInfo(
+                embeds=text_embedding, pooled_embeds=pooled_embedding, add_time_ids=add_time_ids
+            ), regions
+        return BasicConditioningInfo(embeds=text_embedding), regions
+
     def get_conditioning_data(
         self,
         context: InvocationContext,
-        scheduler: Scheduler,
         unet: UNet2DConditionModel,
-        seed: int,
-    ) -> ConditioningData:
-        positive_cond_data = context.conditioning.load(self.positive_conditioning.conditioning_name)
-        c = positive_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
+        latent_height: int,
+        latent_width: int,
+    ) -> TextConditioningData:
+        # Normalize self.positive_conditioning and self.negative_conditioning to lists.
+        cond_list = self.positive_conditioning
+        if not isinstance(cond_list, list):
+            cond_list = [cond_list]
+        uncond_list = self.negative_conditioning
+        if not isinstance(uncond_list, list):
+            uncond_list = [uncond_list]
 
-        negative_cond_data = context.conditioning.load(self.negative_conditioning.conditioning_name)
-        uc = negative_cond_data.conditionings[0].to(device=unet.device, dtype=unet.dtype)
-
-        conditioning_data = ConditioningData(
-            unconditioned_embeddings=uc,
-            text_embeddings=c,
-            guidance_scale=self.cfg_scale,
-            guidance_rescale_multiplier=self.cfg_rescale_multiplier,
+        cond_text_embeddings, cond_text_embedding_masks = self._get_text_embeddings_and_masks(
+            cond_list, context, unet.device, unet.dtype
+        )
+        uncond_text_embeddings, uncond_text_embedding_masks = self._get_text_embeddings_and_masks(
+            uncond_list, context, unet.device, unet.dtype
         )
 
-        conditioning_data = conditioning_data.add_scheduler_args_if_applicable(  # FIXME
-            scheduler,
-            # for ddim scheduler
-            eta=0.0,  # ddim_eta
-            # for ancestral and sde schedulers
-            # flip all bits to have noise different from initial
-            generator=torch.Generator(device=unet.device).manual_seed(seed ^ 0xFFFFFFFF),
+        cond_text_embedding, cond_regions = self._concat_regional_text_embeddings(
+            text_conditionings=cond_text_embeddings,
+            masks=cond_text_embedding_masks,
+            latent_height=latent_height,
+            latent_width=latent_width,
+            dtype=unet.dtype,
+        )
+        uncond_text_embedding, uncond_regions = self._concat_regional_text_embeddings(
+            text_conditionings=uncond_text_embeddings,
+            masks=uncond_text_embedding_masks,
+            latent_height=latent_height,
+            latent_width=latent_width,
+            dtype=unet.dtype,
+        )
+
+        conditioning_data = TextConditioningData(
+            uncond_text=uncond_text_embedding,
+            cond_text=cond_text_embedding,
+            uncond_regions=uncond_regions,
+            cond_regions=cond_regions,
+            guidance_scale=self.cfg_scale,
+            guidance_rescale_multiplier=self.cfg_rescale_multiplier,
         )
         return conditioning_data
 
@@ -488,8 +632,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
         self,
         context: InvocationContext,
         ip_adapter: Optional[Union[IPAdapterField, list[IPAdapterField]]],
-        conditioning_data: ConditioningData,
         exit_stack: ExitStack,
+        latent_height: int,
+        latent_width: int,
+        dtype: torch.dtype,
     ) -> Optional[list[IPAdapterData]]:
         """If IP-Adapter is enabled, then this function loads the requisite models, and adds the image prompt embeddings
         to the `conditioning_data` (in-place).
@@ -505,7 +651,6 @@ class DenoiseLatentsInvocation(BaseInvocation):
             return None
 
         ip_adapter_data_list = []
-        conditioning_data.ip_adapter_conditioning = []
         for single_ip_adapter in ip_adapter:
             ip_adapter_model: Union[IPAdapter, IPAdapterPlus] = exit_stack.enter_context(
                 context.models.load(single_ip_adapter.ip_adapter_model)
@@ -528,9 +673,10 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     single_ipa_images, image_encoder_model
                 )
 
-                conditioning_data.ip_adapter_conditioning.append(
-                    IPAdapterConditioningInfo(image_prompt_embeds, uncond_image_prompt_embeds)
-                )
+            mask = single_ip_adapter.mask
+            if mask is not None:
+                mask = context.tensors.load(mask.tensor_name)
+            mask = self._preprocess_regional_prompt_mask(mask, latent_height, latent_width, dtype=dtype)
 
             ip_adapter_data_list.append(
                 IPAdapterData(
@@ -538,6 +684,8 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     weight=single_ip_adapter.weight,
                     begin_step_percent=single_ip_adapter.begin_step_percent,
                     end_step_percent=single_ip_adapter.end_step_percent,
+                    ip_adapter_conditioning=IPAdapterConditioningInfo(image_prompt_embeds, uncond_image_prompt_embeds),
+                    mask=mask,
                 )
             )
 
@@ -627,6 +775,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
         steps: int,
         denoising_start: float,
         denoising_end: float,
+        seed: int,
     ) -> Tuple[int, List[int], int]:
         assert isinstance(scheduler, ConfigMixin)
         if scheduler.config.get("cpu_only", False):
@@ -655,7 +804,15 @@ class DenoiseLatentsInvocation(BaseInvocation):
         timesteps = timesteps[t_start_idx : t_start_idx + t_end_idx]
         num_inference_steps = len(timesteps) // scheduler.order
 
-        return num_inference_steps, timesteps, init_timestep
+        scheduler_step_kwargs = {}
+        scheduler_step_signature = inspect.signature(scheduler.step)
+        if "generator" in scheduler_step_signature.parameters:
+            # At some point, someone decided that schedulers that accept a generator should use the original seed with
+            # all bits flipped. I don't know the original rationale for this, but now we must keep it like this for
+            # reproducibility.
+            scheduler_step_kwargs = {"generator": torch.Generator(device=device).manual_seed(seed ^ 0xFFFFFFFF)}
+
+        return num_inference_steps, timesteps, init_timestep, scheduler_step_kwargs
 
     def prep_inpaint_mask(
         self, context: InvocationContext, latents: torch.Tensor
@@ -749,7 +906,11 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 )
 
                 pipeline = self.create_pipeline(unet, scheduler)
-                conditioning_data = self.get_conditioning_data(context, scheduler, unet, seed)
+
+                _, _, latent_height, latent_width = latents.shape
+                conditioning_data = self.get_conditioning_data(
+                    context=context, unet=unet, latent_height=latent_height, latent_width=latent_width
+                )
 
                 controlnet_data = self.prep_control_data(
                     context=context,
@@ -763,16 +924,19 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 ip_adapter_data = self.prep_ip_adapter_data(
                     context=context,
                     ip_adapter=self.ip_adapter,
-                    conditioning_data=conditioning_data,
                     exit_stack=exit_stack,
+                    latent_height=latent_height,
+                    latent_width=latent_width,
+                    dtype=unet.dtype,
                 )
 
-                num_inference_steps, timesteps, init_timestep = self.init_scheduler(
+                num_inference_steps, timesteps, init_timestep, scheduler_step_kwargs = self.init_scheduler(
                     scheduler,
                     device=unet.device,
                     steps=self.steps,
                     denoising_start=self.denoising_start,
                     denoising_end=self.denoising_end,
+                    seed=seed,
                 )
 
                 result_latents = pipeline.latents_from_embeddings(
@@ -785,6 +949,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                     masked_latents=masked_latents,
                     gradient_mask=gradient_mask,
                     num_inference_steps=num_inference_steps,
+                    scheduler_step_kwargs=scheduler_step_kwargs,
                     conditioning_data=conditioning_data,
                     control_data=controlnet_data,
                     ip_adapter_data=ip_adapter_data,
@@ -799,7 +964,7 @@ class DenoiseLatentsInvocation(BaseInvocation):
                 mps.empty_cache()
 
             name = context.tensors.save(tensor=result_latents)
-        return LatentsOutput.build(latents_name=name, latents=result_latents, seed=seed)
+        return LatentsOutput.build(latents_name=name, latents=result_latents, seed=None)
 
 
 @invocation(

invokeai/app/invocations/mask.py

@@ -0,0 +1,36 @@
+import torch
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, InvocationContext, invocation
+from invokeai.app.invocations.fields import InputField, TensorField, WithMetadata
+from invokeai.app.invocations.primitives import MaskOutput
+
+
+@invocation(
+    "rectangle_mask",
+    title="Create Rectangle Mask",
+    tags=["conditioning"],
+    category="conditioning",
+    version="1.0.1",
+)
+class RectangleMaskInvocation(BaseInvocation, WithMetadata):
+    """Create a rectangular mask."""
+
+    width: int = InputField(description="The width of the entire mask.")
+    height: int = InputField(description="The height of the entire mask.")
+    x_left: int = InputField(description="The left x-coordinate of the rectangular masked region (inclusive).")
+    y_top: int = InputField(description="The top y-coordinate of the rectangular masked region (inclusive).")
+    rectangle_width: int = InputField(description="The width of the rectangular masked region.")
+    rectangle_height: int = InputField(description="The height of the rectangular masked region.")
+
+    def invoke(self, context: InvocationContext) -> MaskOutput:
+        mask = torch.zeros((1, self.height, self.width), dtype=torch.bool)
+        mask[:, self.y_top : self.y_top + self.rectangle_height, self.x_left : self.x_left + self.rectangle_width] = (
+            True
+        )
+
+        mask_tensor_name = context.tensors.save(mask)
+        return MaskOutput(
+            mask=TensorField(tensor_name=mask_tensor_name),
+            width=self.width,
+            height=self.height,
+        )

invokeai/app/invocations/primitives.py

@@ -15,6 +15,7 @@ from invokeai.app.invocations.fields import (
     InputField,
     LatentsField,
     OutputField,
+    TensorField,
     UIComponent,
 )
 from invokeai.app.services.images.images_common import ImageDTO
@@ -405,9 +406,19 @@ class ColorInvocation(BaseInvocation):
 
 # endregion
 
+
 # region Conditioning
 
 
+@invocation_output("mask_output")
+class MaskOutput(BaseInvocationOutput):
+    """A torch mask tensor."""
+
+    mask: TensorField = OutputField(description="The mask.")
+    width: int = OutputField(description="The width of the mask in pixels.")
+    height: int = OutputField(description="The height of the mask in pixels.")
+
+
 @invocation_output("conditioning_output")
 class ConditioningOutput(BaseInvocationOutput):
     """Base class for nodes that output a single conditioning tensor"""

invokeai/app/services/download/download_default.py

@@ -270,7 +270,7 @@ class DownloadQueueService(DownloadQueueServiceBase):
             job.dest.parent.mkdir(parents=True, exist_ok=True)
             job.download_path = job.dest
 
-        assert job.download_path
+        assert job.download_path is not None
 
         # Don't clobber an existing file. See commit 82c2c85202f88c6d24ff84710f297cfc6ae174af
         # for code that instead resumes an interrupted download.
@@ -280,6 +280,9 @@ class DownloadQueueService(DownloadQueueServiceBase):
         # append ".downloading" to the path
         in_progress_path = self._in_progress_path(job.download_path)
 
+        # catch rare race condition that is appearing in unit tests.
+        assert in_progress_path.parent.exists(), f"Directory doesn't exist! in_progress_path={in_progress_path}; parent={in_progress_path.parent}"
+
         # signal caller that the download is starting. At this point, key fields such as
         # download_path and total_bytes will be populated. We call it here because the might
         # discover that the local file is already complete and generate a COMPLETED status.

invokeai/app/services/session_processor/session_processor_default.py

@@ -86,6 +86,12 @@ class DefaultSessionProcessor(SessionProcessorBase):
             self._poll_now()
         elif event_name == "batch_enqueued":
             self._poll_now()
+        elif event_name == "queue_item_status_changed" and event[1]["data"]["queue_item"]["status"] in [
+            "completed",
+            "failed",
+            "canceled",
+        ]:
+            self._poll_now()
 
     def resume(self) -> SessionProcessorStatus:
         if not self._resume_event.is_set():

invokeai/app/services/shared/invocation_context.py

@@ -245,6 +245,18 @@ class ImagesInterface(InvocationContextInterface):
         """
         return self._services.images.get_dto(image_name)
 
+    def get_path(self, image_name: str, thumbnail: bool = False) -> Path:
+        """Gets the internal path to an image or thumbnail.
+
+        Args:
+            image_name: The name of the image to get the path of.
+            thumbnail: Get the path of the thumbnail instead of the full image
+
+        Returns:
+            The local path of the image or thumbnail.
+        """
+        return self._services.images.get_path(image_name, thumbnail)
+
 
 class TensorsInterface(InvocationContextInterface):
     def save(self, tensor: Tensor) -> str:

invokeai/backend/ip_adapter/attention_processor.py

@@ -1,182 +0,0 @@
-# copied from https://github.com/tencent-ailab/IP-Adapter (Apache License 2.0)
-#   and modified as needed
-
-# tencent-ailab comment:
-# modified from https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-from diffusers.models.attention_processor import AttnProcessor2_0 as DiffusersAttnProcessor2_0
-
-from invokeai.backend.ip_adapter.ip_attention_weights import IPAttentionProcessorWeights
-
-
-# Create a version of AttnProcessor2_0 that is a sub-class of nn.Module. This is required for IP-Adapter state_dict
-# loading.
-class AttnProcessor2_0(DiffusersAttnProcessor2_0, nn.Module):
-    def __init__(self):
-        DiffusersAttnProcessor2_0.__init__(self)
-        nn.Module.__init__(self)
-
-    def __call__(
-        self,
-        attn,
-        hidden_states,
-        encoder_hidden_states=None,
-        attention_mask=None,
-        temb=None,
-        ip_adapter_image_prompt_embeds=None,
-    ):
-        """Re-definition of DiffusersAttnProcessor2_0.__call__(...) that accepts and ignores the
-        ip_adapter_image_prompt_embeds parameter.
-        """
-        return DiffusersAttnProcessor2_0.__call__(
-            self, attn, hidden_states, encoder_hidden_states, attention_mask, temb
-        )
-
-
-class IPAttnProcessor2_0(torch.nn.Module):
-    r"""
-    Attention processor for IP-Adapater for PyTorch 2.0.
-    Args:
-        hidden_size (`int`):
-            The hidden size of the attention layer.
-        cross_attention_dim (`int`):
-            The number of channels in the `encoder_hidden_states`.
-        scale (`float`, defaults to 1.0):
-            the weight scale of image prompt.
-    """
-
-    def __init__(self, weights: list[IPAttentionProcessorWeights], scales: list[float]):
-        super().__init__()
-
-        if not hasattr(F, "scaled_dot_product_attention"):
-            raise ImportError("AttnProcessor2_0 requires PyTorch 2.0, to use it, please upgrade PyTorch to 2.0.")
-
-        assert len(weights) == len(scales)
-
-        self._weights = weights
-        self._scales = scales
-
-    def __call__(
-        self,
-        attn,
-        hidden_states,
-        encoder_hidden_states=None,
-        attention_mask=None,
-        temb=None,
-        ip_adapter_image_prompt_embeds=None,
-    ):
-        """Apply IP-Adapter attention.
-
-        Args:
-            ip_adapter_image_prompt_embeds (torch.Tensor): The image prompt embeddings.
-                Shape: (batch_size, num_ip_images, seq_len, ip_embedding_len).
-        """
-        residual = hidden_states
-
-        if attn.spatial_norm is not None:
-            hidden_states = attn.spatial_norm(hidden_states, temb)
-
-        input_ndim = hidden_states.ndim
-
-        if input_ndim == 4:
-            batch_size, channel, height, width = hidden_states.shape
-            hidden_states = hidden_states.view(batch_size, channel, height * width).transpose(1, 2)
-
-        batch_size, sequence_length, _ = (
-            hidden_states.shape if encoder_hidden_states is None else encoder_hidden_states.shape
-        )
-
-        if attention_mask is not None:
-            attention_mask = attn.prepare_attention_mask(attention_mask, sequence_length, batch_size)
-            # scaled_dot_product_attention expects attention_mask shape to be
-            # (batch, heads, source_length, target_length)
-            attention_mask = attention_mask.view(batch_size, attn.heads, -1, attention_mask.shape[-1])
-
-        if attn.group_norm is not None:
-            hidden_states = attn.group_norm(hidden_states.transpose(1, 2)).transpose(1, 2)
-
-        query = attn.to_q(hidden_states)
-
-        if encoder_hidden_states is None:
-            encoder_hidden_states = hidden_states
-        elif attn.norm_cross:
-            encoder_hidden_states = attn.norm_encoder_hidden_states(encoder_hidden_states)
-
-        key = attn.to_k(encoder_hidden_states)
-        value = attn.to_v(encoder_hidden_states)
-
-        inner_dim = key.shape[-1]
-        head_dim = inner_dim // attn.heads
-
-        query = query.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
-
-        key = key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
-        value = value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
-
-        # the output of sdp = (batch, num_heads, seq_len, head_dim)
-        # TODO: add support for attn.scale when we move to Torch 2.1
-        hidden_states = F.scaled_dot_product_attention(
-            query, key, value, attn_mask=attention_mask, dropout_p=0.0, is_causal=False
-        )
-
-        hidden_states = hidden_states.transpose(1, 2).reshape(batch_size, -1, attn.heads * head_dim)
-        hidden_states = hidden_states.to(query.dtype)
-
-        if encoder_hidden_states is not None:
-            # If encoder_hidden_states is not None, then we are doing cross-attention, not self-attention. In this case,
-            # we will apply IP-Adapter conditioning. We validate the inputs for IP-Adapter conditioning here.
-            assert ip_adapter_image_prompt_embeds is not None
-            assert len(ip_adapter_image_prompt_embeds) == len(self._weights)
-
-            for ipa_embed, ipa_weights, scale in zip(
-                ip_adapter_image_prompt_embeds, self._weights, self._scales, strict=True
-            ):
-                # The batch dimensions should match.
-                assert ipa_embed.shape[0] == encoder_hidden_states.shape[0]
-                # The token_len dimensions should match.
-                assert ipa_embed.shape[-1] == encoder_hidden_states.shape[-1]
-
-                ip_hidden_states = ipa_embed
-
-                # Expected ip_hidden_state shape: (batch_size, num_ip_images, ip_seq_len, ip_image_embedding)
-
-                ip_key = ipa_weights.to_k_ip(ip_hidden_states)
-                ip_value = ipa_weights.to_v_ip(ip_hidden_states)
-
-                # Expected ip_key and ip_value shape: (batch_size, num_ip_images, ip_seq_len, head_dim * num_heads)
-
-                ip_key = ip_key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
-                ip_value = ip_value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
-
-                # Expected ip_key and ip_value shape: (batch_size, num_heads, num_ip_images * ip_seq_len, head_dim)
-
-                # TODO: add support for attn.scale when we move to Torch 2.1
-                ip_hidden_states = F.scaled_dot_product_attention(
-                    query, ip_key, ip_value, attn_mask=None, dropout_p=0.0, is_causal=False
-                )
-
-                # Expected ip_hidden_states shape: (batch_size, num_heads, query_seq_len, head_dim)
-
-                ip_hidden_states = ip_hidden_states.transpose(1, 2).reshape(batch_size, -1, attn.heads * head_dim)
-                ip_hidden_states = ip_hidden_states.to(query.dtype)
-
-                # Expected ip_hidden_states shape: (batch_size, query_seq_len, num_heads * head_dim)
-
-                hidden_states = hidden_states + scale * ip_hidden_states
-
-        # linear proj
-        hidden_states = attn.to_out[0](hidden_states)
-        # dropout
-        hidden_states = attn.to_out[1](hidden_states)
-
-        if input_ndim == 4:
-            hidden_states = hidden_states.transpose(-1, -2).reshape(batch_size, channel, height, width)
-
-        if attn.residual_connection:
-            hidden_states = hidden_states + residual
-
-        hidden_states = hidden_states / attn.rescale_output_factor
-
-        return hidden_states

invokeai/backend/model_manager/load/load_default.py

@@ -37,7 +37,7 @@ class ModelLoader(ModelLoaderBase):
         self._logger = logger
         self._ram_cache = ram_cache
         self._convert_cache = convert_cache
-        self._torch_dtype = torch_dtype(choose_torch_device(), app_config)
+        self._torch_dtype = torch_dtype(choose_torch_device())
 
     def load_model(self, model_config: AnyModelConfig, submodel_type: Optional[SubModelType] = None) -> LoadedModel:
         """

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

@@ -117,7 +117,7 @@ class ModelCacheBase(ABC, Generic[T]):
 
     @property
     @abstractmethod
-    def stats(self) -> CacheStats:
+    def stats(self) -> Optional[CacheStats]:
         """Return collected CacheStats object."""
         pass
 

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

@@ -269,12 +269,14 @@ class ModelCache(ModelCacheBase[AnyModel]):
         if torch.device(source_device).type == torch.device(target_device).type:
             return
 
-        # may raise an exception here if insufficient GPU VRAM
-        self._check_free_vram(target_device, cache_entry.size)
-
         start_model_to_time = time.time()
         snapshot_before = self._capture_memory_snapshot()
-        cache_entry.model.to(target_device)
+        try:
+            cache_entry.model.to(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(
@@ -329,11 +331,11 @@ class ModelCache(ModelCacheBase[AnyModel]):
                     f" {in_ram_models}/{in_vram_models}({locked_in_vram_models})"
                 )
 
-    def make_room(self, model_size: int) -> None:
+    def make_room(self, size: int) -> None:
         """Make enough room in the cache to accommodate a new model of indicated size."""
         # calculate how much memory this model will require
         # multiplier = 2 if self.precision==torch.float32 else 1
-        bytes_needed = model_size
+        bytes_needed = size
         maximum_size = self.max_cache_size * GIG  # stored in GB, convert to bytes
         current_size = self.cache_size()
 
@@ -388,12 +390,11 @@ class ModelCache(ModelCacheBase[AnyModel]):
             # 1 from onnx runtime object
             if not cache_entry.locked and refs <= (3 if "onnx" in model_key else 2):
                 self.logger.debug(
-                    f"Removing {model_key} from RAM cache to free at least {(model_size/GIG):.2f} GB (-{(cache_entry.size/GIG):.2f} GB)"
+                    f"Removing {model_key} from RAM cache to free at least {(size/GIG):.2f} GB (-{(cache_entry.size/GIG):.2f} GB)"
                 )
                 current_size -= cache_entry.size
                 models_cleared += 1
-                del self._cache_stack[pos]
-                del self._cached_models[model_key]
+                self._delete_cache_entry(cache_entry)
                 del cache_entry
 
             else:
@@ -421,23 +422,6 @@ class ModelCache(ModelCacheBase[AnyModel]):
 
         self.logger.debug(f"After making room: cached_models={len(self._cached_models)}")
 
-    def _free_vram(self, device: torch.device) -> int:
-        vram_device = (  # mem_get_info() needs an indexed device
-            device if device.index is not None else torch.device(str(device), index=0)
-        )
-        free_mem, _ = torch.cuda.mem_get_info(vram_device)
-        for _, cache_entry in self._cached_models.items():
-            if cache_entry.loaded and not cache_entry.locked:
-                free_mem += cache_entry.size
-        return free_mem
-
-    def _check_free_vram(self, target_device: torch.device, needed_size: int) -> None:
-        if target_device.type != "cuda":
-            return
-        free_mem = self._free_vram(target_device)
-        if needed_size > free_mem:
-            needed_gb = round(needed_size / GIG, 2)
-            free_gb = round(free_mem / GIG, 2)
-            raise torch.cuda.OutOfMemoryError(
-                f"Insufficient VRAM to load model, requested {needed_gb}GB but only had {free_gb}GB free"
-            )
+    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/stable_diffusion/diffusers_pipeline.py

@@ -21,10 +21,12 @@ from pydantic import Field
 from transformers import CLIPFeatureExtractor, CLIPTextModel, CLIPTokenizer
 
 from invokeai.app.services.config.config_default import get_config
-from invokeai.backend.ip_adapter.ip_adapter import IPAdapter
-from invokeai.backend.ip_adapter.unet_patcher import UNetPatcher
-from invokeai.backend.stable_diffusion.diffusion.conditioning_data import ConditioningData
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
+    IPAdapterData,
+    TextConditioningData,
+)
 from invokeai.backend.stable_diffusion.diffusion.shared_invokeai_diffusion import InvokeAIDiffuserComponent
+from invokeai.backend.stable_diffusion.diffusion.unet_attention_patcher import UNetAttentionPatcher
 from invokeai.backend.util.attention import auto_detect_slice_size
 from invokeai.backend.util.devices import normalize_device
 
@@ -149,16 +151,6 @@ class ControlNetData:
     resize_mode: str = Field(default="just_resize")
 
 
-@dataclass
-class IPAdapterData:
-    ip_adapter_model: IPAdapter = Field(default=None)
-    # TODO: change to polymorphic so can do different weights per step (once implemented...)
-    weight: Union[float, List[float]] = Field(default=1.0)
-    # weight: float = Field(default=1.0)
-    begin_step_percent: float = Field(default=0.0)
-    end_step_percent: float = Field(default=1.0)
-
-
 @dataclass
 class T2IAdapterData:
     """A structure containing the information required to apply conditioning from a single T2I-Adapter model."""
@@ -295,7 +287,8 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         self,
         latents: torch.Tensor,
         num_inference_steps: int,
-        conditioning_data: ConditioningData,
+        scheduler_step_kwargs: dict[str, Any],
+        conditioning_data: TextConditioningData,
         *,
         noise: Optional[torch.Tensor],
         timesteps: torch.Tensor,
@@ -308,7 +301,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         mask: Optional[torch.Tensor] = None,
         masked_latents: Optional[torch.Tensor] = None,
         gradient_mask: Optional[bool] = False,
-        seed: Optional[int] = None,
+        seed: int,
     ) -> torch.Tensor:
         if init_timestep.shape[0] == 0:
             return latents
@@ -326,20 +319,6 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
             latents = self.scheduler.add_noise(latents, noise, batched_t)
 
         if mask is not None:
-            # if no noise provided, noisify unmasked area based on seed(or 0 as fallback)
-            if noise is None:
-                noise = torch.randn(
-                    orig_latents.shape,
-                    dtype=torch.float32,
-                    device="cpu",
-                    generator=torch.Generator(device="cpu").manual_seed(seed or 0),
-                ).to(device=orig_latents.device, dtype=orig_latents.dtype)
-
-                latents = self.scheduler.add_noise(latents, noise, batched_t)
-                latents = torch.lerp(
-                    orig_latents, latents.to(dtype=orig_latents.dtype), mask.to(dtype=orig_latents.dtype)
-                )
-
             if is_inpainting_model(self.unet):
                 if masked_latents is None:
                     raise Exception("Source image required for inpaint mask when inpaint model used!")
@@ -348,6 +327,15 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
                     self._unet_forward, mask, masked_latents
                 )
             else:
+                # if no noise provided, noisify unmasked area based on seed
+                if noise is None:
+                    noise = torch.randn(
+                        orig_latents.shape,
+                        dtype=torch.float32,
+                        device="cpu",
+                        generator=torch.Generator(device="cpu").manual_seed(seed),
+                    ).to(device=orig_latents.device, dtype=orig_latents.dtype)
+
                 additional_guidance.append(AddsMaskGuidance(mask, orig_latents, self.scheduler, noise, gradient_mask))
 
         try:
@@ -355,6 +343,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
                 latents,
                 timesteps,
                 conditioning_data,
+                scheduler_step_kwargs=scheduler_step_kwargs,
                 additional_guidance=additional_guidance,
                 control_data=control_data,
                 ip_adapter_data=ip_adapter_data,
@@ -380,7 +369,8 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         self,
         latents: torch.Tensor,
         timesteps,
-        conditioning_data: ConditioningData,
+        conditioning_data: TextConditioningData,
+        scheduler_step_kwargs: dict[str, Any],
         *,
         additional_guidance: List[Callable] = None,
         control_data: List[ControlNetData] = None,
@@ -397,22 +387,17 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         if timesteps.shape[0] == 0:
             return latents
 
-        ip_adapter_unet_patcher = None
-        extra_conditioning_info = conditioning_data.text_embeddings.extra_conditioning
-        if extra_conditioning_info is not None and extra_conditioning_info.wants_cross_attention_control:
-            attn_ctx = self.invokeai_diffuser.custom_attention_context(
-                self.invokeai_diffuser.model,
-                extra_conditioning_info=extra_conditioning_info,
-            )
-            self.use_ip_adapter = False
-        elif ip_adapter_data is not None:
-            # TODO(ryand): Should we raise an exception if both custom attention and IP-Adapter attention are active?
-            # As it is now, the IP-Adapter will silently be skipped.
-            ip_adapter_unet_patcher = UNetPatcher([ipa.ip_adapter_model for ipa in ip_adapter_data])
-            attn_ctx = ip_adapter_unet_patcher.apply_ip_adapter_attention(self.invokeai_diffuser.model)
-            self.use_ip_adapter = True
-        else:
-            attn_ctx = nullcontext()
+        use_ip_adapter = ip_adapter_data is not None
+        use_regional_prompting = (
+            conditioning_data.cond_regions is not None or conditioning_data.uncond_regions is not None
+        )
+        unet_attention_patcher = None
+        self.use_ip_adapter = use_ip_adapter
+        attn_ctx = nullcontext()
+        if use_ip_adapter or use_regional_prompting:
+            ip_adapters = [ipa.ip_adapter_model for ipa in ip_adapter_data] if use_ip_adapter else None
+            unet_attention_patcher = UNetAttentionPatcher(ip_adapters)
+            attn_ctx = unet_attention_patcher.apply_ip_adapter_attention(self.invokeai_diffuser.model)
 
         with attn_ctx:
             if callback is not None:
@@ -435,11 +420,11 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
                     conditioning_data,
                     step_index=i,
                     total_step_count=len(timesteps),
+                    scheduler_step_kwargs=scheduler_step_kwargs,
                     additional_guidance=additional_guidance,
                     control_data=control_data,
                     ip_adapter_data=ip_adapter_data,
                     t2i_adapter_data=t2i_adapter_data,
-                    ip_adapter_unet_patcher=ip_adapter_unet_patcher,
                 )
                 latents = step_output.prev_sample
                 predicted_original = getattr(step_output, "pred_original_sample", None)
@@ -463,14 +448,14 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         self,
         t: torch.Tensor,
         latents: torch.Tensor,
-        conditioning_data: ConditioningData,
+        conditioning_data: TextConditioningData,
         step_index: int,
         total_step_count: int,
+        scheduler_step_kwargs: dict[str, Any],
         additional_guidance: List[Callable] = None,
         control_data: List[ControlNetData] = None,
         ip_adapter_data: Optional[list[IPAdapterData]] = None,
         t2i_adapter_data: Optional[list[T2IAdapterData]] = None,
-        ip_adapter_unet_patcher: Optional[UNetPatcher] = None,
     ):
         # invokeai_diffuser has batched timesteps, but diffusers schedulers expect a single value
         timestep = t[0]
@@ -485,23 +470,6 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
         #     i.e. before or after passing it to InvokeAIDiffuserComponent
         latent_model_input = self.scheduler.scale_model_input(latents, timestep)
 
-        # handle IP-Adapter
-        if self.use_ip_adapter and ip_adapter_data is not None:  # somewhat redundant but logic is clearer
-            for i, single_ip_adapter_data in enumerate(ip_adapter_data):
-                first_adapter_step = math.floor(single_ip_adapter_data.begin_step_percent * total_step_count)
-                last_adapter_step = math.ceil(single_ip_adapter_data.end_step_percent * total_step_count)
-                weight = (
-                    single_ip_adapter_data.weight[step_index]
-                    if isinstance(single_ip_adapter_data.weight, List)
-                    else single_ip_adapter_data.weight
-                )
-                if step_index >= first_adapter_step and step_index <= last_adapter_step:
-                    # Only apply this IP-Adapter if the current step is within the IP-Adapter's begin/end step range.
-                    ip_adapter_unet_patcher.set_scale(i, weight)
-                else:
-                    # Otherwise, set the IP-Adapter's scale to 0, so it has no effect.
-                    ip_adapter_unet_patcher.set_scale(i, 0.0)
-
         # Handle ControlNet(s)
         down_block_additional_residuals = None
         mid_block_additional_residual = None
@@ -550,6 +518,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
             step_index=step_index,
             total_step_count=total_step_count,
             conditioning_data=conditioning_data,
+            ip_adapter_data=ip_adapter_data,
             down_block_additional_residuals=down_block_additional_residuals,  # for ControlNet
             mid_block_additional_residual=mid_block_additional_residual,  # for ControlNet
             down_intrablock_additional_residuals=down_intrablock_additional_residuals,  # for T2I-Adapter
@@ -569,7 +538,7 @@ class StableDiffusionGeneratorPipeline(StableDiffusionPipeline):
             )
 
         # compute the previous noisy sample x_t -> x_t-1
-        step_output = self.scheduler.step(noise_pred, timestep, latents, **conditioning_data.scheduler_args)
+        step_output = self.scheduler.step(noise_pred, timestep, latents, **scheduler_step_kwargs)
 
         # TODO: discuss injection point options. For now this is a patch to get progress images working with inpainting again.
         for guidance in additional_guidance:

invokeai/backend/stable_diffusion/diffusion/conditioning_data.py

@@ -1,27 +1,17 @@
-import dataclasses
-import inspect
-from dataclasses import dataclass, field
-from typing import Any, List, Optional, Union
+import math
+from dataclasses import dataclass
+from typing import List, Optional, Union
 
 import torch
 
-from .cross_attention_control import Arguments
-
-
-@dataclass
-class ExtraConditioningInfo:
-    tokens_count_including_eos_bos: int
-    cross_attention_control_args: Optional[Arguments] = None
-
-    @property
-    def wants_cross_attention_control(self):
-        return self.cross_attention_control_args is not None
+from invokeai.backend.ip_adapter.ip_adapter import IPAdapter
 
 
 @dataclass
 class BasicConditioningInfo:
+    """SD 1/2 text conditioning information produced by Compel."""
+
     embeds: torch.Tensor
-    extra_conditioning: Optional[ExtraConditioningInfo]
 
     def to(self, device, dtype=None):
         self.embeds = self.embeds.to(device=device, dtype=dtype)
@@ -35,6 +25,8 @@ class ConditioningFieldData:
 
 @dataclass
 class SDXLConditioningInfo(BasicConditioningInfo):
+    """SDXL text conditioning information produced by Compel."""
+
     pooled_embeds: torch.Tensor
     add_time_ids: torch.Tensor
 
@@ -57,37 +49,74 @@ class IPAdapterConditioningInfo:
 
 
 @dataclass
-class ConditioningData:
-    unconditioned_embeddings: BasicConditioningInfo
-    text_embeddings: BasicConditioningInfo
-    """
-    Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
-    `guidance_scale` is defined as `w` of equation 2. of [Imagen Paper](https://arxiv.org/pdf/2205.11487.pdf).
-    Guidance scale is enabled by setting `guidance_scale > 1`. Higher guidance scale encourages to generate
-    images that are closely linked to the text `prompt`, usually at the expense of lower image quality.
-    """
-    guidance_scale: Union[float, List[float]]
-    """ for models trained using zero-terminal SNR ("ztsnr"), it's suggested to use guidance_rescale_multiplier of 0.7 .
-     ref [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf)
-    """
-    guidance_rescale_multiplier: float = 0
-    scheduler_args: dict[str, Any] = field(default_factory=dict)
+class IPAdapterData:
+    ip_adapter_model: IPAdapter
+    ip_adapter_conditioning: IPAdapterConditioningInfo
+    mask: torch.Tensor
 
-    ip_adapter_conditioning: Optional[list[IPAdapterConditioningInfo]] = None
+    # Either a single weight applied to all steps, or a list of weights for each step.
+    weight: Union[float, List[float]] = 1.0
+    begin_step_percent: float = 0.0
+    end_step_percent: float = 1.0
 
-    @property
-    def dtype(self):
-        return self.text_embeddings.dtype
+    def scale_for_step(self, step_index: int, total_steps: int) -> float:
+        first_adapter_step = math.floor(self.begin_step_percent * total_steps)
+        last_adapter_step = math.ceil(self.end_step_percent * total_steps)
+        weight = self.weight[step_index] if isinstance(self.weight, List) else self.weight
+        if step_index >= first_adapter_step and step_index <= last_adapter_step:
+            # Only apply this IP-Adapter if the current step is within the IP-Adapter's begin/end step range.
+            return weight
+        # Otherwise, set the IP-Adapter's scale to 0, so it has no effect.
+        return 0.0
 
-    def add_scheduler_args_if_applicable(self, scheduler, **kwargs):
-        scheduler_args = dict(self.scheduler_args)
-        step_method = inspect.signature(scheduler.step)
-        for name, value in kwargs.items():
-            try:
-                step_method.bind_partial(**{name: value})
-            except TypeError:
-                # FIXME: don't silently discard arguments
-                pass  # debug("%s does not accept argument named %r", scheduler, name)
-            else:
-                scheduler_args[name] = value
-        return dataclasses.replace(self, scheduler_args=scheduler_args)
+
+@dataclass
+class Range:
+    start: int
+    end: int
+
+
+class TextConditioningRegions:
+    def __init__(
+        self,
+        masks: torch.Tensor,
+        ranges: list[Range],
+    ):
+        # A binary mask indicating the regions of the image that the prompt should be applied to.
+        # Shape: (1, num_prompts, height, width)
+        # Dtype: torch.bool
+        self.masks = masks
+
+        # A list of ranges indicating the start and end indices of the embeddings that corresponding mask applies to.
+        # ranges[i] contains the embedding range for the i'th prompt / mask.
+        self.ranges = ranges
+
+        assert self.masks.shape[1] == len(self.ranges)
+
+
+class TextConditioningData:
+    def __init__(
+        self,
+        uncond_text: Union[BasicConditioningInfo, SDXLConditioningInfo],
+        cond_text: Union[BasicConditioningInfo, SDXLConditioningInfo],
+        uncond_regions: Optional[TextConditioningRegions],
+        cond_regions: Optional[TextConditioningRegions],
+        guidance_scale: Union[float, List[float]],
+        guidance_rescale_multiplier: float = 0,
+    ):
+        self.uncond_text = uncond_text
+        self.cond_text = cond_text
+        self.uncond_regions = uncond_regions
+        self.cond_regions = cond_regions
+        # Guidance scale as defined in [Classifier-Free Diffusion Guidance](https://arxiv.org/abs/2207.12598).
+        # `guidance_scale` is defined as `w` of equation 2. of [Imagen Paper](https://arxiv.org/pdf/2205.11487.pdf).
+        # Guidance scale is enabled by setting `guidance_scale > 1`. Higher guidance scale encourages to generate
+        # images that are closely linked to the text `prompt`, usually at the expense of lower image quality.
+        self.guidance_scale = guidance_scale
+        # For models trained using zero-terminal SNR ("ztsnr"), it's suggested to use guidance_rescale_multiplier of 0.7.
+        # See [Common Diffusion Noise Schedules and Sample Steps are Flawed](https://arxiv.org/pdf/2305.08891.pdf).
+        self.guidance_rescale_multiplier = guidance_rescale_multiplier
+
+    def is_sdxl(self):
+        assert isinstance(self.uncond_text, SDXLConditioningInfo) == isinstance(self.cond_text, SDXLConditioningInfo)
+        return isinstance(self.cond_text, SDXLConditioningInfo)

invokeai/backend/stable_diffusion/diffusion/cross_attention_control.py

@@ -1,218 +0,0 @@
-# adapted from bloc97's CrossAttentionControl colab
-# https://github.com/bloc97/CrossAttentionControl
-
-
-import enum
-from dataclasses import dataclass, field
-from typing import Optional
-
-import torch
-from compel.cross_attention_control import Arguments
-from diffusers.models.attention_processor import Attention, SlicedAttnProcessor
-from diffusers.models.unets.unet_2d_condition import UNet2DConditionModel
-
-from invokeai.backend.util.devices import torch_dtype
-
-
-class CrossAttentionType(enum.Enum):
-    SELF = 1
-    TOKENS = 2
-
-
-class CrossAttnControlContext:
-    def __init__(self, arguments: Arguments):
-        """
-        :param arguments: Arguments for the cross-attention control process
-        """
-        self.cross_attention_mask: Optional[torch.Tensor] = None
-        self.cross_attention_index_map: Optional[torch.Tensor] = None
-        self.arguments = arguments
-
-    def get_active_cross_attention_control_types_for_step(
-        self, percent_through: float = None
-    ) -> list[CrossAttentionType]:
-        """
-        Should cross-attention control be applied on the given step?
-        :param percent_through: How far through the step sequence are we (0.0=pure noise, 1.0=completely denoised image). Expected range 0.0..<1.0.
-        :return: A list of attention types that cross-attention control should be performed for on the given step. May be [].
-        """
-        if percent_through is None:
-            return [CrossAttentionType.SELF, CrossAttentionType.TOKENS]
-
-        opts = self.arguments.edit_options
-        to_control = []
-        if opts["s_start"] <= percent_through < opts["s_end"]:
-            to_control.append(CrossAttentionType.SELF)
-        if opts["t_start"] <= percent_through < opts["t_end"]:
-            to_control.append(CrossAttentionType.TOKENS)
-        return to_control
-
-
-def setup_cross_attention_control_attention_processors(unet: UNet2DConditionModel, context: CrossAttnControlContext):
-    """
-    Inject attention parameters and functions into the passed in model to enable cross attention editing.
-
-    :param model: The unet model to inject into.
-    :return: None
-    """
-
-    # adapted from init_attention_edit
-    device = context.arguments.edited_conditioning.device
-
-    # urgh. should this be hardcoded?
-    max_length = 77
-    # mask=1 means use base prompt attention, mask=0 means use edited prompt attention
-    mask = torch.zeros(max_length, dtype=torch_dtype(device))
-    indices_target = torch.arange(max_length, dtype=torch.long)
-    indices = torch.arange(max_length, dtype=torch.long)
-    for name, a0, a1, b0, b1 in context.arguments.edit_opcodes:
-        if b0 < max_length:
-            if name == "equal":  # or (name == "replace" and a1 - a0 == b1 - b0):
-                # these tokens have not been edited
-                indices[b0:b1] = indices_target[a0:a1]
-                mask[b0:b1] = 1
-
-    context.cross_attention_mask = mask.to(device)
-    context.cross_attention_index_map = indices.to(device)
-    old_attn_processors = unet.attn_processors
-    if torch.backends.mps.is_available():
-        # see note in StableDiffusionGeneratorPipeline.__init__ about borked slicing on MPS
-        unet.set_attn_processor(SwapCrossAttnProcessor())
-    else:
-        # try to re-use an existing slice size
-        default_slice_size = 4
-        slice_size = next(
-            (p.slice_size for p in old_attn_processors.values() if type(p) is SlicedAttnProcessor), default_slice_size
-        )
-        unet.set_attn_processor(SlicedSwapCrossAttnProcesser(slice_size=slice_size))
-
-
-@dataclass
-class SwapCrossAttnContext:
-    modified_text_embeddings: torch.Tensor
-    index_map: torch.Tensor  # maps from original prompt token indices to the equivalent tokens in the modified prompt
-    mask: torch.Tensor  # in the target space of the index_map
-    cross_attention_types_to_do: list[CrossAttentionType] = field(default_factory=list)
-
-    def wants_cross_attention_control(self, attn_type: CrossAttentionType) -> bool:
-        return attn_type in self.cross_attention_types_to_do
-
-    @classmethod
-    def make_mask_and_index_map(
-        cls, edit_opcodes: list[tuple[str, int, int, int, int]], max_length: int
-    ) -> tuple[torch.Tensor, torch.Tensor]:
-        # mask=1 means use original prompt attention, mask=0 means use modified prompt attention
-        mask = torch.zeros(max_length)
-        indices_target = torch.arange(max_length, dtype=torch.long)
-        indices = torch.arange(max_length, dtype=torch.long)
-        for name, a0, a1, b0, b1 in edit_opcodes:
-            if b0 < max_length:
-                if name == "equal":
-                    # these tokens remain the same as in the original prompt
-                    indices[b0:b1] = indices_target[a0:a1]
-                    mask[b0:b1] = 1
-
-        return mask, indices
-
-
-class SlicedSwapCrossAttnProcesser(SlicedAttnProcessor):
-    # TODO: dynamically pick slice size based on memory conditions
-
-    def __call__(
-        self,
-        attn: Attention,
-        hidden_states,
-        encoder_hidden_states=None,
-        attention_mask=None,
-        # kwargs
-        swap_cross_attn_context: SwapCrossAttnContext = None,
-        **kwargs,
-    ):
-        attention_type = CrossAttentionType.SELF if encoder_hidden_states is None else CrossAttentionType.TOKENS
-
-        # if cross-attention control is not in play, just call through to the base implementation.
-        if (
-            attention_type is CrossAttentionType.SELF
-            or swap_cross_attn_context is None
-            or not swap_cross_attn_context.wants_cross_attention_control(attention_type)
-        ):
-            # print(f"SwapCrossAttnContext for {attention_type} not active - passing request to superclass")
-            return super().__call__(attn, hidden_states, encoder_hidden_states, attention_mask)
-        # else:
-        #    print(f"SwapCrossAttnContext for {attention_type} active")
-
-        batch_size, sequence_length, _ = hidden_states.shape
-        attention_mask = attn.prepare_attention_mask(
-            attention_mask=attention_mask,
-            target_length=sequence_length,
-            batch_size=batch_size,
-        )
-
-        query = attn.to_q(hidden_states)
-        dim = query.shape[-1]
-        query = attn.head_to_batch_dim(query)
-
-        original_text_embeddings = encoder_hidden_states
-        modified_text_embeddings = swap_cross_attn_context.modified_text_embeddings
-        original_text_key = attn.to_k(original_text_embeddings)
-        modified_text_key = attn.to_k(modified_text_embeddings)
-        original_value = attn.to_v(original_text_embeddings)
-        modified_value = attn.to_v(modified_text_embeddings)
-
-        original_text_key = attn.head_to_batch_dim(original_text_key)
-        modified_text_key = attn.head_to_batch_dim(modified_text_key)
-        original_value = attn.head_to_batch_dim(original_value)
-        modified_value = attn.head_to_batch_dim(modified_value)
-
-        # compute slices and prepare output tensor
-        batch_size_attention = query.shape[0]
-        hidden_states = torch.zeros(
-            (batch_size_attention, sequence_length, dim // attn.heads),
-            device=query.device,
-            dtype=query.dtype,
-        )
-
-        # do slices
-        for i in range(max(1, hidden_states.shape[0] // self.slice_size)):
-            start_idx = i * self.slice_size
-            end_idx = (i + 1) * self.slice_size
-
-            query_slice = query[start_idx:end_idx]
-            original_key_slice = original_text_key[start_idx:end_idx]
-            modified_key_slice = modified_text_key[start_idx:end_idx]
-            attn_mask_slice = attention_mask[start_idx:end_idx] if attention_mask is not None else None
-
-            original_attn_slice = attn.get_attention_scores(query_slice, original_key_slice, attn_mask_slice)
-            modified_attn_slice = attn.get_attention_scores(query_slice, modified_key_slice, attn_mask_slice)
-
-            # because the prompt modifications may result in token sequences shifted forwards or backwards,
-            # the original attention probabilities must be remapped to account for token index changes in the
-            # modified prompt
-            remapped_original_attn_slice = torch.index_select(
-                original_attn_slice, -1, swap_cross_attn_context.index_map
-            )
-
-            # only some tokens taken from the original attention probabilities. this is controlled by the mask.
-            mask = swap_cross_attn_context.mask
-            inverse_mask = 1 - mask
-            attn_slice = remapped_original_attn_slice * mask + modified_attn_slice * inverse_mask
-
-            del remapped_original_attn_slice, modified_attn_slice
-
-            attn_slice = torch.bmm(attn_slice, modified_value[start_idx:end_idx])
-            hidden_states[start_idx:end_idx] = attn_slice
-
-        # done
-        hidden_states = attn.batch_to_head_dim(hidden_states)
-
-        # linear proj
-        hidden_states = attn.to_out[0](hidden_states)
-        # dropout
-        hidden_states = attn.to_out[1](hidden_states)
-
-        return hidden_states
-
-
-class SwapCrossAttnProcessor(SlicedSwapCrossAttnProcesser):
-    def __init__(self):
-        super(SwapCrossAttnProcessor, self).__init__(slice_size=int(1e9))  # massive slice size = don't slice

invokeai/backend/stable_diffusion/diffusion/custom_atttention.py

@@ -0,0 +1,198 @@
+from typing import Optional
+
+import torch
+import torch.nn.functional as F
+from diffusers.models.attention_processor import Attention, AttnProcessor2_0
+
+from invokeai.backend.ip_adapter.ip_attention_weights import IPAttentionProcessorWeights
+from invokeai.backend.stable_diffusion.diffusion.regional_ip_data import RegionalIPData
+from invokeai.backend.stable_diffusion.diffusion.regional_prompt_data import RegionalPromptData
+
+
+class CustomAttnProcessor2_0(AttnProcessor2_0):
+    """A custom implementation of AttnProcessor2_0 that supports additional Invoke features.
+    This implementation is based on
+    https://github.com/huggingface/diffusers/blame/fcfa270fbd1dc294e2f3a505bae6bcb791d721c3/src/diffusers/models/attention_processor.py#L1204
+    Supported custom features:
+    - IP-Adapter
+    - Regional prompt attention
+    """
+
+    def __init__(
+        self,
+        ip_adapter_weights: Optional[list[IPAttentionProcessorWeights]] = None,
+    ):
+        """Initialize a CustomAttnProcessor2_0.
+        Note: Arguments that are the same for all attention layers are passed to __call__(). Arguments that are
+        layer-specific are passed to __init__().
+        Args:
+            ip_adapter_weights: The IP-Adapter attention weights. ip_adapter_weights[i] contains the attention weights
+                for the i'th IP-Adapter.
+        """
+        super().__init__()
+        self._ip_adapter_weights = ip_adapter_weights
+
+    def _is_ip_adapter_enabled(self) -> bool:
+        return self._ip_adapter_weights is not None
+
+    def __call__(
+        self,
+        attn: Attention,
+        hidden_states: torch.FloatTensor,
+        encoder_hidden_states: Optional[torch.FloatTensor] = None,
+        attention_mask: Optional[torch.FloatTensor] = None,
+        temb: Optional[torch.FloatTensor] = None,
+        # For regional prompting:
+        regional_prompt_data: Optional[RegionalPromptData] = None,
+        percent_through: Optional[torch.FloatTensor] = None,
+        # For IP-Adapter:
+        regional_ip_data: Optional[RegionalIPData] = None,
+    ) -> torch.FloatTensor:
+        """Apply attention.
+        Args:
+            regional_prompt_data: The regional prompt data for the current batch. If not None, this will be used to
+                apply regional prompt masking.
+            regional_ip_data: The IP-Adapter data for the current batch.
+        """
+        # If true, we are doing cross-attention, if false we are doing self-attention.
+        is_cross_attention = encoder_hidden_states is not None
+
+        # Start unmodified block from AttnProcessor2_0.
+        # vvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvv
+        residual = hidden_states
+        if attn.spatial_norm is not None:
+            hidden_states = attn.spatial_norm(hidden_states, temb)
+
+        input_ndim = hidden_states.ndim
+
+        if input_ndim == 4:
+            batch_size, channel, height, width = hidden_states.shape
+            hidden_states = hidden_states.view(batch_size, channel, height * width).transpose(1, 2)
+
+        batch_size, sequence_length, _ = (
+            hidden_states.shape if encoder_hidden_states is None else encoder_hidden_states.shape
+        )
+        # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+        # End unmodified block from AttnProcessor2_0.
+
+        _, query_seq_len, _ = hidden_states.shape
+        # Handle regional prompt attention masks.
+        if regional_prompt_data is not None and is_cross_attention:
+            assert percent_through is not None
+            prompt_region_attention_mask = regional_prompt_data.get_cross_attn_mask(
+                query_seq_len=query_seq_len, key_seq_len=sequence_length
+            )
+
+            if attention_mask is None:
+                attention_mask = prompt_region_attention_mask
+            else:
+                attention_mask = prompt_region_attention_mask + attention_mask
+
+        # Start unmodified block from AttnProcessor2_0.
+        # vvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvv
+        if attention_mask is not None:
+            attention_mask = attn.prepare_attention_mask(attention_mask, sequence_length, batch_size)
+            # scaled_dot_product_attention expects attention_mask shape to be
+            # (batch, heads, source_length, target_length)
+            attention_mask = attention_mask.view(batch_size, attn.heads, -1, attention_mask.shape[-1])
+
+        if attn.group_norm is not None:
+            hidden_states = attn.group_norm(hidden_states.transpose(1, 2)).transpose(1, 2)
+
+        query = attn.to_q(hidden_states)
+
+        if encoder_hidden_states is None:
+            encoder_hidden_states = hidden_states
+        elif attn.norm_cross:
+            encoder_hidden_states = attn.norm_encoder_hidden_states(encoder_hidden_states)
+
+        key = attn.to_k(encoder_hidden_states)
+        value = attn.to_v(encoder_hidden_states)
+
+        inner_dim = key.shape[-1]
+        head_dim = inner_dim // attn.heads
+
+        query = query.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+
+        key = key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+        value = value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+
+        # the output of sdp = (batch, num_heads, seq_len, head_dim)
+        # TODO: add support for attn.scale when we move to Torch 2.1
+        hidden_states = F.scaled_dot_product_attention(
+            query, key, value, attn_mask=attention_mask, dropout_p=0.0, is_causal=False
+        )
+
+        hidden_states = hidden_states.transpose(1, 2).reshape(batch_size, -1, attn.heads * head_dim)
+        hidden_states = hidden_states.to(query.dtype)
+        # ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+        # End unmodified block from AttnProcessor2_0.
+
+        # Apply IP-Adapter conditioning.
+        if is_cross_attention:
+            if self._is_ip_adapter_enabled():
+                assert regional_ip_data is not None
+                ip_masks = regional_ip_data.get_masks(query_seq_len=query_seq_len)
+                assert (
+                    len(regional_ip_data.image_prompt_embeds)
+                    == len(self._ip_adapter_weights)
+                    == len(regional_ip_data.scales)
+                    == ip_masks.shape[1]
+                )
+                for ipa_index, ipa_embed in enumerate(regional_ip_data.image_prompt_embeds):
+                    ipa_weights = self._ip_adapter_weights[ipa_index]
+                    ipa_scale = regional_ip_data.scales[ipa_index]
+                    ip_mask = ip_masks[0, ipa_index, ...]
+
+                    # The batch dimensions should match.
+                    assert ipa_embed.shape[0] == encoder_hidden_states.shape[0]
+                    # The token_len dimensions should match.
+                    assert ipa_embed.shape[-1] == encoder_hidden_states.shape[-1]
+
+                    ip_hidden_states = ipa_embed
+
+                    # Expected ip_hidden_state shape: (batch_size, num_ip_images, ip_seq_len, ip_image_embedding)
+
+                    ip_key = ipa_weights.to_k_ip(ip_hidden_states)
+                    ip_value = ipa_weights.to_v_ip(ip_hidden_states)
+
+                    # Expected ip_key and ip_value shape: (batch_size, num_ip_images, ip_seq_len, head_dim * num_heads)
+
+                    ip_key = ip_key.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+                    ip_value = ip_value.view(batch_size, -1, attn.heads, head_dim).transpose(1, 2)
+
+                    # Expected ip_key and ip_value shape: (batch_size, num_heads, num_ip_images * ip_seq_len, head_dim)
+
+                    # TODO: add support for attn.scale when we move to Torch 2.1
+                    ip_hidden_states = F.scaled_dot_product_attention(
+                        query, ip_key, ip_value, attn_mask=None, dropout_p=0.0, is_causal=False
+                    )
+
+                    # Expected ip_hidden_states shape: (batch_size, num_heads, query_seq_len, head_dim)
+
+                    ip_hidden_states = ip_hidden_states.transpose(1, 2).reshape(batch_size, -1, attn.heads * head_dim)
+                    ip_hidden_states = ip_hidden_states.to(query.dtype)
+
+                    # Expected ip_hidden_states shape: (batch_size, query_seq_len, num_heads * head_dim)
+
+                    hidden_states = hidden_states + ipa_scale * ip_hidden_states * ip_mask
+            else:
+                # If IP-Adapter is not enabled, then regional_ip_data should not be passed in.
+                assert regional_ip_data is None
+
+        # Start unmodified block from AttnProcessor2_0.
+        # vvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvvv
+        # linear proj
+        hidden_states = attn.to_out[0](hidden_states)
+        # dropout
+        hidden_states = attn.to_out[1](hidden_states)
+
+        if input_ndim == 4:
+            hidden_states = hidden_states.transpose(-1, -2).reshape(batch_size, channel, height, width)
+
+        if attn.residual_connection:
+            hidden_states = hidden_states + residual
+
+        hidden_states = hidden_states / attn.rescale_output_factor
+
+        return hidden_states

invokeai/backend/stable_diffusion/diffusion/regional_ip_data.py

@@ -0,0 +1,72 @@
+import torch
+
+
+class RegionalIPData:
+    """A class to manage the data for regional IP-Adapter conditioning."""
+
+    def __init__(
+        self,
+        image_prompt_embeds: list[torch.Tensor],
+        scales: list[float],
+        masks: list[torch.Tensor],
+        dtype: torch.dtype,
+        device: torch.device,
+        max_downscale_factor: int = 8,
+    ):
+        """Initialize a `IPAdapterConditioningData` object."""
+        assert len(image_prompt_embeds) == len(scales) == len(masks)
+
+        # The image prompt embeddings.
+        # regional_ip_data[i] contains the image prompt embeddings for the i'th IP-Adapter. Each tensor
+        # has shape (batch_size, num_ip_images, seq_len, ip_embedding_len).
+        self.image_prompt_embeds = image_prompt_embeds
+
+        # The scales for the IP-Adapter attention.
+        # scales[i] contains the attention scale for the i'th IP-Adapter.
+        self.scales = scales
+
+        # The IP-Adapter masks.
+        # self._masks_by_seq_len[s] contains the spatial masks for the downsampling level with query sequence length of
+        # s. It has shape (batch_size, num_ip_images, query_seq_len, 1). The masks have values of 1.0 for included
+        # regions and 0.0 for excluded regions.
+        self._masks_by_seq_len = self._prepare_masks(masks, max_downscale_factor, device, dtype)
+
+    def _prepare_masks(
+        self, masks: list[torch.Tensor], max_downscale_factor: int, device: torch.device, dtype: torch.dtype
+    ) -> dict[int, torch.Tensor]:
+        """Prepare the masks for the IP-Adapter attention."""
+        # Concatenate the masks so that they can be processed more efficiently.
+        mask_tensor = torch.cat(masks, dim=1)
+
+        mask_tensor = mask_tensor.to(device=device, dtype=dtype)
+
+        masks_by_seq_len: dict[int, torch.Tensor] = {}
+
+        # Downsample the spatial dimensions by factors of 2 until max_downscale_factor is reached.
+        downscale_factor = 1
+        while downscale_factor <= max_downscale_factor:
+            b, num_ip_adapters, h, w = mask_tensor.shape
+            # Assert that the batch size is 1, because I haven't thought through batch handling for this feature yet.
+            assert b == 1
+
+            # The IP-Adapters are applied in the cross-attention layers, where the query sequence length is the h * w of
+            # the spatial features.
+            query_seq_len = h * w
+
+            masks_by_seq_len[query_seq_len] = mask_tensor.view((b, num_ip_adapters, -1, 1))
+
+            downscale_factor *= 2
+            if downscale_factor <= max_downscale_factor:
+                # We use max pooling because we downscale to a pretty low resolution, so we don't want small mask
+                # regions to be lost entirely.
+                #
+                # ceil_mode=True is set to mirror the downsampling behavior of SD and SDXL.
+                #
+                # TODO(ryand): In the future, we may want to experiment with other downsampling methods.
+                mask_tensor = torch.nn.functional.max_pool2d(mask_tensor, kernel_size=2, stride=2, ceil_mode=True)
+
+        return masks_by_seq_len
+
+    def get_masks(self, query_seq_len: int) -> torch.Tensor:
+        """Get the mask for the given query sequence length."""
+        return self._masks_by_seq_len[query_seq_len]

invokeai/backend/stable_diffusion/diffusion/regional_prompt_data.py

@@ -0,0 +1,105 @@
+import torch
+import torch.nn.functional as F
+
+from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
+    TextConditioningRegions,
+)
+
+
+class RegionalPromptData:
+    """A class to manage the prompt data for regional conditioning."""
+
+    def __init__(
+        self,
+        regions: list[TextConditioningRegions],
+        device: torch.device,
+        dtype: torch.dtype,
+        max_downscale_factor: int = 8,
+    ):
+        """Initialize a `RegionalPromptData` object.
+        Args:
+            regions (list[TextConditioningRegions]): regions[i] contains the prompt regions for the i'th sample in the
+                batch.
+            device (torch.device): The device to use for the attention masks.
+            dtype (torch.dtype): The data type to use for the attention masks.
+            max_downscale_factor: Spatial masks will be prepared for downscale factors from 1 to max_downscale_factor
+                in steps of 2x.
+        """
+        self._regions = regions
+        self._device = device
+        self._dtype = dtype
+        # self._spatial_masks_by_seq_len[b][s] contains the spatial masks for the b'th batch sample with a query
+        # sequence length of s.
+        self._spatial_masks_by_seq_len: list[dict[int, torch.Tensor]] = self._prepare_spatial_masks(
+            regions, max_downscale_factor
+        )
+        self._negative_cross_attn_mask_score = -10000.0
+
+    def _prepare_spatial_masks(
+        self, regions: list[TextConditioningRegions], max_downscale_factor: int = 8
+    ) -> list[dict[int, torch.Tensor]]:
+        """Prepare the spatial masks for all downscaling factors."""
+        # batch_masks_by_seq_len[b][s] contains the spatial masks for the b'th batch sample with a query sequence length
+        # of s.
+        batch_sample_masks_by_seq_len: list[dict[int, torch.Tensor]] = []
+
+        for batch_sample_regions in regions:
+            batch_sample_masks_by_seq_len.append({})
+
+            batch_sample_masks = batch_sample_regions.masks.to(device=self._device, dtype=self._dtype)
+
+            # Downsample the spatial dimensions by factors of 2 until max_downscale_factor is reached.
+            downscale_factor = 1
+            while downscale_factor <= max_downscale_factor:
+                b, _num_prompts, h, w = batch_sample_masks.shape
+                assert b == 1
+                query_seq_len = h * w
+
+                batch_sample_masks_by_seq_len[-1][query_seq_len] = batch_sample_masks
+
+                downscale_factor *= 2
+                if downscale_factor <= max_downscale_factor:
+                    # We use max pooling because we downscale to a pretty low resolution, so we don't want small prompt
+                    # regions to be lost entirely.
+                    #
+                    # ceil_mode=True is set to mirror the downsampling behavior of SD and SDXL.
+                    #
+                    # TODO(ryand): In the future, we may want to experiment with other downsampling methods (e.g.
+                    # nearest interpolation), and could potentially use a weighted mask rather than a binary mask.
+                    batch_sample_masks = F.max_pool2d(batch_sample_masks, kernel_size=2, stride=2, ceil_mode=True)
+
+        return batch_sample_masks_by_seq_len
+
+    def get_cross_attn_mask(self, query_seq_len: int, key_seq_len: int) -> torch.Tensor:
+        """Get the cross-attention mask for the given query sequence length.
+        Args:
+            query_seq_len: The length of the flattened spatial features at the current downscaling level.
+            key_seq_len (int): The sequence length of the prompt embeddings (which act as the key in the cross-attention
+                layers). This is most likely equal to the max embedding range end, but we pass it explicitly to be sure.
+        Returns:
+            torch.Tensor: The cross-attention score mask.
+                shape: (batch_size, query_seq_len, key_seq_len).
+                dtype: float
+        """
+        batch_size = len(self._spatial_masks_by_seq_len)
+        batch_spatial_masks = [self._spatial_masks_by_seq_len[b][query_seq_len] for b in range(batch_size)]
+
+        # Create an empty attention mask with the correct shape.
+        attn_mask = torch.zeros((batch_size, query_seq_len, key_seq_len), dtype=self._dtype, device=self._device)
+
+        for batch_idx in range(batch_size):
+            batch_sample_spatial_masks = batch_spatial_masks[batch_idx]
+            batch_sample_regions = self._regions[batch_idx]
+
+            # Flatten the spatial dimensions of the mask by reshaping to (1, num_prompts, query_seq_len, 1).
+            _, num_prompts, _, _ = batch_sample_spatial_masks.shape
+            batch_sample_query_masks = batch_sample_spatial_masks.view((1, num_prompts, query_seq_len, 1))
+
+            for prompt_idx, embedding_range in enumerate(batch_sample_regions.ranges):
+                batch_sample_query_scores = batch_sample_query_masks[0, prompt_idx, :, :].clone()
+                batch_sample_query_mask = batch_sample_query_scores > 0.5
+                batch_sample_query_scores[batch_sample_query_mask] = 0.0
+                batch_sample_query_scores[~batch_sample_query_mask] = self._negative_cross_attn_mask_score
+                attn_mask[batch_idx, :, embedding_range.start : embedding_range.end] = batch_sample_query_scores
+
+        return attn_mask

invokeai/backend/stable_diffusion/diffusion/shared_invokeai_diffusion.py

@@ -1,26 +1,20 @@
 from __future__ import annotations
 
 import math
-from contextlib import contextmanager
 from typing import Any, Callable, Optional, Union
 
 import torch
-from diffusers import UNet2DConditionModel
 from typing_extensions import TypeAlias
 
 from invokeai.app.services.config.config_default import get_config
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
-    ConditioningData,
-    ExtraConditioningInfo,
-    SDXLConditioningInfo,
-)
-
-from .cross_attention_control import (
-    CrossAttentionType,
-    CrossAttnControlContext,
-    SwapCrossAttnContext,
-    setup_cross_attention_control_attention_processors,
+    IPAdapterData,
+    Range,
+    TextConditioningData,
+    TextConditioningRegions,
 )
+from invokeai.backend.stable_diffusion.diffusion.regional_ip_data import RegionalIPData
+from invokeai.backend.stable_diffusion.diffusion.regional_prompt_data import RegionalPromptData
 
 ModelForwardCallback: TypeAlias = Union[
     # x, t, conditioning, Optional[cross-attention kwargs]
@@ -58,31 +52,8 @@ class InvokeAIDiffuserComponent:
         self.conditioning = None
         self.model = model
         self.model_forward_callback = model_forward_callback
-        self.cross_attention_control_context = None
         self.sequential_guidance = config.sequential_guidance
 
-    @contextmanager
-    def custom_attention_context(
-        self,
-        unet: UNet2DConditionModel,
-        extra_conditioning_info: Optional[ExtraConditioningInfo],
-    ):
-        old_attn_processors = unet.attn_processors
-
-        try:
-            self.cross_attention_control_context = CrossAttnControlContext(
-                arguments=extra_conditioning_info.cross_attention_control_args,
-            )
-            setup_cross_attention_control_attention_processors(
-                unet,
-                self.cross_attention_control_context,
-            )
-
-            yield None
-        finally:
-            self.cross_attention_control_context = None
-            unet.set_attn_processor(old_attn_processors)
-
     def do_controlnet_step(
         self,
         control_data,
@@ -90,7 +61,7 @@ class InvokeAIDiffuserComponent:
         timestep: torch.Tensor,
         step_index: int,
         total_step_count: int,
-        conditioning_data,
+        conditioning_data: TextConditioningData,
     ):
         down_block_res_samples, mid_block_res_sample = None, None
 
@@ -123,28 +94,28 @@ class InvokeAIDiffuserComponent:
                 added_cond_kwargs = None
 
                 if cfg_injection:  # only applying ControlNet to conditional instead of in unconditioned
-                    if type(conditioning_data.text_embeddings) is SDXLConditioningInfo:
+                    if conditioning_data.is_sdxl():
                         added_cond_kwargs = {
-                            "text_embeds": conditioning_data.text_embeddings.pooled_embeds,
-                            "time_ids": conditioning_data.text_embeddings.add_time_ids,
+                            "text_embeds": conditioning_data.cond_text.pooled_embeds,
+                            "time_ids": conditioning_data.cond_text.add_time_ids,
                         }
-                    encoder_hidden_states = conditioning_data.text_embeddings.embeds
+                    encoder_hidden_states = conditioning_data.cond_text.embeds
                     encoder_attention_mask = None
                 else:
-                    if type(conditioning_data.text_embeddings) is SDXLConditioningInfo:
+                    if conditioning_data.is_sdxl():
                         added_cond_kwargs = {
                             "text_embeds": torch.cat(
                                 [
                                     # TODO: how to pad? just by zeros? or even truncate?
-                                    conditioning_data.unconditioned_embeddings.pooled_embeds,
-                                    conditioning_data.text_embeddings.pooled_embeds,
+                                    conditioning_data.uncond_text.pooled_embeds,
+                                    conditioning_data.cond_text.pooled_embeds,
                                 ],
                                 dim=0,
                             ),
                             "time_ids": torch.cat(
                                 [
-                                    conditioning_data.unconditioned_embeddings.add_time_ids,
-                                    conditioning_data.text_embeddings.add_time_ids,
+                                    conditioning_data.uncond_text.add_time_ids,
+                                    conditioning_data.cond_text.add_time_ids,
                                 ],
                                 dim=0,
                             ),
@@ -153,8 +124,8 @@ class InvokeAIDiffuserComponent:
                         encoder_hidden_states,
                         encoder_attention_mask,
                     ) = self._concat_conditionings_for_batch(
-                        conditioning_data.unconditioned_embeddings.embeds,
-                        conditioning_data.text_embeddings.embeds,
+                        conditioning_data.uncond_text.embeds,
+                        conditioning_data.cond_text.embeds,
                     )
                 if isinstance(control_datum.weight, list):
                     # if controlnet has multiple weights, use the weight for the current step
@@ -198,24 +169,15 @@ class InvokeAIDiffuserComponent:
         self,
         sample: torch.Tensor,
         timestep: torch.Tensor,
-        conditioning_data: ConditioningData,
+        conditioning_data: TextConditioningData,
+        ip_adapter_data: Optional[list[IPAdapterData]],
         step_index: int,
         total_step_count: int,
         down_block_additional_residuals: Optional[torch.Tensor] = None,  # for ControlNet
         mid_block_additional_residual: Optional[torch.Tensor] = None,  # for ControlNet
         down_intrablock_additional_residuals: Optional[torch.Tensor] = None,  # for T2I-Adapter
     ):
-        cross_attention_control_types_to_do = []
-        if self.cross_attention_control_context is not None:
-            percent_through = step_index / total_step_count
-            cross_attention_control_types_to_do = (
-                self.cross_attention_control_context.get_active_cross_attention_control_types_for_step(percent_through)
-            )
-        wants_cross_attention_control = len(cross_attention_control_types_to_do) > 0
-
-        if wants_cross_attention_control or self.sequential_guidance:
-            # If wants_cross_attention_control is True, we force the sequential mode to be used, because cross-attention
-            # control is currently only supported in sequential mode.
+        if self.sequential_guidance:
             (
                 unconditioned_next_x,
                 conditioned_next_x,
@@ -223,7 +185,9 @@ class InvokeAIDiffuserComponent:
                 x=sample,
                 sigma=timestep,
                 conditioning_data=conditioning_data,
-                cross_attention_control_types_to_do=cross_attention_control_types_to_do,
+                ip_adapter_data=ip_adapter_data,
+                step_index=step_index,
+                total_step_count=total_step_count,
                 down_block_additional_residuals=down_block_additional_residuals,
                 mid_block_additional_residual=mid_block_additional_residual,
                 down_intrablock_additional_residuals=down_intrablock_additional_residuals,
@@ -236,6 +200,9 @@ class InvokeAIDiffuserComponent:
                 x=sample,
                 sigma=timestep,
                 conditioning_data=conditioning_data,
+                ip_adapter_data=ip_adapter_data,
+                step_index=step_index,
+                total_step_count=total_step_count,
                 down_block_additional_residuals=down_block_additional_residuals,
                 mid_block_additional_residual=mid_block_additional_residual,
                 down_intrablock_additional_residuals=down_intrablock_additional_residuals,
@@ -294,53 +261,84 @@ class InvokeAIDiffuserComponent:
 
     def _apply_standard_conditioning(
         self,
-        x,
-        sigma,
-        conditioning_data: ConditioningData,
+        x: torch.Tensor,
+        sigma: torch.Tensor,
+        conditioning_data: TextConditioningData,
+        ip_adapter_data: Optional[list[IPAdapterData]],
+        step_index: int,
+        total_step_count: int,
         down_block_additional_residuals: Optional[torch.Tensor] = None,  # for ControlNet
         mid_block_additional_residual: Optional[torch.Tensor] = None,  # for ControlNet
         down_intrablock_additional_residuals: Optional[torch.Tensor] = None,  # for T2I-Adapter
-    ):
+    ) -> tuple[torch.Tensor, torch.Tensor]:
         """Runs the conditioned and unconditioned UNet forward passes in a single batch for faster inference speed at
         the cost of higher memory usage.
         """
         x_twice = torch.cat([x] * 2)
         sigma_twice = torch.cat([sigma] * 2)
 
-        cross_attention_kwargs = None
-        if conditioning_data.ip_adapter_conditioning is not None:
+        cross_attention_kwargs = {}
+        if ip_adapter_data is not None:
+            ip_adapter_conditioning = [ipa.ip_adapter_conditioning for ipa in ip_adapter_data]
             # Note that we 'stack' to produce tensors of shape (batch_size, num_ip_images, seq_len, token_len).
-            cross_attention_kwargs = {
-                "ip_adapter_image_prompt_embeds": [
-                    torch.stack(
-                        [ipa_conditioning.uncond_image_prompt_embeds, ipa_conditioning.cond_image_prompt_embeds]
-                    )
-                    for ipa_conditioning in conditioning_data.ip_adapter_conditioning
-                ]
-            }
+            image_prompt_embeds = [
+                torch.stack([ipa_conditioning.uncond_image_prompt_embeds, ipa_conditioning.cond_image_prompt_embeds])
+                for ipa_conditioning in ip_adapter_conditioning
+            ]
+            scales = [ipa.scale_for_step(step_index, total_step_count) for ipa in ip_adapter_data]
+            ip_masks = [ipa.mask for ipa in ip_adapter_data]
+            regional_ip_data = RegionalIPData(
+                image_prompt_embeds=image_prompt_embeds, scales=scales, masks=ip_masks, dtype=x.dtype, device=x.device
+            )
+            cross_attention_kwargs["regional_ip_data"] = regional_ip_data
 
         added_cond_kwargs = None
-        if type(conditioning_data.text_embeddings) is SDXLConditioningInfo:
+        if conditioning_data.is_sdxl():
             added_cond_kwargs = {
                 "text_embeds": torch.cat(
                     [
                         # TODO: how to pad? just by zeros? or even truncate?
-                        conditioning_data.unconditioned_embeddings.pooled_embeds,
-                        conditioning_data.text_embeddings.pooled_embeds,
+                        conditioning_data.uncond_text.pooled_embeds,
+                        conditioning_data.cond_text.pooled_embeds,
                     ],
                     dim=0,
                 ),
                 "time_ids": torch.cat(
                     [
-                        conditioning_data.unconditioned_embeddings.add_time_ids,
-                        conditioning_data.text_embeddings.add_time_ids,
+                        conditioning_data.uncond_text.add_time_ids,
+                        conditioning_data.cond_text.add_time_ids,
                     ],
                     dim=0,
                 ),
             }
 
+        if conditioning_data.cond_regions is not None or conditioning_data.uncond_regions is not None:
+            # TODO(ryand): We currently initialize RegionalPromptData for every denoising step. The text conditionings
+            # and masks are not changing from step-to-step, so this really only needs to be done once. While this seems
+            # painfully inefficient, the time spent is typically negligible compared to the forward inference pass of
+            # the UNet. The main reason that this hasn't been moved up to eliminate redundancy is that it is slightly
+            # awkward to handle both standard conditioning and sequential conditioning further up the stack.
+            regions = []
+            for c, r in [
+                (conditioning_data.uncond_text, conditioning_data.uncond_regions),
+                (conditioning_data.cond_text, conditioning_data.cond_regions),
+            ]:
+                if r is None:
+                    # Create a dummy mask and range for text conditioning that doesn't have region masks.
+                    _, _, h, w = x.shape
+                    r = TextConditioningRegions(
+                        masks=torch.ones((1, 1, h, w), dtype=x.dtype),
+                        ranges=[Range(start=0, end=c.embeds.shape[1])],
+                    )
+                regions.append(r)
+
+            cross_attention_kwargs["regional_prompt_data"] = RegionalPromptData(
+                regions=regions, device=x.device, dtype=x.dtype
+            )
+            cross_attention_kwargs["percent_through"] = step_index / total_step_count
+
         both_conditionings, encoder_attention_mask = self._concat_conditionings_for_batch(
-            conditioning_data.unconditioned_embeddings.embeds, conditioning_data.text_embeddings.embeds
+            conditioning_data.uncond_text.embeds, conditioning_data.cond_text.embeds
         )
         both_results = self.model_forward_callback(
             x_twice,
@@ -360,8 +358,10 @@ class InvokeAIDiffuserComponent:
         self,
         x: torch.Tensor,
         sigma,
-        conditioning_data: ConditioningData,
-        cross_attention_control_types_to_do: list[CrossAttentionType],
+        conditioning_data: TextConditioningData,
+        ip_adapter_data: Optional[list[IPAdapterData]],
+        step_index: int,
+        total_step_count: int,
         down_block_additional_residuals: Optional[torch.Tensor] = None,  # for ControlNet
         mid_block_additional_residual: Optional[torch.Tensor] = None,  # for ControlNet
         down_intrablock_additional_residuals: Optional[torch.Tensor] = None,  # for T2I-Adapter
@@ -391,53 +391,48 @@ class InvokeAIDiffuserComponent:
         if mid_block_additional_residual is not None:
             uncond_mid_block, cond_mid_block = mid_block_additional_residual.chunk(2)
 
-        # If cross-attention control is enabled, prepare the SwapCrossAttnContext.
-        cross_attn_processor_context = None
-        if self.cross_attention_control_context is not None:
-            # Note that the SwapCrossAttnContext is initialized with an empty list of cross_attention_types_to_do.
-            # This list is empty because cross-attention control is not applied in the unconditioned pass. This field
-            # will be populated before the conditioned pass.
-            cross_attn_processor_context = SwapCrossAttnContext(
-                modified_text_embeddings=self.cross_attention_control_context.arguments.edited_conditioning,
-                index_map=self.cross_attention_control_context.cross_attention_index_map,
-                mask=self.cross_attention_control_context.cross_attention_mask,
-                cross_attention_types_to_do=[],
-            )
-
         #####################
         # Unconditioned pass
         #####################
 
-        cross_attention_kwargs = None
+        cross_attention_kwargs = {}
 
         # Prepare IP-Adapter cross-attention kwargs for the unconditioned pass.
-        if conditioning_data.ip_adapter_conditioning is not None:
+        if ip_adapter_data is not None:
+            ip_adapter_conditioning = [ipa.ip_adapter_conditioning for ipa in ip_adapter_data]
             # Note that we 'unsqueeze' to produce tensors of shape (batch_size=1, num_ip_images, seq_len, token_len).
-            cross_attention_kwargs = {
-                "ip_adapter_image_prompt_embeds": [
-                    torch.unsqueeze(ipa_conditioning.uncond_image_prompt_embeds, dim=0)
-                    for ipa_conditioning in conditioning_data.ip_adapter_conditioning
-                ]
-            }
+            image_prompt_embeds = [
+                torch.unsqueeze(ipa_conditioning.uncond_image_prompt_embeds, dim=0)
+                for ipa_conditioning in ip_adapter_conditioning
+            ]
 
-        # Prepare cross-attention control kwargs for the unconditioned pass.
-        if cross_attn_processor_context is not None:
-            cross_attention_kwargs = {"swap_cross_attn_context": cross_attn_processor_context}
+            scales = [ipa.scale_for_step(step_index, total_step_count) for ipa in ip_adapter_data]
+            ip_masks = [ipa.mask for ipa in ip_adapter_data]
+            regional_ip_data = RegionalIPData(
+                image_prompt_embeds=image_prompt_embeds, scales=scales, masks=ip_masks, dtype=x.dtype, device=x.device
+            )
+            cross_attention_kwargs["regional_ip_data"] = regional_ip_data
 
         # Prepare SDXL conditioning kwargs for the unconditioned pass.
         added_cond_kwargs = None
-        is_sdxl = type(conditioning_data.text_embeddings) is SDXLConditioningInfo
-        if is_sdxl:
+        if conditioning_data.is_sdxl():
             added_cond_kwargs = {
-                "text_embeds": conditioning_data.unconditioned_embeddings.pooled_embeds,
-                "time_ids": conditioning_data.unconditioned_embeddings.add_time_ids,
+                "text_embeds": conditioning_data.uncond_text.pooled_embeds,
+                "time_ids": conditioning_data.uncond_text.add_time_ids,
             }
 
+        # Prepare prompt regions for the unconditioned pass.
+        if conditioning_data.uncond_regions is not None:
+            cross_attention_kwargs["regional_prompt_data"] = RegionalPromptData(
+                regions=[conditioning_data.uncond_regions], device=x.device, dtype=x.dtype
+            )
+            cross_attention_kwargs["percent_through"] = step_index / total_step_count
+
         # Run unconditioned UNet denoising (i.e. negative prompt).
         unconditioned_next_x = self.model_forward_callback(
             x,
             sigma,
-            conditioning_data.unconditioned_embeddings.embeds,
+            conditioning_data.uncond_text.embeds,
             cross_attention_kwargs=cross_attention_kwargs,
             down_block_additional_residuals=uncond_down_block,
             mid_block_additional_residual=uncond_mid_block,
@@ -449,36 +444,43 @@ class InvokeAIDiffuserComponent:
         # Conditioned pass
         ###################
 
-        cross_attention_kwargs = None
+        cross_attention_kwargs = {}
 
-        # Prepare IP-Adapter cross-attention kwargs for the conditioned pass.
-        if conditioning_data.ip_adapter_conditioning is not None:
+        if ip_adapter_data is not None:
+            ip_adapter_conditioning = [ipa.ip_adapter_conditioning for ipa in ip_adapter_data]
             # Note that we 'unsqueeze' to produce tensors of shape (batch_size=1, num_ip_images, seq_len, token_len).
-            cross_attention_kwargs = {
-                "ip_adapter_image_prompt_embeds": [
-                    torch.unsqueeze(ipa_conditioning.cond_image_prompt_embeds, dim=0)
-                    for ipa_conditioning in conditioning_data.ip_adapter_conditioning
-                ]
-            }
+            image_prompt_embeds = [
+                torch.unsqueeze(ipa_conditioning.cond_image_prompt_embeds, dim=0)
+                for ipa_conditioning in ip_adapter_conditioning
+            ]
 
-        # Prepare cross-attention control kwargs for the conditioned pass.
-        if cross_attn_processor_context is not None:
-            cross_attn_processor_context.cross_attention_types_to_do = cross_attention_control_types_to_do
-            cross_attention_kwargs = {"swap_cross_attn_context": cross_attn_processor_context}
+            scales = [ipa.scale_for_step(step_index, total_step_count) for ipa in ip_adapter_data]
+            ip_masks = [ipa.mask for ipa in ip_adapter_data]
+            regional_ip_data = RegionalIPData(
+                image_prompt_embeds=image_prompt_embeds, scales=scales, masks=ip_masks, dtype=x.dtype, device=x.device
+            )
+            cross_attention_kwargs["regional_ip_data"] = regional_ip_data
 
         # Prepare SDXL conditioning kwargs for the conditioned pass.
         added_cond_kwargs = None
-        if is_sdxl:
+        if conditioning_data.is_sdxl():
             added_cond_kwargs = {
-                "text_embeds": conditioning_data.text_embeddings.pooled_embeds,
-                "time_ids": conditioning_data.text_embeddings.add_time_ids,
+                "text_embeds": conditioning_data.cond_text.pooled_embeds,
+                "time_ids": conditioning_data.cond_text.add_time_ids,
             }
 
+        # Prepare prompt regions for the conditioned pass.
+        if conditioning_data.cond_regions is not None:
+            cross_attention_kwargs["regional_prompt_data"] = RegionalPromptData(
+                regions=[conditioning_data.cond_regions], device=x.device, dtype=x.dtype
+            )
+            cross_attention_kwargs["percent_through"] = step_index / total_step_count
+
         # Run conditioned UNet denoising (i.e. positive prompt).
         conditioned_next_x = self.model_forward_callback(
             x,
             sigma,
-            conditioning_data.text_embeddings.embeds,
+            conditioning_data.cond_text.embeds,
             cross_attention_kwargs=cross_attention_kwargs,
             down_block_additional_residuals=cond_down_block,
             mid_block_additional_residual=cond_mid_block,

invokeai/backend/stable_diffusion/diffusion/unet_attention_patcher.py

@@ -1,52 +1,46 @@
 from contextlib import contextmanager
+from typing import Optional
 
 from diffusers.models import UNet2DConditionModel
 
-from invokeai.backend.ip_adapter.attention_processor import AttnProcessor2_0, IPAttnProcessor2_0
 from invokeai.backend.ip_adapter.ip_adapter import IPAdapter
+from invokeai.backend.stable_diffusion.diffusion.custom_atttention import CustomAttnProcessor2_0
 
 
-class UNetPatcher:
-    """A class that contains multiple IP-Adapters and can apply them to a UNet."""
+class UNetAttentionPatcher:
+    """A class for patching a UNet with CustomAttnProcessor2_0 attention layers."""
 
-    def __init__(self, ip_adapters: list[IPAdapter]):
+    def __init__(self, ip_adapters: Optional[list[IPAdapter]]):
         self._ip_adapters = ip_adapters
-        self._scales = [1.0] * len(self._ip_adapters)
-
-    def set_scale(self, idx: int, value: float):
-        self._scales[idx] = value
 
     def _prepare_attention_processors(self, unet: UNet2DConditionModel):
         """Prepare a dict of attention processors that can be injected into a unet, and load the IP-Adapter attention
-        weights into them.
-
+        weights into them (if IP-Adapters are being applied).
         Note that the `unet` param is only used to determine attention block dimensions and naming.
         """
         # Construct a dict of attention processors based on the UNet's architecture.
         attn_procs = {}
         for idx, name in enumerate(unet.attn_processors.keys()):
-            if name.endswith("attn1.processor"):
-                attn_procs[name] = AttnProcessor2_0()
+            if name.endswith("attn1.processor") or self._ip_adapters is None:
+                # "attn1" processors do not use IP-Adapters.
+                attn_procs[name] = CustomAttnProcessor2_0()
             else:
                 # Collect the weights from each IP Adapter for the idx'th attention processor.
-                attn_procs[name] = IPAttnProcessor2_0(
+                attn_procs[name] = CustomAttnProcessor2_0(
                     [ip_adapter.attn_weights.get_attention_processor_weights(idx) for ip_adapter in self._ip_adapters],
-                    self._scales,
                 )
         return attn_procs
 
     @contextmanager
     def apply_ip_adapter_attention(self, unet: UNet2DConditionModel):
-        """A context manager that patches `unet` with IP-Adapter attention processors."""
-
+        """A context manager that patches `unet` with CustomAttnProcessor2_0 attention layers."""
         attn_procs = self._prepare_attention_processors(unet)
-
         orig_attn_processors = unet.attn_processors
 
         try:
-            # Note to future devs: set_attn_processor(...) does something slightly unexpected - it pops elements from the
-            # passed dict. So, if you wanted to keep the dict for future use, you'd have to make a moderately-shallow copy
-            # of it. E.g. `attn_procs_copy = {k: v for k, v in attn_procs.items()}`.
+            # Note to future devs: set_attn_processor(...) does something slightly unexpected - it pops elements from
+            # the passed dict. So, if you wanted to keep the dict for future use, you'd have to make a
+            # moderately-shallow copy of it. E.g. `attn_procs_copy = {k: v for k, v in attn_procs.items()}`.
             unet.set_attn_processor(attn_procs)
             yield None
         finally:

invokeai/backend/util/devices.py

@@ -6,8 +6,7 @@ from typing import Literal, Optional, Union
 import torch
 from torch import autocast
 
-from invokeai.app.services.config import InvokeAIAppConfig
-from invokeai.app.services.config.config_default import get_config
+from invokeai.app.services.config.config_default import PRECISION, get_config
 
 CPU_DEVICE = torch.device("cpu")
 CUDA_DEVICE = torch.device("cuda")
@@ -33,35 +32,34 @@ def get_torch_device_name() -> str:
     return torch.cuda.get_device_name(device) if device.type == "cuda" else device.type.upper()
 
 
-# We are in transition here from using a single global AppConfig to allowing multiple
-# configurations. It is strongly recommended to pass the app_config to this function.
-def choose_precision(
-    device: torch.device, app_config: Optional[InvokeAIAppConfig] = None
-) -> Literal["float32", "float16", "bfloat16"]:
+def choose_precision(device: torch.device) -> Literal["float32", "float16", "bfloat16"]:
     """Return an appropriate precision for the given torch device."""
-    app_config = app_config or get_config()
+    app_config = get_config()
     if device.type == "cuda":
         device_name = torch.cuda.get_device_name(device)
-        if not ("GeForce GTX 1660" in device_name or "GeForce GTX 1650" in device_name):
-            if app_config.precision == "float32":
-                return "float32"
-            elif app_config.precision == "bfloat16":
-                return "bfloat16"
-            else:
-                return "float16"
+        if "GeForce GTX 1660" in device_name or "GeForce GTX 1650" in device_name:
+            # These GPUs have limited support for float16
+            return "float32"
+        elif app_config.precision == "auto" or app_config.precision == "autocast":
+            # Default to float16 for CUDA devices
+            return "float16"
+        else:
+            # Use the user-defined precision
+            return app_config.precision
     elif device.type == "mps":
-        return "float16"
+        if app_config.precision == "auto" or app_config.precision == "autocast":
+            # Default to float16 for MPS devices
+            return "float16"
+        else:
+            # Use the user-defined precision
+            return app_config.precision
+    # CPU / safe fallback
     return "float32"
 
 
-# We are in transition here from using a single global AppConfig to allowing multiple
-# configurations. It is strongly recommended to pass the app_config to this function.
-def torch_dtype(
-    device: Optional[torch.device] = None,
-    app_config: Optional[InvokeAIAppConfig] = None,
-) -> torch.dtype:
+def torch_dtype(device: Optional[torch.device] = None) -> torch.dtype:
     device = device or choose_torch_device()
-    precision = choose_precision(device, app_config)
+    precision = choose_precision(device)
     if precision == "float16":
         return torch.float16
     if precision == "bfloat16":
@@ -71,7 +69,7 @@ def torch_dtype(
         return torch.float32
 
 
-def choose_autocast(precision):
+def choose_autocast(precision: PRECISION):
     """Returns an autocast context or nullcontext for the given precision string"""
     # float16 currently requires autocast to avoid errors like:
     # 'expected scalar type Half but found Float'

invokeai/backend/util/mask.py

@@ -0,0 +1,53 @@
+import torch
+
+
+def to_standard_mask_dim(mask: torch.Tensor) -> torch.Tensor:
+    """Standardize the dimensions of a mask tensor.
+
+    Args:
+        mask (torch.Tensor): A mask tensor. The shape can be (1, h, w) or (h, w).
+
+    Returns:
+        torch.Tensor: The output mask tensor. The shape is (1, h, w).
+    """
+    # Get the mask height and width.
+    if mask.ndim == 2:
+        mask = mask.unsqueeze(0)
+    elif mask.ndim == 3 and mask.shape[0] == 1:
+        pass
+    else:
+        raise ValueError(f"Unsupported mask shape: {mask.shape}. Expected (1, h, w) or (h, w).")
+
+    return mask
+
+
+def to_standard_float_mask(mask: torch.Tensor, out_dtype: torch.dtype) -> torch.Tensor:
+    """Standardize the format of a mask tensor.
+
+    Args:
+        mask (torch.Tensor): A mask tensor. The dtype can be any bool, float, or int type. The shape must be (1, h, w)
+            or (h, w).
+
+        out_dtype (torch.dtype): The dtype of the output mask tensor. Must be a float type.
+
+    Returns:
+        torch.Tensor: The output mask tensor. The dtype is out_dtype. The shape is (1, h, w). All values are either 0.0
+            or 1.0.
+    """
+
+    if not out_dtype.is_floating_point:
+        raise ValueError(f"out_dtype must be a float type, but got {out_dtype}")
+
+    mask = to_standard_mask_dim(mask)
+    mask = mask.to(out_dtype)
+
+    # Set masked regions to 1.0.
+    if mask.dtype == torch.bool:
+        mask = mask.to(out_dtype)
+    else:
+        mask = mask.to(out_dtype)
+        mask_region = mask > 0.5
+        mask[mask_region] = 1.0
+        mask[~mask_region] = 0.0
+
+    return mask

invokeai/frontend/web/index.html

@@ -8,7 +8,7 @@
   <meta http-equiv="Pragma" content="no-cache">
   <meta http-equiv="Expires" content="0">
   <title>Invoke - Community Edition</title>
-  <link rel="icon" type="icon" href="assets/images/invoke-favicon.svg" />
+  <link id="invoke-favicon" rel="icon" type="icon" href="assets/images/invoke-favicon.svg" />
   <style>
     html,
     body {
@@ -23,4 +23,4 @@
   <script type="module" src="/src/main.tsx"></script>
 </body>
 
-</html>
+</html>

invokeai/frontend/web/knip.ts

@@ -1,6 +1,7 @@
 import type { KnipConfig } from 'knip';
 
 const config: KnipConfig = {
+  project: ['src/**/*.{ts,tsx}!'],
   ignore: [
     // This file is only used during debugging
     'src/app/store/middleware/debugLoggerMiddleware.ts',
@@ -10,6 +11,9 @@ const config: KnipConfig = {
     'src/features/nodes/types/v2/**',
   ],
   ignoreBinaries: ['only-allow'],
+  paths: {
+    'public/*': ['public/*'],
+  },
 };
 
 export default config;

invokeai/frontend/web/package.json

@@ -24,7 +24,7 @@
     "build": "pnpm run lint && vite build",
     "typegen": "node scripts/typegen.js",
     "preview": "vite preview",
-    "lint:knip": "knip --tags=-@knipignore",
+    "lint:knip": "knip",
     "lint:dpdm": "dpdm --no-warning --no-tree --transform --exit-code circular:1 src/main.tsx",
     "lint:eslint": "eslint --max-warnings=0 .",
     "lint:prettier": "prettier --check .",
@@ -52,6 +52,7 @@
   },
   "dependencies": {
     "@chakra-ui/react-use-size": "^2.1.0",
+    "@dagrejs/dagre": "^1.1.1",
     "@dagrejs/graphlib": "^2.2.1",
     "@dnd-kit/core": "^6.1.0",
     "@dnd-kit/sortable": "^8.0.0",

invokeai/frontend/web/pnpm-lock.yaml

@@ -11,6 +11,9 @@ dependencies:
   '@chakra-ui/react-use-size':
     specifier: ^2.1.0
     version: 2.1.0(react@18.2.0)
+  '@dagrejs/dagre':
+    specifier: ^1.1.1
+    version: 1.1.1
   '@dagrejs/graphlib':
     specifier: ^2.2.1
     version: 2.2.1
@@ -3092,6 +3095,12 @@ packages:
     dev: true
     optional: true
 
+  /@dagrejs/dagre@1.1.1:
+    resolution: {integrity: sha512-AQfT6pffEuPE32weFzhS/u3UpX+bRXUARIXL7UqLaxz497cN8pjuBlX6axO4IIECE2gBV8eLFQkGCtKX5sDaUA==}
+    dependencies:
+      '@dagrejs/graphlib': 2.2.1
+    dev: false
+
   /@dagrejs/graphlib@2.2.1:
     resolution: {integrity: sha512-xJsN1v6OAxXk6jmNdM+OS/bBE8nDCwM0yDNprXR18ZNatL6to9ggod9+l2XtiLhXfLm0NkE7+Er/cpdlM+SkUA==}
     engines: {node: '>17.0.0'}

invokeai/frontend/web/public/assets/images/invoke-alert-favicon.svg

@@ -0,0 +1,5 @@
+<svg width="16" height="16" viewBox="0 0 16 16" fill="none" xmlns="http://www.w3.org/2000/svg">
+<rect width="16" height="16" rx="2" fill="#E6FD13"/>
+<path d="M9.61889 5.45H12.5V3.5H3.5V5.45H6.38111L9.61889 10.55H12.5V12.5H3.5V10.55H6.38111" stroke="black"/>
+<circle cx="12" cy="4" r="3" fill="#f5480c" stroke="#0d1117" stroke-width="1"/>
+</svg>

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

@@ -291,7 +291,6 @@
         "canvasMerged": "تم دمج الخط",
         "sentToImageToImage": "تم إرسال إلى صورة إلى صورة",
         "sentToUnifiedCanvas": "تم إرسال إلى لوحة موحدة",
-        "parametersSet": "تم تعيين المعلمات",
         "parametersNotSet": "لم يتم تعيين المعلمات",
         "metadataLoadFailed": "فشل تحميل البيانات الوصفية"
     },

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

@@ -480,7 +480,6 @@
         "canvasMerged": "Leinwand zusammengeführt",
         "sentToImageToImage": "Gesendet an Bild zu Bild",
         "sentToUnifiedCanvas": "Gesendet an Leinwand",
-        "parametersSet": "Parameter festlegen",
         "parametersNotSet": "Parameter nicht festgelegt",
         "metadataLoadFailed": "Metadaten konnten nicht geladen werden",
         "setCanvasInitialImage": "Ausgangsbild setzen",

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

@@ -326,7 +326,8 @@
         "drop": "Drop",
         "dropOrUpload": "$t(gallery.drop) or Upload",
         "dropToUpload": "$t(gallery.drop) to Upload",
-        "deleteImage": "Delete Image",
+        "deleteImage_one": "Delete Image",
+        "deleteImage_other": "Delete {{count}} Images",
         "deleteImageBin": "Deleted images will be sent to your operating system's Bin.",
         "deleteImagePermanent": "Deleted images cannot be restored.",
         "download": "Download",
@@ -849,6 +850,7 @@
         "version": "Version",
         "versionUnknown": " Version Unknown",
         "workflow": "Workflow",
+        "graph": "Graph",
         "workflowAuthor": "Author",
         "workflowContact": "Contact",
         "workflowDescription": "Short Description",
@@ -1041,10 +1043,10 @@
         "metadataLoadFailed": "Failed to load metadata",
         "modelAddedSimple": "Model Added to Queue",
         "modelImportCanceled": "Model Import Canceled",
+        "parameters": "Parameters",
         "parameterNotSet": "{{parameter}} not set",
         "parameterSet": "{{parameter}} set",
         "parametersNotSet": "Parameters Not Set",
-        "parametersSet": "Parameters Set",
         "problemCopyingCanvas": "Problem Copying Canvas",
         "problemCopyingCanvasDesc": "Unable to export base layer",
         "problemCopyingImage": "Unable to Copy Image",
@@ -1423,6 +1425,7 @@
         "eraseBoundingBox": "Erase Bounding Box",
         "eraser": "Eraser",
         "fillBoundingBox": "Fill Bounding Box",
+        "hideBoundingBox": "Hide Bounding Box",
         "initialFitImageSize": "Fit Image Size on Drop",
         "invertBrushSizeScrollDirection": "Invert Scroll for Brush Size",
         "layer": "Layer",
@@ -1440,6 +1443,7 @@
         "saveMask": "Save $t(unifiedCanvas.mask)",
         "saveToGallery": "Save To Gallery",
         "scaledBoundingBox": "Scaled Bounding Box",
+        "showBoundingBox": "Show Bounding Box",
         "showCanvasDebugInfo": "Show Additional Canvas Info",
         "showGrid": "Show Grid",
         "showResultsOn": "Show Results (On)",
@@ -1482,7 +1486,11 @@
         "workflowName": "Workflow Name",
         "newWorkflowCreated": "New Workflow Created",
         "workflowCleared": "Workflow Cleared",
-        "workflowEditorMenu": "Workflow Editor Menu"
+        "workflowEditorMenu": "Workflow Editor Menu",
+        "loadFromGraph": "Load Workflow from Graph",
+        "convertGraph": "Convert Graph",
+        "loadWorkflow": "$t(common.load) Workflow",
+        "autoLayout": "Auto Layout"
     },
     "app": {
         "storeNotInitialized": "Store is not initialized"

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

@@ -363,7 +363,6 @@
         "canvasMerged": "Lienzo consolidado",
         "sentToImageToImage": "Enviar hacia Imagen a Imagen",
         "sentToUnifiedCanvas": "Enviar hacia Lienzo Consolidado",
-        "parametersSet": "Parámetros establecidos",
         "parametersNotSet": "Parámetros no establecidos",
         "metadataLoadFailed": "Error al cargar metadatos",
         "serverError": "Error en el servidor",

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

@@ -298,7 +298,6 @@
         "canvasMerged": "Canvas fusionné",
         "sentToImageToImage": "Envoyé à Image à Image",
         "sentToUnifiedCanvas": "Envoyé à Canvas unifié",
-        "parametersSet": "Paramètres définis",
         "parametersNotSet": "Paramètres non définis",
         "metadataLoadFailed": "Échec du chargement des métadonnées"
     },

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

@@ -306,7 +306,6 @@
         "canvasMerged": "קנבס מוזג",
         "sentToImageToImage": "נשלח לתמונה לתמונה",
         "sentToUnifiedCanvas": "נשלח אל קנבס מאוחד",
-        "parametersSet": "הגדרת פרמטרים",
         "parametersNotSet": "פרמטרים לא הוגדרו",
         "metadataLoadFailed": "טעינת מטא-נתונים נכשלה"
     },

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

@@ -444,7 +444,8 @@
         "hfTokenInvalidErrorMessage2": "Aggiornalo in ",
         "main": "Principali",
         "noModelsInstalledDesc1": "Installa i modelli con",
-        "ipAdapters": "Adattatori IP"
+        "ipAdapters": "Adattatori IP",
+        "noMatchingModels": "Nessun modello corrispondente"
     },
     "parameters": {
         "images": "Immagini",
@@ -526,7 +527,12 @@
         "aspect": "Aspetto",
         "setToOptimalSizeTooLarge": "$t(parameters.setToOptimalSize) (potrebbe essere troppo grande)",
         "remixImage": "Remixa l'immagine",
-        "coherenceEdgeSize": "Dim. bordo"
+        "coherenceEdgeSize": "Dim. bordo",
+        "infillMosaicTileWidth": "Larghezza piastrella",
+        "infillMosaicMinColor": "Colore minimo",
+        "infillMosaicMaxColor": "Colore massimo",
+        "infillMosaicTileHeight": "Altezza piastrella",
+        "infillColorValue": "Colore di riempimento"
     },
     "settings": {
         "models": "Modelli",
@@ -569,7 +575,6 @@
         "canvasMerged": "Tela unita",
         "sentToImageToImage": "Inviato a Immagine a Immagine",
         "sentToUnifiedCanvas": "Inviato a Tela Unificata",
-        "parametersSet": "Parametri impostati",
         "parametersNotSet": "Parametri non impostati",
         "metadataLoadFailed": "Impossibile caricare i metadati",
         "serverError": "Errore del Server",
@@ -621,7 +626,8 @@
         "uploadInitialImage": "Carica l'immagine iniziale",
         "problemDownloadingImage": "Impossibile scaricare l'immagine",
         "prunedQueue": "Coda ripulita",
-        "modelImportCanceled": "Importazione del modello annullata"
+        "modelImportCanceled": "Importazione del modello annullata",
+        "parameters": "Parametri"
     },
     "tooltip": {
         "feature": {
@@ -690,7 +696,10 @@
         "coherenceModeBoxBlur": "Sfocatura Box",
         "coherenceModeStaged": "Maschera espansa",
         "invertBrushSizeScrollDirection": "Inverti scorrimento per dimensione pennello",
-        "discardCurrent": "Scarta l'attuale"
+        "discardCurrent": "Scarta l'attuale",
+        "initialFitImageSize": "Adatta dimensione immagine al rilascio",
+        "hideBoundingBox": "Nascondi il rettangolo di selezione",
+        "showBoundingBox": "Mostra il rettangolo di selezione"
     },
     "accessibility": {
         "invokeProgressBar": "Barra di avanzamento generazione",
@@ -833,7 +842,8 @@
         "editMode": "Modifica nell'editor del flusso di lavoro",
         "resetToDefaultValue": "Ripristina il valore predefinito",
         "noFieldsViewMode": "Questo flusso di lavoro non ha campi selezionati da visualizzare. Visualizza il flusso di lavoro completo per configurare i valori.",
-        "edit": "Modifica"
+        "edit": "Modifica",
+        "graph": "Grafico"
     },
     "boards": {
         "autoAddBoard": "Aggiungi automaticamente bacheca",
@@ -1347,13 +1357,13 @@
             ]
         },
         "seamlessTilingXAxis": {
-            "heading": "Asse X di piastrellatura senza cuciture",
+            "heading": "Piastrella senza giunte sull'asse X",
             "paragraphs": [
                 "Affianca senza soluzione di continuità un'immagine lungo l'asse orizzontale."
             ]
         },
         "seamlessTilingYAxis": {
-            "heading": "Asse Y di piastrellatura senza cuciture",
+            "heading": "Piastrella senza giunte sull'asse Y",
             "paragraphs": [
                 "Affianca senza soluzione di continuità un'immagine lungo l'asse verticale."
             ]
@@ -1477,7 +1487,11 @@
         "name": "Nome",
         "updated": "Aggiornato",
         "projectWorkflows": "Flussi di lavoro del progetto",
-        "opened": "Aperto"
+        "opened": "Aperto",
+        "convertGraph": "Converti grafico",
+        "loadWorkflow": "$t(common.load) Flusso di lavoro",
+        "autoLayout": "Disposizione automatica",
+        "loadFromGraph": "Carica il flusso di lavoro dal grafico"
     },
     "app": {
         "storeNotInitialized": "Il negozio non è inizializzato"

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

@@ -420,7 +420,6 @@
         "canvasMerged": "Canvas samengevoegd",
         "sentToImageToImage": "Gestuurd naar Afbeelding naar afbeelding",
         "sentToUnifiedCanvas": "Gestuurd naar Centraal canvas",
-        "parametersSet": "Parameters ingesteld",
         "parametersNotSet": "Parameters niet ingesteld",
         "metadataLoadFailed": "Fout bij laden metagegevens",
         "serverError": "Serverfout",

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

@@ -267,7 +267,6 @@
         "canvasMerged": "Scalono widoczne warstwy",
         "sentToImageToImage": "Wysłano do Obraz na obraz",
         "sentToUnifiedCanvas": "Wysłano do trybu uniwersalnego",
-        "parametersSet": "Ustawiono parametry",
         "parametersNotSet": "Nie ustawiono parametrów",
         "metadataLoadFailed": "Błąd wczytywania metadanych"
     },

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

@@ -310,7 +310,6 @@
         "canvasMerged": "Tela Fundida",
         "sentToImageToImage": "Mandar Para Imagem Para Imagem",
         "sentToUnifiedCanvas": "Enviada para a Tela Unificada",
-        "parametersSet": "Parâmetros Definidos",
         "parametersNotSet": "Parâmetros Não Definidos",
         "metadataLoadFailed": "Falha ao tentar carregar metadados"
     },

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

@@ -307,7 +307,6 @@
         "canvasMerged": "Tela Fundida",
         "sentToImageToImage": "Mandar Para Imagem Para Imagem",
         "sentToUnifiedCanvas": "Enviada para a Tela Unificada",
-        "parametersSet": "Parâmetros Definidos",
         "parametersNotSet": "Parâmetros Não Definidos",
         "metadataLoadFailed": "Falha ao tentar carregar metadados"
     },

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

@@ -448,7 +448,9 @@
         "loraModels": "LoRAs",
         "main": "Основные",
         "noModelsInstalled": "Нет установленных моделей",
-        "noModelsInstalledDesc1": "Установите модели с помощью"
+        "noModelsInstalledDesc1": "Установите модели с помощью",
+        "noMatchingModels": "Нет подходящих моделей",
+        "ipAdapters": "IP адаптеры"
     },
     "parameters": {
         "images": "Изображения",
@@ -532,7 +534,12 @@
         "lockAspectRatio": "Заблокировать соотношение",
         "remixImage": "Ремикс изображения",
         "coherenceMinDenoise": "Мин. шумоподавление",
-        "coherenceEdgeSize": "Размер края"
+        "coherenceEdgeSize": "Размер края",
+        "infillMosaicTileWidth": "Ширина плиток",
+        "infillMosaicTileHeight": "Высота плиток",
+        "infillMosaicMinColor": "Мин цвет",
+        "infillMosaicMaxColor": "Макс цвет",
+        "infillColorValue": "Цвет заливки"
     },
     "settings": {
         "models": "Модели",
@@ -575,7 +582,6 @@
         "canvasMerged": "Холст объединен",
         "sentToImageToImage": "Отправить в img2img",
         "sentToUnifiedCanvas": "Отправлено на Единый холст",
-        "parametersSet": "Параметры заданы",
         "parametersNotSet": "Параметры не заданы",
         "metadataLoadFailed": "Не удалось загрузить метаданные",
         "serverError": "Ошибка сервера",
@@ -627,7 +633,8 @@
         "uploadInitialImage": "Загрузить начальное изображение",
         "resetInitialImage": "Сбросить начальное изображение",
         "prunedQueue": "Урезанная очередь",
-        "modelImportCanceled": "Импорт модели отменен"
+        "modelImportCanceled": "Импорт модели отменен",
+        "parameters": "Параметры"
     },
     "tooltip": {
         "feature": {
@@ -696,7 +703,8 @@
         "coherenceModeGaussianBlur": "Размытие по Гауссу",
         "coherenceModeBoxBlur": "коробчатое размытие",
         "discardCurrent": "Отбросить текущее",
-        "invertBrushSizeScrollDirection": "Инвертировать прокрутку для размера кисти"
+        "invertBrushSizeScrollDirection": "Инвертировать прокрутку для размера кисти",
+        "initialFitImageSize": "Подогнать размер изображения при перебросе"
     },
     "accessibility": {
         "uploadImage": "Загрузить изображение",
@@ -922,7 +930,8 @@
         "modelSize": "Размер модели",
         "small": "Маленький",
         "body": "Тело",
-        "hands": "Руки"
+        "hands": "Руки",
+        "selectCLIPVisionModel": "Выбрать модель CLIP Vision"
     },
     "boards": {
         "autoAddBoard": "Авто добавление Доски",

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

@@ -315,7 +315,6 @@
         "canvasMerged": "Полотно об'єднане",
         "sentToImageToImage": "Надіслати до img2img",
         "sentToUnifiedCanvas": "Надіслати на полотно",
-        "parametersSet": "Параметри задані",
         "parametersNotSet": "Параметри не задані",
         "metadataLoadFailed": "Не вдалося завантажити метадані",
         "serverError": "Помилка сервера",

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

@@ -65,7 +65,12 @@
         "nextPage": "下一页",
         "saveAs": "保存为",
         "ai": "ai",
-        "or": "或"
+        "or": "或",
+        "aboutDesc": "使用 Invoke 工作？查看：",
+        "add": "添加",
+        "loglevel": "日志级别",
+        "copy": "复制",
+        "localSystem": "本地系统"
     },
     "gallery": {
         "galleryImageSize": "预览大小",
@@ -487,7 +492,6 @@
         "canvasMerged": "画布已合并",
         "sentToImageToImage": "已发送到图生图",
         "sentToUnifiedCanvas": "已发送到统一画布",
-        "parametersSet": "参数已设定",
         "parametersNotSet": "参数未设定",
         "metadataLoadFailed": "加载元数据失败",
         "uploadFailedInvalidUploadDesc": "必须是单张的 PNG 或 JPEG 图片",
@@ -600,7 +604,8 @@
         "loadMore": "加载更多",
         "mode": "模式",
         "resetUI": "$t(accessibility.reset) UI",
-        "createIssue": "创建问题"
+        "createIssue": "创建问题",
+        "about": "关于"
     },
     "tooltip": {
         "feature": {
@@ -1202,7 +1207,16 @@
         "workflows": "工作流",
         "noDescription": "无描述",
         "uploadWorkflow": "从文件中加载",
-        "newWorkflowCreated": "已创建新的工作流"
+        "newWorkflowCreated": "已创建新的工作流",
+        "name": "名称",
+        "defaultWorkflows": "默认工作流",
+        "created": "已创建",
+        "ascending": "升序",
+        "descending": "降序",
+        "updated": "已更新",
+        "userWorkflows": "我的工作流",
+        "projectWorkflows": "项目工作流",
+        "opened": "已打开"
     },
     "app": {
         "storeNotInitialized": "商店尚未初始化"
@@ -1220,7 +1234,8 @@
             "title": "生成"
         },
         "advanced": {
-            "title": "高级"
+            "title": "高级",
+            "options": "$t(accordions.advanced.title) 选项"
         },
         "image": {
             "title": "图像"

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

@@ -1,5 +1,6 @@
 import { Box, useGlobalModifiersInit } from '@invoke-ai/ui-library';
 import { useSocketIO } from 'app/hooks/useSocketIO';
+import { useSyncQueueStatus } from 'app/hooks/useSyncQueueStatus';
 import { useLogger } from 'app/logging/useLogger';
 import { appStarted } from 'app/store/middleware/listenerMiddleware/listeners/appStarted';
 import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
@@ -70,6 +71,7 @@ const App = ({ config = DEFAULT_CONFIG, selectedImage }: Props) => {
   }, [dispatch]);
 
   useStarterModelsToast();
+  useSyncQueueStatus();
 
   return (
     <ErrorBoundary onReset={handleReset} FallbackComponent={AppErrorBoundaryFallback}>

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

@@ -0,0 +1,25 @@
+import { useEffect } from 'react';
+import { useGetQueueStatusQuery } from 'services/api/endpoints/queue';
+
+const baseTitle = document.title;
+const invokeLogoSVG = 'assets/images/invoke-favicon.svg';
+const invokeAlertLogoSVG = 'assets/images/invoke-alert-favicon.svg';
+
+/**
+ * This hook synchronizes the queue status with the page's title and favicon.
+ * It should be considered a singleton and only used once in the component tree.
+ */
+export const useSyncQueueStatus = () => {
+  const { queueSize } = useGetQueueStatusQuery(undefined, {
+    selectFromResult: (res) => ({
+      queueSize: res.data ? res.data.queue.pending + res.data.queue.in_progress : 0,
+    }),
+  });
+  useEffect(() => {
+    document.title = queueSize > 0 ? `(${queueSize}) ${baseTitle}` : baseTitle;
+    const faviconEl = document.getElementById('invoke-favicon');
+    if (faviconEl instanceof HTMLLinkElement) {
+      faviconEl.href = queueSize > 0 ? invokeAlertLogoSVG : invokeLogoSVG;
+    }
+  }, [queueSize]);
+};

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

@@ -1,12 +1,18 @@
 import { isAnyOf } from '@reduxjs/toolkit';
 import { logger } from 'app/logging/logger';
 import type { AppStartListening } from 'app/store/middleware/listenerMiddleware';
-import { canvasBatchIdsReset, commitStagingAreaImage, discardStagedImages } from 'features/canvas/store/canvasSlice';
+import {
+  canvasBatchIdsReset,
+  commitStagingAreaImage,
+  discardStagedImages,
+  resetCanvas,
+  setInitialCanvasImage,
+} from 'features/canvas/store/canvasSlice';
 import { addToast } from 'features/system/store/systemSlice';
 import { t } from 'i18next';
 import { queueApi } from 'services/api/endpoints/queue';
 
-const matcher = isAnyOf(commitStagingAreaImage, discardStagedImages);
+const matcher = isAnyOf(commitStagingAreaImage, discardStagedImages, resetCanvas, setInitialCanvasImage);
 
 export const addCommitStagingAreaImageListener = (startAppListening: AppStartListening) => {
   startAppListening({

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

@@ -1,5 +1,4 @@
 import { Flex, Image, Spinner } from '@invoke-ai/ui-library';
-/** @knipignore */
 import InvokeLogoWhite from 'public/assets/images/invoke-symbol-wht-lrg.svg';
 import { memo } from 'react';
 

invokeai/frontend/web/src/features/canvas/components/IAICanvasStagingAreaToolbar.tsx

@@ -49,14 +49,20 @@ const selector = createMemoizedSelector(selectCanvasSlice, (canvas) => {
 const ClearStagingIntermediatesIconButton = () => {
   const dispatch = useAppDispatch();
   const { t } = useTranslation();
+  const totalStagedImages = useAppSelector((s) => s.canvas.layerState.stagingArea.images.length);
 
   const handleDiscardStagingArea = useCallback(() => {
     dispatch(discardStagedImages());
   }, [dispatch]);
 
   const handleDiscardStagingImage = useCallback(() => {
-    dispatch(discardStagedImage());
-  }, [dispatch]);
+    // Discarding all staged images triggers cancelation of all canvas batches. It's too easy to accidentally
+    // click the discard button, so to prevent accidental cancelation of all batches, we only discard the current
+    // image if there are more than one staged images.
+    if (totalStagedImages > 1) {
+      dispatch(discardStagedImage());
+    }
+  }, [dispatch, totalStagedImages]);
 
   return (
     <>
@@ -67,6 +73,7 @@ const ClearStagingIntermediatesIconButton = () => {
         onClick={handleDiscardStagingImage}
         colorScheme="invokeBlue"
         fontSize={16}
+        isDisabled={totalStagedImages <= 1}
       />
       <IconButton
         tooltip={`${t('unifiedCanvas.discardAll')} (Esc)`}

invokeai/frontend/web/src/features/canvas/components/IAICanvasToolbar/IAICanvasToolbar.tsx

@@ -13,7 +13,13 @@ import {
 } from 'features/canvas/store/actions';
 import { $canvasBaseLayer, $tool } from 'features/canvas/store/canvasNanostore';
 import { isStagingSelector } from 'features/canvas/store/canvasSelectors';
-import { resetCanvas, resetCanvasView, setIsMaskEnabled, setLayer } from 'features/canvas/store/canvasSlice';
+import {
+  resetCanvas,
+  resetCanvasView,
+  setIsMaskEnabled,
+  setLayer,
+  setShouldShowBoundingBox,
+} from 'features/canvas/store/canvasSlice';
 import type { CanvasLayer } from 'features/canvas/store/canvasTypes';
 import { LAYER_NAMES_DICT } from 'features/canvas/store/canvasTypes';
 import { memo, useCallback, useMemo } from 'react';
@@ -23,6 +29,8 @@ import {
   PiCopyBold,
   PiCrosshairSimpleBold,
   PiDownloadSimpleBold,
+  PiEyeBold,
+  PiEyeSlashBold,
   PiFloppyDiskBold,
   PiHandGrabbingBold,
   PiStackBold,
@@ -44,6 +52,7 @@ const IAICanvasToolbar = () => {
   const isStaging = useAppSelector(isStagingSelector);
   const { t } = useTranslation();
   const { isClipboardAPIAvailable } = useCopyImageToClipboard();
+  const shouldShowBoundingBox = useAppSelector((s) => s.canvas.shouldShowBoundingBox);
 
   const { getUploadButtonProps, getUploadInputProps } = useImageUploadButton({
     postUploadAction: { type: 'SET_CANVAS_INITIAL_IMAGE' },
@@ -61,6 +70,18 @@ const IAICanvasToolbar = () => {
     []
   );
 
+  useHotkeys(
+    'shift+h',
+    () => {
+      dispatch(setShouldShowBoundingBox(!shouldShowBoundingBox));
+    },
+    {
+      enabled: () => !isStaging,
+      preventDefault: true,
+    },
+    [shouldShowBoundingBox]
+  );
+
   useHotkeys(
     ['r'],
     () => {
@@ -125,6 +146,10 @@ const IAICanvasToolbar = () => {
     $tool.set('move');
   }, []);
 
+  const handleSetShouldShowBoundingBox = useCallback(() => {
+    dispatch(setShouldShowBoundingBox(!shouldShowBoundingBox));
+  }, [dispatch, shouldShowBoundingBox]);
+
   const handleResetCanvasView = useCallback(
     (shouldScaleTo1 = false) => {
       const canvasBaseLayer = $canvasBaseLayer.get();
@@ -212,6 +237,13 @@ const IAICanvasToolbar = () => {
           isChecked={tool === 'move' || isStaging}
           onClick={handleSelectMoveTool}
         />
+        <IconButton
+          aria-label={`${shouldShowBoundingBox ? t('unifiedCanvas.hideBoundingBox') : t('unifiedCanvas.showBoundingBox')} (Shift + H)`}
+          tooltip={`${shouldShowBoundingBox ? t('unifiedCanvas.hideBoundingBox') : t('unifiedCanvas.showBoundingBox')} (Shift + H)`}
+          icon={shouldShowBoundingBox ? <PiEyeBold /> : <PiEyeSlashBold />}
+          onClick={handleSetShouldShowBoundingBox}
+          isDisabled={isStaging}
+        />
         <IconButton
           aria-label={`${t('unifiedCanvas.resetView')} (R)`}
           tooltip={`${t('unifiedCanvas.resetView')} (R)`}

invokeai/frontend/web/src/features/canvas/hooks/useCanvasHotkeys.ts

@@ -7,12 +7,7 @@ import {
   resetToolInteractionState,
 } from 'features/canvas/store/canvasNanostore';
 import { isStagingSelector } from 'features/canvas/store/canvasSelectors';
-import {
-  clearMask,
-  setIsMaskEnabled,
-  setShouldShowBoundingBox,
-  setShouldSnapToGrid,
-} from 'features/canvas/store/canvasSlice';
+import { clearMask, setIsMaskEnabled, setShouldSnapToGrid } from 'features/canvas/store/canvasSlice';
 import { isInteractiveTarget } from 'features/canvas/util/isInteractiveTarget';
 import { activeTabNameSelector } from 'features/ui/store/uiSelectors';
 import { useCallback, useEffect } from 'react';
@@ -21,7 +16,6 @@ import { useHotkeys } from 'react-hotkeys-hook';
 const useInpaintingCanvasHotkeys = () => {
   const dispatch = useAppDispatch();
   const activeTabName = useAppSelector(activeTabNameSelector);
-  const shouldShowBoundingBox = useAppSelector((s) => s.canvas.shouldShowBoundingBox);
   const isStaging = useAppSelector(isStagingSelector);
   const isMaskEnabled = useAppSelector((s) => s.canvas.isMaskEnabled);
   const shouldSnapToGrid = useAppSelector((s) => s.canvas.shouldSnapToGrid);
@@ -79,18 +73,6 @@ const useInpaintingCanvasHotkeys = () => {
     }
   );
 
-  useHotkeys(
-    'shift+h',
-    () => {
-      dispatch(setShouldShowBoundingBox(!shouldShowBoundingBox));
-    },
-    {
-      enabled: () => !isStaging,
-      preventDefault: true,
-    },
-    [activeTabName, shouldShowBoundingBox]
-  );
-
   const onKeyDown = useCallback(
     (e: KeyboardEvent) => {
       if (e.repeat || e.key !== ' ' || isInteractiveTarget(e.target) || activeTabName !== 'unifiedCanvas') {

invokeai/frontend/web/src/features/canvas/store/canvasSlice.ts

@@ -190,7 +190,6 @@ export const canvasSlice = createSlice({
           ],
         };
         state.futureLayerStates = [];
-        state.batchIds = [];
 
         const newScale = calculateScale(
           stageDimensions.width,
@@ -286,40 +285,14 @@ export const canvasSlice = createSlice({
     },
     discardStagedImages: (state) => {
       pushToPrevLayerStates(state);
-
-      state.layerState.stagingArea = deepClone(initialLayerState.stagingArea);
-
+      resetStagingArea(state);
       state.futureLayerStates = [];
-      state.shouldShowStagingOutline = true;
-      state.shouldShowStagingImage = true;
-      state.batchIds = [];
     },
     discardStagedImage: (state) => {
       const { images, selectedImageIndex } = state.layerState.stagingArea;
       pushToPrevLayerStates(state);
-
       images.splice(selectedImageIndex, 1);
-
-      if (images.length === 0) {
-        pushToPrevLayerStates(state);
-
-        state.layerState.stagingArea = deepClone(initialLayerState.stagingArea);
-
-        state.futureLayerStates = [];
-        state.shouldShowStagingOutline = true;
-        state.shouldShowStagingImage = true;
-        state.batchIds = [];
-      }
-
-      if (selectedImageIndex >= images.length) {
-        state.layerState.stagingArea.selectedImageIndex = images.length - 1;
-      }
-
-      if (!images.length) {
-        state.shouldShowStagingImage = false;
-        state.shouldShowStagingOutline = false;
-      }
-
+      state.layerState.stagingArea.selectedImageIndex = Math.max(0, images.length - 1);
       state.futureLayerStates = [];
     },
     addFillRect: (state) => {
@@ -433,7 +406,6 @@ export const canvasSlice = createSlice({
       pushToPrevLayerStates(state);
       state.layerState = deepClone(initialLayerState);
       state.futureLayerStates = [];
-      state.batchIds = [];
       state.boundingBoxCoordinates = {
         ...initialCanvasState.boundingBoxCoordinates,
       };
@@ -534,12 +506,9 @@ export const canvasSlice = createSlice({
           ...imageToCommit,
         });
       }
-      state.layerState.stagingArea = deepClone(initialLayerState.stagingArea);
 
+      resetStagingArea(state);
       state.futureLayerStates = [];
-      state.shouldShowStagingOutline = true;
-      state.shouldShowStagingImage = true;
-      state.batchIds = [];
     },
     setBoundingBoxScaleMethod: {
       reducer: (state, action: PayloadActionWithOptimalDimension<BoundingBoxScaleMethod>) => {
@@ -647,12 +616,19 @@ export const canvasSlice = createSlice({
       if (batch_status.in_progress === 0 && batch_status.pending === 0) {
         state.batchIds = state.batchIds.filter((id) => id !== batch_status.batch_id);
       }
+
+      const queueItemStatus = action.payload.data.queue_item.status;
+      if (queueItemStatus === 'canceled' || queueItemStatus === 'failed') {
+        resetStagingAreaIfEmpty(state);
+      }
     });
     builder.addMatcher(queueApi.endpoints.clearQueue.matchFulfilled, (state) => {
       state.batchIds = [];
+      resetStagingAreaIfEmpty(state);
     });
     builder.addMatcher(queueApi.endpoints.cancelByBatchIds.matchFulfilled, (state, action) => {
       state.batchIds = state.batchIds.filter((id) => !action.meta.arg.originalArgs.batch_ids.includes(id));
+      resetStagingAreaIfEmpty(state);
     });
   },
 });
@@ -726,7 +702,7 @@ export const canvasPersistConfig: PersistConfig<CanvasState> = {
   name: canvasSlice.name,
   initialState: initialCanvasState,
   migrate: migrateCanvasState,
-  persistDenylist: [],
+  persistDenylist: ['shouldShowStagingImage', 'shouldShowStagingOutline'],
 };
 
 const pushToPrevLayerStates = (state: CanvasState) => {
@@ -742,3 +718,15 @@ const pushToFutureLayerStates = (state: CanvasState) => {
     state.futureLayerStates = state.futureLayerStates.slice(0, MAX_HISTORY);
   }
 };
+
+const resetStagingAreaIfEmpty = (state: CanvasState) => {
+  if (state.batchIds.length === 0 && state.layerState.stagingArea.images.length === 0) {
+    resetStagingArea(state);
+  }
+};
+
+const resetStagingArea = (state: CanvasState) => {
+  state.layerState.stagingArea = { ...initialCanvasState.layerState.stagingArea };
+  state.shouldShowStagingImage = initialCanvasState.shouldShowStagingImage;
+  state.shouldShowStagingOutline = initialCanvasState.shouldShowStagingOutline;
+};

invokeai/frontend/web/src/features/controlAdapters/components/parameters/ParamControlAdapterModel.tsx

@@ -103,7 +103,7 @@ const ParamControlAdapterModel = ({ id }: ParamControlAdapterModelProps) => {
 
   return (
     <Flex sx={{ gap: 2 }}>
-      <Tooltip label={value?.description}>
+      <Tooltip label={selectedModel?.description}>
         <FormControl
           isDisabled={!isEnabled}
           isInvalid={!value || mainModel?.base !== modelConfig?.base}

invokeai/frontend/web/src/features/deleteImageModal/components/DeleteImageButton.tsx

@@ -13,13 +13,15 @@ export const DeleteImageButton = memo((props: DeleteImageButtonProps) => {
   const { onClick, isDisabled } = props;
   const { t } = useTranslation();
   const isConnected = useAppSelector((s) => s.system.isConnected);
+  const imageSelectionLength: number = useAppSelector((s) => s.gallery.selection.length);
+  const labelMessage: string = `${t('gallery.deleteImage', { count: imageSelectionLength })} (Del)`;
 
   return (
     <IconButton
       onClick={onClick}
       icon={<PiTrashSimpleBold />}
-      tooltip={`${t('gallery.deleteImage')} (Del)`}
-      aria-label={`${t('gallery.deleteImage')} (Del)`}
+      tooltip={labelMessage}
+      aria-label={labelMessage}
       isDisabled={isDisabled || !isConnected}
       colorScheme="error"
     />

invokeai/frontend/web/src/features/deleteImageModal/components/DeleteImageModal.tsx

@@ -80,7 +80,7 @@ const DeleteImageModal = () => {
 
   return (
     <ConfirmationAlertDialog
-      title={t('gallery.deleteImage')}
+      title={t('gallery.deleteImage', { count: imagesToDelete.length })}
       isOpen={isModalOpen}
       onClose={handleClose}
       cancelButtonText={t('boards.cancel')}

invokeai/frontend/web/src/features/gallery/components/Boards/BoardsList/NoBoardBoard.tsx

@@ -6,7 +6,6 @@ import type { RemoveFromBoardDropData } from 'features/dnd/types';
 import AutoAddIcon from 'features/gallery/components/Boards/AutoAddIcon';
 import BoardContextMenu from 'features/gallery/components/Boards/BoardContextMenu';
 import { autoAddBoardIdChanged, boardIdSelected } from 'features/gallery/store/gallerySlice';
-/** @knipignore */
 import InvokeLogoSVG from 'public/assets/images/invoke-symbol-wht-lrg.svg';
 import { memo, useCallback, useMemo, useState } from 'react';
 import { useTranslation } from 'react-i18next';

invokeai/frontend/web/src/features/gallery/components/CurrentImage/CurrentImageButtons.tsx

@@ -51,6 +51,7 @@ const CurrentImageButtons = () => {
   const shouldShowImageDetails = useAppSelector((s) => s.ui.shouldShowImageDetails);
   const shouldShowProgressInViewer = useAppSelector((s) => s.ui.shouldShowProgressInViewer);
   const lastSelectedImage = useAppSelector(selectLastSelectedImage);
+  const selection = useAppSelector((s) => s.gallery.selection);
   const shouldDisableToolbarButtons = useAppSelector(selectShouldDisableToolbarButtons);
 
   const isUpscalingEnabled = useFeatureStatus('upscaling').isFeatureEnabled;
@@ -102,8 +103,8 @@ const CurrentImageButtons = () => {
     if (!imageDTO) {
       return;
     }
-    dispatch(imagesToDeleteSelected([imageDTO]));
-  }, [dispatch, imageDTO]);
+    dispatch(imagesToDeleteSelected(selection));
+  }, [dispatch, imageDTO, selection]);
 
   useHotkeys(
     'Shift+U',

invokeai/frontend/web/src/features/gallery/components/ImageContextMenu/SingleSelectionMenuItems.tsx

@@ -188,7 +188,7 @@ const SingleSelectionMenuItems = (props: SingleSelectionMenuItemsProps) => {
       )}
       <MenuDivider />
       <MenuItem color="error.300" icon={<PiTrashSimpleBold />} onClickCapture={handleDelete}>
-        {t('gallery.deleteImage')}
+        {t('gallery.deleteImage', { count: 1 })}
       </MenuItem>
     </>
   );

invokeai/frontend/web/src/features/gallery/components/ImageGrid/GalleryImage.tsx

@@ -180,7 +180,7 @@ const GalleryImage = (props: HoverableImageProps) => {
               <IAIDndImageIcon
                 onClick={handleDelete}
                 icon={<PiTrashSimpleFill size="16px" />}
-                tooltip={t('gallery.deleteImage')}
+                tooltip={t('gallery.deleteImage', { count: 1 })}
                 styleOverrides={imageIconStyleOverrides}
               />
             )}

invokeai/frontend/web/src/features/gallery/components/ImageMetadataViewer/ImageMetadataActions.tsx

@@ -33,6 +33,7 @@ const ImageMetadataActions = (props: Props) => {
       <MetadataItem metadata={metadata} handlers={handlers.scheduler} />
       <MetadataItem metadata={metadata} handlers={handlers.cfgScale} />
       <MetadataItem metadata={metadata} handlers={handlers.cfgRescaleMultiplier} />
+      <MetadataItem metadata={metadata} handlers={handlers.initialImage} />
       <MetadataItem metadata={metadata} handlers={handlers.strength} />
       <MetadataItem metadata={metadata} handlers={handlers.hrfEnabled} />
       <MetadataItem metadata={metadata} handlers={handlers.hrfMethod} />

invokeai/frontend/web/src/features/metadata/util/handlers.ts

@@ -189,6 +189,12 @@ export const handlers = {
     recaller: recallers.cfgScale,
   }),
   height: buildHandlers({ getLabel: () => t('metadata.height'), parser: parsers.height, recaller: recallers.height }),
+  initialImage: buildHandlers({
+    getLabel: () => t('metadata.initImage'),
+    parser: parsers.initialImage,
+    recaller: recallers.initialImage,
+    renderValue: async (imageDTO) => imageDTO.image_name,
+  }),
   negativePrompt: buildHandlers({
     getLabel: () => t('metadata.negativePrompt'),
     parser: parsers.negativePrompt,
@@ -405,6 +411,6 @@ export const parseAndRecallAllMetadata = async (metadata: unknown, skip: (keyof
       })
   );
   if (results.some((result) => result.status === 'fulfilled')) {
-    parameterSetToast(t('toast.parametersSet'));
+    parameterSetToast(t('toast.parameters'));
   }
 };

invokeai/frontend/web/src/features/metadata/util/parsers.ts

@@ -1,3 +1,4 @@
+import { getStore } from 'app/store/nanostores/store';
 import {
   initialControlNet,
   initialIPAdapter,
@@ -57,6 +58,8 @@ import {
   isParameterWidth,
 } from 'features/parameters/types/parameterSchemas';
 import { get, isArray, isString } from 'lodash-es';
+import { imagesApi } from 'services/api/endpoints/images';
+import type { ImageDTO } from 'services/api/types';
 import {
   isControlNetModelConfig,
   isIPAdapterModelConfig,
@@ -135,6 +138,14 @@ const parseCFGRescaleMultiplier: MetadataParseFunc<ParameterCFGRescaleMultiplier
 const parseScheduler: MetadataParseFunc<ParameterScheduler> = (metadata) =>
   getProperty(metadata, 'scheduler', isParameterScheduler);
 
+const parseInitialImage: MetadataParseFunc<ImageDTO> = async (metadata) => {
+  const imageName = await getProperty(metadata, 'init_image', isString);
+  const imageDTORequest = getStore().dispatch(imagesApi.endpoints.getImageDTO.initiate(imageName));
+  const imageDTO = await imageDTORequest.unwrap();
+  imageDTORequest.unsubscribe();
+  return imageDTO;
+};
+
 const parseWidth: MetadataParseFunc<ParameterWidth> = (metadata) => getProperty(metadata, 'width', isParameterWidth);
 
 const parseHeight: MetadataParseFunc<ParameterHeight> = (metadata) =>
@@ -145,8 +156,13 @@ const parseSteps: MetadataParseFunc<ParameterSteps> = (metadata) => getProperty(
 const parseStrength: MetadataParseFunc<ParameterStrength> = (metadata) =>
   getProperty(metadata, 'strength', isParameterStrength);
 
-const parseHRFEnabled: MetadataParseFunc<ParameterHRFEnabled> = (metadata) =>
-  getProperty(metadata, 'hrf_enabled', isParameterHRFEnabled);
+const parseHRFEnabled: MetadataParseFunc<ParameterHRFEnabled> = async (metadata) => {
+  try {
+    return await getProperty(metadata, 'hrf_enabled', isParameterHRFEnabled);
+  } catch {
+    return false;
+  }
+};
 
 const parseHRFStrength: MetadataParseFunc<ParameterStrength> = (metadata) =>
   getProperty(metadata, 'hrf_strength', isParameterStrength);
@@ -213,12 +229,16 @@ const parseLoRA: MetadataParseFunc<LoRA> = async (metadataItem) => {
 };
 
 const parseAllLoRAs: MetadataParseFunc<LoRA[]> = async (metadata) => {
-  const lorasRaw = await getProperty(metadata, 'loras', isArray);
-  const parseResults = await Promise.allSettled(lorasRaw.map((lora) => parseLoRA(lora)));
-  const loras = parseResults
-    .filter((result): result is PromiseFulfilledResult<LoRA> => result.status === 'fulfilled')
-    .map((result) => result.value);
-  return loras;
+  try {
+    const lorasRaw = await getProperty(metadata, 'loras', isArray);
+    const parseResults = await Promise.allSettled(lorasRaw.map((lora) => parseLoRA(lora)));
+    const loras = parseResults
+      .filter((result): result is PromiseFulfilledResult<LoRA> => result.status === 'fulfilled')
+      .map((result) => result.value);
+    return loras;
+  } catch {
+    return [];
+  }
 };
 
 const parseControlNet: MetadataParseFunc<ControlNetConfigMetadata> = async (metadataItem) => {
@@ -277,12 +297,16 @@ const parseControlNet: MetadataParseFunc<ControlNetConfigMetadata> = async (meta
 };
 
 const parseAllControlNets: MetadataParseFunc<ControlNetConfigMetadata[]> = async (metadata) => {
-  const controlNetsRaw = await getProperty(metadata, 'controlnets', isArray);
-  const parseResults = await Promise.allSettled(controlNetsRaw.map((cn) => parseControlNet(cn)));
-  const controlNets = parseResults
-    .filter((result): result is PromiseFulfilledResult<ControlNetConfigMetadata> => result.status === 'fulfilled')
-    .map((result) => result.value);
-  return controlNets;
+  try {
+    const controlNetsRaw = await getProperty(metadata, 'controlnets', isArray || undefined);
+    const parseResults = await Promise.allSettled(controlNetsRaw.map((cn) => parseControlNet(cn)));
+    const controlNets = parseResults
+      .filter((result): result is PromiseFulfilledResult<ControlNetConfigMetadata> => result.status === 'fulfilled')
+      .map((result) => result.value);
+    return controlNets;
+  } catch {
+    return [];
+  }
 };
 
 const parseT2IAdapter: MetadataParseFunc<T2IAdapterConfigMetadata> = async (metadataItem) => {
@@ -337,12 +361,16 @@ const parseT2IAdapter: MetadataParseFunc<T2IAdapterConfigMetadata> = async (meta
 };
 
 const parseAllT2IAdapters: MetadataParseFunc<T2IAdapterConfigMetadata[]> = async (metadata) => {
-  const t2iAdaptersRaw = await getProperty(metadata, 't2iAdapters', isArray);
-  const parseResults = await Promise.allSettled(t2iAdaptersRaw.map((t2iAdapter) => parseT2IAdapter(t2iAdapter)));
-  const t2iAdapters = parseResults
-    .filter((result): result is PromiseFulfilledResult<T2IAdapterConfigMetadata> => result.status === 'fulfilled')
-    .map((result) => result.value);
-  return t2iAdapters;
+  try {
+    const t2iAdaptersRaw = await getProperty(metadata, 't2iAdapters', isArray);
+    const parseResults = await Promise.allSettled(t2iAdaptersRaw.map((t2iAdapter) => parseT2IAdapter(t2iAdapter)));
+    const t2iAdapters = parseResults
+      .filter((result): result is PromiseFulfilledResult<T2IAdapterConfigMetadata> => result.status === 'fulfilled')
+      .map((result) => result.value);
+    return t2iAdapters;
+  } catch {
+    return [];
+  }
 };
 
 const parseIPAdapter: MetadataParseFunc<IPAdapterConfigMetadata> = async (metadataItem) => {
@@ -383,12 +411,16 @@ const parseIPAdapter: MetadataParseFunc<IPAdapterConfigMetadata> = async (metada
 };
 
 const parseAllIPAdapters: MetadataParseFunc<IPAdapterConfigMetadata[]> = async (metadata) => {
-  const ipAdaptersRaw = await getProperty(metadata, 'ipAdapters', isArray);
-  const parseResults = await Promise.allSettled(ipAdaptersRaw.map((ipAdapter) => parseIPAdapter(ipAdapter)));
-  const ipAdapters = parseResults
-    .filter((result): result is PromiseFulfilledResult<IPAdapterConfigMetadata> => result.status === 'fulfilled')
-    .map((result) => result.value);
-  return ipAdapters;
+  try {
+    const ipAdaptersRaw = await getProperty(metadata, 'ipAdapters', isArray);
+    const parseResults = await Promise.allSettled(ipAdaptersRaw.map((ipAdapter) => parseIPAdapter(ipAdapter)));
+    const ipAdapters = parseResults
+      .filter((result): result is PromiseFulfilledResult<IPAdapterConfigMetadata> => result.status === 'fulfilled')
+      .map((result) => result.value);
+    return ipAdapters;
+  } catch {
+    return [];
+  }
 };
 
 export const parsers = {
@@ -402,6 +434,7 @@ export const parsers = {
   cfgScale: parseCFGScale,
   cfgRescaleMultiplier: parseCFGRescaleMultiplier,
   scheduler: parseScheduler,
+  initialImage: parseInitialImage,
   width: parseWidth,
   height: parseHeight,
   steps: parseSteps,

invokeai/frontend/web/src/features/metadata/util/recallers.ts

@@ -17,6 +17,7 @@ import type {
 import { modelSelected } from 'features/parameters/store/actions';
 import {
   heightRecalled,
+  initialImageChanged,
   setCfgRescaleMultiplier,
   setCfgScale,
   setImg2imgStrength,
@@ -61,6 +62,7 @@ import {
   setRefinerStart,
   setRefinerSteps,
 } from 'features/sdxl/store/sdxlSlice';
+import type { ImageDTO } from 'services/api/types';
 
 const recallPositivePrompt: MetadataRecallFunc<ParameterPositivePrompt> = (positivePrompt) => {
   getStore().dispatch(setPositivePrompt(positivePrompt));
@@ -94,6 +96,10 @@ const recallScheduler: MetadataRecallFunc<ParameterScheduler> = (scheduler) => {
   getStore().dispatch(setScheduler(scheduler));
 };
 
+const recallInitialImage: MetadataRecallFunc<ImageDTO> = async (imageDTO) => {
+  getStore().dispatch(initialImageChanged(imageDTO));
+};
+
 const recallWidth: MetadataRecallFunc<ParameterWidth> = (width) => {
   getStore().dispatch(widthRecalled(width));
 };
@@ -171,11 +177,11 @@ const recallLoRA: MetadataRecallFunc<LoRA> = (lora) => {
 };
 
 const recallAllLoRAs: MetadataRecallFunc<LoRA[]> = (loras) => {
+  const { dispatch } = getStore();
+  dispatch(lorasReset());
   if (!loras.length) {
     return;
   }
-  const { dispatch } = getStore();
-  dispatch(lorasReset());
   loras.forEach((lora) => {
     dispatch(loraRecalled(lora));
   });
@@ -186,11 +192,11 @@ const recallControlNet: MetadataRecallFunc<ControlNetConfigMetadata> = (controlN
 };
 
 const recallControlNets: MetadataRecallFunc<ControlNetConfigMetadata[]> = (controlNets) => {
+  const { dispatch } = getStore();
+  dispatch(controlNetsReset());
   if (!controlNets.length) {
     return;
   }
-  const { dispatch } = getStore();
-  dispatch(controlNetsReset());
   controlNets.forEach((controlNet) => {
     dispatch(controlAdapterRecalled(controlNet));
   });
@@ -201,11 +207,11 @@ const recallT2IAdapter: MetadataRecallFunc<T2IAdapterConfigMetadata> = (t2iAdapt
 };
 
 const recallT2IAdapters: MetadataRecallFunc<T2IAdapterConfigMetadata[]> = (t2iAdapters) => {
+  const { dispatch } = getStore();
+  dispatch(t2iAdaptersReset());
   if (!t2iAdapters.length) {
     return;
   }
-  const { dispatch } = getStore();
-  dispatch(t2iAdaptersReset());
   t2iAdapters.forEach((t2iAdapter) => {
     dispatch(controlAdapterRecalled(t2iAdapter));
   });
@@ -216,11 +222,11 @@ const recallIPAdapter: MetadataRecallFunc<IPAdapterConfigMetadata> = (ipAdapter)
 };
 
 const recallIPAdapters: MetadataRecallFunc<IPAdapterConfigMetadata[]> = (ipAdapters) => {
+  const { dispatch } = getStore();
+  dispatch(ipAdaptersReset());
   if (!ipAdapters.length) {
     return;
   }
-  const { dispatch } = getStore();
-  dispatch(ipAdaptersReset());
   ipAdapters.forEach((ipAdapter) => {
     dispatch(controlAdapterRecalled(ipAdapter));
   });
@@ -235,6 +241,7 @@ export const recallers = {
   cfgScale: recallCFGScale,
   cfgRescaleMultiplier: recallCFGRescaleMultiplier,
   scheduler: recallScheduler,
+  initialImage: recallInitialImage,
   width: recallWidth,
   height: recallHeight,
   steps: recallSteps,

invokeai/frontend/web/src/features/modelManagerV2/subpanels/AddModelPanel/InstallModelForm.tsx

@@ -74,7 +74,6 @@ export const InstallModelForm = () => {
                 onClick={handleSubmit(onSubmit)}
                 isDisabled={!formState.dirtyFields.location}
                 isLoading={isLoading}
-                type="submit"
                 size="sm"
               >
                 {t('modelManager.install')}

invokeai/frontend/web/src/features/modelManagerV2/subpanels/ModelPanel/ControlNetOrT2IAdapterDefaultSettings/ControlNetOrT2IAdapterDefaultSettings.tsx

@@ -86,7 +86,6 @@ export const ControlNetOrT2IAdapterDefaultSettings = () => {
           colorScheme="invokeYellow"
           isDisabled={!formState.isDirty}
           onClick={handleSubmit(onSubmit)}
-          type="submit"
           isLoading={isLoadingUpdateModel}
         >
           {t('common.save')}

invokeai/frontend/web/src/features/modelManagerV2/subpanels/ModelPanel/MainModelDefaultSettings/MainModelDefaultSettings.tsx

@@ -116,7 +116,6 @@ export const MainModelDefaultSettings = () => {
           colorScheme="invokeYellow"
           isDisabled={!formState.isDirty}
           onClick={handleSubmit(onSubmit)}
-          type="submit"
           isLoading={isLoadingUpdateModel}
         >
           {t('common.save')}

invokeai/frontend/web/src/features/modelManagerV2/subpanels/ModelPanel/TriggerPhrases.tsx

@@ -88,7 +88,6 @@ export const TriggerPhrases = () => {
               <Button
                 leftIcon={<PiPlusBold />}
                 size="sm"
-                type="submit"
                 onClick={addTriggerPhrase}
                 isDisabled={!phrase || Boolean(errors.length)}
                 isLoading={isLoading}

invokeai/frontend/web/src/features/nodes/components/NodeEditor.tsx

@@ -3,6 +3,7 @@ import 'reactflow/dist/style.css';
 import { Flex } from '@invoke-ai/ui-library';
 import { IAINoContentFallback } from 'common/components/IAIImageFallback';
 import TopPanel from 'features/nodes/components/flow/panels/TopPanel/TopPanel';
+import { LoadWorkflowFromGraphModal } from 'features/workflowLibrary/components/LoadWorkflowFromGraphModal/LoadWorkflowFromGraphModal';
 import { SaveWorkflowAsDialog } from 'features/workflowLibrary/components/SaveWorkflowAsDialog/SaveWorkflowAsDialog';
 import type { AnimationProps } from 'framer-motion';
 import { AnimatePresence, motion } from 'framer-motion';
@@ -61,6 +62,7 @@ const NodeEditor = () => {
             <BottomLeftPanel />
             <MinimapPanel />
             <SaveWorkflowAsDialog />
+            <LoadWorkflowFromGraphModal />
           </motion.div>
         )}
       </AnimatePresence>

invokeai/frontend/web/src/features/nodes/components/flow/nodes/Invocation/fields/inputs/NumberFieldInputComponent.tsx

@@ -37,34 +37,50 @@ const NumberFieldInputComponent = (
   );
 
   const min = useMemo(() => {
+    let min = -NUMPY_RAND_MAX;
     if (!isNil(fieldTemplate.minimum)) {
-      return fieldTemplate.minimum;
+      min = fieldTemplate.minimum;
     }
     if (!isNil(fieldTemplate.exclusiveMinimum)) {
-      return fieldTemplate.exclusiveMinimum + 0.01;
+      min = fieldTemplate.exclusiveMinimum + 0.01;
     }
-    return;
+    return min;
   }, [fieldTemplate.exclusiveMinimum, fieldTemplate.minimum]);
 
   const max = useMemo(() => {
+    let max = NUMPY_RAND_MAX;
     if (!isNil(fieldTemplate.maximum)) {
-      return fieldTemplate.maximum;
+      max = fieldTemplate.maximum;
     }
     if (!isNil(fieldTemplate.exclusiveMaximum)) {
-      return fieldTemplate.exclusiveMaximum - 0.01;
+      max = fieldTemplate.exclusiveMaximum - 0.01;
     }
-    return;
+    return max;
   }, [fieldTemplate.exclusiveMaximum, fieldTemplate.maximum]);
 
+  const step = useMemo(() => {
+    if (isNil(fieldTemplate.multipleOf)) {
+      return isIntegerField ? 1 : 0.1;
+    }
+    return fieldTemplate.multipleOf;
+  }, [fieldTemplate.multipleOf, isIntegerField]);
+
+  const fineStep = useMemo(() => {
+    if (isNil(fieldTemplate.multipleOf)) {
+      return isIntegerField ? 1 : 0.01;
+    }
+    return fieldTemplate.multipleOf;
+  }, [fieldTemplate.multipleOf, isIntegerField]);
+
   return (
     <CompositeNumberInput
       defaultValue={fieldTemplate.default}
       onChange={handleValueChanged}
       value={field.value}
-      min={min ?? -NUMPY_RAND_MAX}
-      max={max ?? NUMPY_RAND_MAX}
-      step={isIntegerField ? 1 : 0.1}
-      fineStep={isIntegerField ? 1 : 0.01}
+      min={min}
+      max={max}
+      step={step}
+      fineStep={fineStep}
       className="nodrag"
     />
   );

invokeai/frontend/web/src/features/nodes/components/sidePanel/viewMode/EmptyState.tsx

@@ -1,7 +1,6 @@
 import { Button, Flex, Image, Text } from '@invoke-ai/ui-library';
 import { useAppDispatch } from 'app/store/storeHooks';
 import { workflowModeChanged } from 'features/nodes/store/workflowSlice';
-/** @knipignore */
 import InvokeLogoSVG from 'public/assets/images/invoke-symbol-wht-lrg.svg';
 import { useCallback } from 'react';
 import { useTranslation } from 'react-i18next';

invokeai/frontend/web/src/features/nodes/util/graph/addSDXLRefinerToGraph.ts

@@ -1,26 +1,18 @@
 import type { RootState } from 'app/store/store';
 import { fetchModelConfigWithTypeGuard } from 'features/metadata/util/modelFetchingHelpers';
-import {
-  type CreateDenoiseMaskInvocation,
-  type ImageDTO,
-  isRefinerMainModelModelConfig,
-  type NonNullableGraph,
-  type SeamlessModeInvocation,
-} from 'services/api/types';
+import type { NonNullableGraph, SeamlessModeInvocation } from 'services/api/types';
+import { isRefinerMainModelModelConfig } from 'services/api/types';
 
 import {
   CANVAS_OUTPUT,
-  INPAINT_IMAGE_RESIZE_UP,
+  INPAINT_CREATE_MASK,
   LATENTS_TO_IMAGE,
-  MASK_COMBINE,
-  MASK_RESIZE_UP,
   SDXL_CANVAS_IMAGE_TO_IMAGE_GRAPH,
   SDXL_CANVAS_INPAINT_GRAPH,
   SDXL_CANVAS_OUTPAINT_GRAPH,
   SDXL_CANVAS_TEXT_TO_IMAGE_GRAPH,
   SDXL_MODEL_LOADER,
   SDXL_REFINER_DENOISE_LATENTS,
-  SDXL_REFINER_INPAINT_CREATE_MASK,
   SDXL_REFINER_MODEL_LOADER,
   SDXL_REFINER_NEGATIVE_CONDITIONING,
   SDXL_REFINER_POSITIVE_CONDITIONING,
@@ -33,9 +25,7 @@ export const addSDXLRefinerToGraph = async (
   state: RootState,
   graph: NonNullableGraph,
   baseNodeId: string,
-  modelLoaderNodeId?: string,
-  canvasInitImage?: ImageDTO,
-  canvasMaskImage?: ImageDTO
+  modelLoaderNodeId?: string
 ): Promise<void> => {
   const {
     refinerModel,
@@ -51,11 +41,9 @@ export const addSDXLRefinerToGraph = async (
     return;
   }
 
-  const { seamlessXAxis, seamlessYAxis, vaePrecision } = state.generation;
+  const { seamlessXAxis, seamlessYAxis } = state.generation;
   const { boundingBoxScaleMethod } = state.canvas;
 
-  const fp32 = vaePrecision === 'fp32';
-
   const isUsingScaledDimensions = ['auto', 'manual'].includes(boundingBoxScaleMethod);
   const modelConfig = await fetchModelConfigWithTypeGuard(refinerModel.key, isRefinerMainModelModelConfig);
 
@@ -214,67 +202,9 @@ export const addSDXLRefinerToGraph = async (
   );
 
   if (graph.id === SDXL_CANVAS_INPAINT_GRAPH || graph.id === SDXL_CANVAS_OUTPAINT_GRAPH) {
-    graph.nodes[SDXL_REFINER_INPAINT_CREATE_MASK] = {
-      type: 'create_denoise_mask',
-      id: SDXL_REFINER_INPAINT_CREATE_MASK,
-      is_intermediate: true,
-      fp32,
-    };
-
-    if (isUsingScaledDimensions) {
-      graph.edges.push({
-        source: {
-          node_id: INPAINT_IMAGE_RESIZE_UP,
-          field: 'image',
-        },
-        destination: {
-          node_id: SDXL_REFINER_INPAINT_CREATE_MASK,
-          field: 'image',
-        },
-      });
-    } else {
-      graph.nodes[SDXL_REFINER_INPAINT_CREATE_MASK] = {
-        ...(graph.nodes[SDXL_REFINER_INPAINT_CREATE_MASK] as CreateDenoiseMaskInvocation),
-        image: canvasInitImage,
-      };
-    }
-
-    if (graph.id === SDXL_CANVAS_INPAINT_GRAPH) {
-      if (isUsingScaledDimensions) {
-        graph.edges.push({
-          source: {
-            node_id: MASK_RESIZE_UP,
-            field: 'image',
-          },
-          destination: {
-            node_id: SDXL_REFINER_INPAINT_CREATE_MASK,
-            field: 'mask',
-          },
-        });
-      } else {
-        graph.nodes[SDXL_REFINER_INPAINT_CREATE_MASK] = {
-          ...(graph.nodes[SDXL_REFINER_INPAINT_CREATE_MASK] as CreateDenoiseMaskInvocation),
-          mask: canvasMaskImage,
-        };
-      }
-    }
-
-    if (graph.id === SDXL_CANVAS_OUTPAINT_GRAPH) {
-      graph.edges.push({
-        source: {
-          node_id: isUsingScaledDimensions ? MASK_RESIZE_UP : MASK_COMBINE,
-          field: 'image',
-        },
-        destination: {
-          node_id: SDXL_REFINER_INPAINT_CREATE_MASK,
-          field: 'mask',
-        },
-      });
-    }
-
     graph.edges.push({
       source: {
-        node_id: SDXL_REFINER_INPAINT_CREATE_MASK,
+        node_id: INPAINT_CREATE_MASK,
         field: 'denoise_mask',
       },
       destination: {

invokeai/frontend/web/src/features/nodes/util/graph/addVAEToGraph.ts

@@ -17,7 +17,6 @@ import {
   SDXL_CANVAS_OUTPAINT_GRAPH,
   SDXL_CANVAS_TEXT_TO_IMAGE_GRAPH,
   SDXL_IMAGE_TO_IMAGE_GRAPH,
-  SDXL_REFINER_INPAINT_CREATE_MASK,
   SDXL_REFINER_SEAMLESS,
   SDXL_TEXT_TO_IMAGE_GRAPH,
   SEAMLESS,
@@ -166,27 +165,6 @@ export const addVAEToGraph = async (
     );
   }
 
-  if (refinerModel) {
-    if (graph.id === SDXL_CANVAS_INPAINT_GRAPH || graph.id === SDXL_CANVAS_OUTPAINT_GRAPH) {
-      graph.edges.push({
-        source: {
-          node_id: isSeamlessEnabled
-            ? isUsingRefiner
-              ? SDXL_REFINER_SEAMLESS
-              : SEAMLESS
-            : isAutoVae
-              ? modelLoaderNodeId
-              : VAE_LOADER,
-          field: 'vae',
-        },
-        destination: {
-          node_id: SDXL_REFINER_INPAINT_CREATE_MASK,
-          field: 'vae',
-        },
-      });
-    }
-  }
-
   if (vae) {
     upsertMetadata(graph, { vae });
   }

invokeai/frontend/web/src/features/nodes/util/graph/buildCanvasSDXLInpaintGraph.ts

@@ -133,7 +133,7 @@ export const buildCanvasSDXLInpaintGraph = async (
         id: INPAINT_CREATE_MASK,
         is_intermediate,
         coherence_mode: canvasCoherenceMode,
-        minimum_denoise: canvasCoherenceMinDenoise,
+        minimum_denoise: refinerModel ? Math.max(0.2, canvasCoherenceMinDenoise) : canvasCoherenceMinDenoise,
         edge_radius: canvasCoherenceEdgeSize,
       },
       [SDXL_DENOISE_LATENTS]: {
@@ -426,14 +426,7 @@ export const buildCanvasSDXLInpaintGraph = async (
 
   // Add Refiner if enabled
   if (refinerModel) {
-    await addSDXLRefinerToGraph(
-      state,
-      graph,
-      SDXL_DENOISE_LATENTS,
-      modelLoaderNodeId,
-      canvasInitImage,
-      canvasMaskImage
-    );
+    await addSDXLRefinerToGraph(state, graph, SDXL_DENOISE_LATENTS, modelLoaderNodeId);
     if (seamlessXAxis || seamlessYAxis) {
       modelLoaderNodeId = SDXL_REFINER_SEAMLESS;
     }

invokeai/frontend/web/src/features/nodes/util/graph/buildCanvasSDXLOutpaintGraph.ts

@@ -156,7 +156,7 @@ export const buildCanvasSDXLOutpaintGraph = async (
         is_intermediate,
         coherence_mode: canvasCoherenceMode,
         edge_radius: canvasCoherenceEdgeSize,
-        minimum_denoise: canvasCoherenceMinDenoise,
+        minimum_denoise: refinerModel ? Math.max(0.2, canvasCoherenceMinDenoise) : canvasCoherenceMinDenoise,
       },
       [SDXL_DENOISE_LATENTS]: {
         type: 'denoise_latents',
@@ -582,7 +582,7 @@ export const buildCanvasSDXLOutpaintGraph = async (
 
   // Add Refiner if enabled
   if (refinerModel) {
-    await addSDXLRefinerToGraph(state, graph, SDXL_DENOISE_LATENTS, modelLoaderNodeId, canvasInitImage);
+    await addSDXLRefinerToGraph(state, graph, SDXL_DENOISE_LATENTS, modelLoaderNodeId);
     if (seamlessXAxis || seamlessYAxis) {
       modelLoaderNodeId = SDXL_REFINER_SEAMLESS;
     }

invokeai/frontend/web/src/features/nodes/util/workflow/graphToWorkflow.ts

@@ -0,0 +1,148 @@
+import * as dagre from '@dagrejs/dagre';
+import { logger } from 'app/logging/logger';
+import { getStore } from 'app/store/nanostores/store';
+import { NODE_WIDTH } from 'features/nodes/types/constants';
+import type { FieldInputInstance } from 'features/nodes/types/field';
+import type { WorkflowV3 } from 'features/nodes/types/workflow';
+import { buildFieldInputInstance } from 'features/nodes/util/schema/buildFieldInputInstance';
+import { t } from 'i18next';
+import { forEach } from 'lodash-es';
+import type { NonNullableGraph } from 'services/api/types';
+import { v4 as uuidv4 } from 'uuid';
+
+/**
+ * Converts a graph to a workflow. This is a best-effort conversion and may not be perfect.
+ * For example, if a graph references an unknown node type, that node will be skipped.
+ * @param graph The graph to convert to a workflow
+ * @param autoLayout Whether to auto-layout the nodes using `dagre`. If false, nodes will be simply stacked on top of one another with an offset.
+ * @returns The workflow.
+ */
+export const graphToWorkflow = (graph: NonNullableGraph, autoLayout = true): WorkflowV3 => {
+  const invocationTemplates = getStore().getState().nodes.templates;
+
+  if (!invocationTemplates) {
+    throw new Error(t('app.storeNotInitialized'));
+  }
+
+  // Initialize the workflow
+  const workflow: WorkflowV3 = {
+    name: '',
+    author: '',
+    contact: '',
+    description: '',
+    meta: {
+      category: 'user',
+      version: '3.0.0',
+    },
+    notes: '',
+    tags: '',
+    version: '',
+    exposedFields: [],
+    edges: [],
+    nodes: [],
+  };
+
+  // Convert nodes
+  forEach(graph.nodes, (node) => {
+    const template = invocationTemplates[node.type];
+
+    // Skip missing node templates - this is a best-effort
+    if (!template) {
+      logger('nodes').warn(`Node type ${node.type} not found in invocationTemplates`);
+      return;
+    }
+
+    // Build field input instances for each attr
+    const inputs: Record<string, FieldInputInstance> = {};
+
+    forEach(node, (value, key) => {
+      // Ignore the non-input keys - I think this is all of them?
+      if (key === 'id' || key === 'type' || key === 'is_intermediate' || key === 'use_cache') {
+        return;
+      }
+
+      const inputTemplate = template.inputs[key];
+
+      // Skip missing input templates
+      if (!inputTemplate) {
+        logger('nodes').warn(`Input ${key} not found in template for node type ${node.type}`);
+        return;
+      }
+
+      // This _should_ be all we need to do!
+      const inputInstance = buildFieldInputInstance(node.id, inputTemplate);
+      inputInstance.value = value;
+      inputs[key] = inputInstance;
+    });
+
+    workflow.nodes.push({
+      id: node.id,
+      type: 'invocation',
+      position: { x: 0, y: 0 }, // we'll do layout later, just need something here
+      data: {
+        id: node.id,
+        type: node.type,
+        version: template.version,
+        label: '',
+        notes: '',
+        isOpen: true,
+        isIntermediate: node.is_intermediate ?? false,
+        useCache: node.use_cache ?? true,
+        inputs,
+      },
+    });
+  });
+
+  forEach(graph.edges, (edge) => {
+    workflow.edges.push({
+      id: uuidv4(), // we don't have edge IDs in the graph
+      type: 'default',
+      source: edge.source.node_id,
+      sourceHandle: edge.source.field,
+      target: edge.destination.node_id,
+      targetHandle: edge.destination.field,
+    });
+  });
+
+  if (autoLayout) {
+    // Best-effort auto layout via dagre - not perfect but better than nothing
+    const dagreGraph = new dagre.graphlib.Graph();
+    // `rankdir` and `align` could be tweaked, but it's gonna be janky no matter what we choose
+    dagreGraph.setGraph({ rankdir: 'TB', align: 'UL' });
+    dagreGraph.setDefaultEdgeLabel(() => ({}));
+
+    // We don't know the dimensions of the nodes until we load the graph into `reactflow` - use a reasonable value
+    forEach(graph.nodes, (node) => {
+      const width = NODE_WIDTH;
+      const height = NODE_WIDTH * 1.5;
+      dagreGraph.setNode(node.id, { width, height });
+    });
+
+    graph.edges.forEach((edge) => {
+      dagreGraph.setEdge(edge.source.node_id, edge.destination.node_id);
+    });
+
+    // This does the magic
+    dagre.layout(dagreGraph);
+
+    // Update the workflow now that we've got the positions
+    workflow.nodes.forEach((node) => {
+      const nodeWithPosition = dagreGraph.node(node.id);
+      node.position = {
+        x: nodeWithPosition.x - nodeWithPosition.width / 2,
+        y: nodeWithPosition.y - nodeWithPosition.height / 2,
+      };
+    });
+  } else {
+    // Stack nodes with a 50px,50px offset from the previous ndoe
+    let x = 0;
+    let y = 0;
+    workflow.nodes.forEach((node) => {
+      node.position = { x, y };
+      x = x + 50;
+      y = y + 50;
+    });
+  }
+
+  return workflow;
+};

invokeai/frontend/web/src/features/parameters/components/MainModel/ParamMainModelSelect.tsx

@@ -1,4 +1,4 @@
-import { Combobox, FormControl, FormLabel, Tooltip } from '@invoke-ai/ui-library';
+import { Box, Combobox, FormControl, FormLabel, Tooltip } from '@invoke-ai/ui-library';
 import { createMemoizedSelector } from 'app/store/createMemoizedSelector';
 import { useAppDispatch, useAppSelector } from 'app/store/storeHooks';
 import { InformationalPopover } from 'common/components/InformationalPopover/InformationalPopover';
@@ -46,20 +46,22 @@ const ParamMainModelSelect = () => {
   });
 
   return (
-    <Tooltip label={tooltipLabel}>
-      <FormControl isDisabled={!modelConfigs.length} isInvalid={!value || !modelConfigs.length}>
-        <InformationalPopover feature="paramModel">
-          <FormLabel>{t('modelManager.model')}</FormLabel>
-        </InformationalPopover>
-        <Combobox
-          value={value}
-          placeholder={placeholder}
-          options={options}
-          onChange={onChange}
-          noOptionsMessage={noOptionsMessage}
-        />
-      </FormControl>
-    </Tooltip>
+    <FormControl isDisabled={!modelConfigs.length} isInvalid={!value || !modelConfigs.length}>
+      <InformationalPopover feature="paramModel">
+        <FormLabel>{t('modelManager.model')}</FormLabel>
+      </InformationalPopover>
+      <Tooltip label={tooltipLabel}>
+        <Box w="full">
+          <Combobox
+            value={value}
+            placeholder={placeholder}
+            options={options}
+            onChange={onChange}
+            noOptionsMessage={noOptionsMessage}
+          />
+        </Box>
+      </Tooltip>
+    </FormControl>
   );
 };
 

invokeai/frontend/web/src/features/settingsAccordions/components/ImageSettingsAccordion/ImageSettingsAccordion.tsx

@@ -29,6 +29,7 @@ const selector = createMemoizedSelector(
     const { shouldRandomizeSeed, model } = generation;
     const { hrfEnabled } = hrf;
     const badges: string[] = [];
+    const isSDXL = model?.base === 'sdxl';
 
     if (activeTabName === 'unifiedCanvas') {
       const {
@@ -53,10 +54,10 @@ const selector = createMemoizedSelector(
       badges.push('Manual Seed');
     }
 
-    if (hrfEnabled) {
+    if (hrfEnabled && !isSDXL) {
       badges.push('HiRes Fix');
     }
-    return { badges, activeTabName, isSDXL: model?.base === 'sdxl' };
+    return { badges, activeTabName, isSDXL };
   }
 );
 

invokeai/frontend/web/src/features/system/components/AboutModal/AboutModal.tsx

@@ -21,7 +21,6 @@ import {
 import ScrollableContent from 'common/components/OverlayScrollbars/ScrollableContent';
 import { discordLink, githubLink, websiteLink } from 'features/system/store/constants';
 import { map } from 'lodash-es';
-/** @knipignore */
 import InvokeLogoYellow from 'public/assets/images/invoke-tag-lrg.svg';
 import type { ReactElement } from 'react';
 import { cloneElement, memo, useCallback } from 'react';

invokeai/frontend/web/src/features/system/components/InvokeAILogoComponent.tsx

@@ -2,7 +2,6 @@
 import { Image, Text, Tooltip } from '@invoke-ai/ui-library';
 import { useStore } from '@nanostores/react';
 import { $logo } from 'app/store/nanostores/logo';
-/** @knipignore */
 import InvokeLogoYellow from 'public/assets/images/invoke-symbol-ylw-lrg.svg';
 import { memo, useMemo, useRef } from 'react';
 import { useGetAppVersionQuery } from 'services/api/endpoints/appInfo';

invokeai/frontend/web/src/features/workflowLibrary/components/LoadWorkflowFromGraphModal/LoadWorkflowFromGraphModal.tsx

@@ -0,0 +1,111 @@
+import {
+  Button,
+  Checkbox,
+  Flex,
+  FormControl,
+  FormLabel,
+  Modal,
+  ModalBody,
+  ModalCloseButton,
+  ModalContent,
+  ModalHeader,
+  ModalOverlay,
+  Spacer,
+  Textarea,
+} from '@invoke-ai/ui-library';
+import { useStore } from '@nanostores/react';
+import { useAppDispatch } from 'app/store/storeHooks';
+import { workflowLoadRequested } from 'features/nodes/store/actions';
+import { graphToWorkflow } from 'features/nodes/util/workflow/graphToWorkflow';
+import { atom } from 'nanostores';
+import type { ChangeEvent } from 'react';
+import { useCallback, useState } from 'react';
+import { useTranslation } from 'react-i18next';
+
+const $isOpen = atom<boolean>(false);
+
+export const useLoadWorkflowFromGraphModal = () => {
+  const isOpen = useStore($isOpen);
+  const onOpen = useCallback(() => {
+    $isOpen.set(true);
+  }, []);
+  const onClose = useCallback(() => {
+    $isOpen.set(false);
+  }, []);
+
+  return { isOpen, onOpen, onClose };
+};
+
+export const LoadWorkflowFromGraphModal = () => {
+  const { t } = useTranslation();
+  const dispatch = useAppDispatch();
+  const { isOpen, onClose } = useLoadWorkflowFromGraphModal();
+  const [graphRaw, setGraphRaw] = useState<string>('');
+  const [workflowRaw, setWorkflowRaw] = useState<string>('');
+  const [shouldAutoLayout, setShouldAutoLayout] = useState(true);
+  const onChangeGraphRaw = useCallback((e: ChangeEvent<HTMLTextAreaElement>) => {
+    setGraphRaw(e.target.value);
+  }, []);
+  const onChangeWorkflowRaw = useCallback((e: ChangeEvent<HTMLTextAreaElement>) => {
+    setWorkflowRaw(e.target.value);
+  }, []);
+  const onChangeShouldAutoLayout = useCallback((e: ChangeEvent<HTMLInputElement>) => {
+    setShouldAutoLayout(e.target.checked);
+  }, []);
+  const parse = useCallback(() => {
+    const graph = JSON.parse(graphRaw);
+    const workflow = graphToWorkflow(graph, shouldAutoLayout);
+    setWorkflowRaw(JSON.stringify(workflow, null, 2));
+  }, [graphRaw, shouldAutoLayout]);
+  const loadWorkflow = useCallback(() => {
+    const workflow = JSON.parse(workflowRaw);
+    dispatch(workflowLoadRequested({ workflow, asCopy: true }));
+    onClose();
+  }, [dispatch, onClose, workflowRaw]);
+  return (
+    <Modal isOpen={isOpen} onClose={onClose} isCentered>
+      <ModalOverlay />
+      <ModalContent w="80vw" h="80vh" maxW="unset" maxH="unset">
+        <ModalHeader>{t('workflows.loadFromGraph')}</ModalHeader>
+        <ModalCloseButton />
+        <ModalBody as={Flex} flexDir="column" gap={4} w="full" h="full" pb={4}>
+          <Flex gap={4}>
+            <Button onClick={parse} size="sm" flexShrink={0}>
+              {t('workflows.convertGraph')}
+            </Button>
+            <FormControl>
+              <FormLabel>{t('workflows.autoLayout')}</FormLabel>
+              <Checkbox isChecked={shouldAutoLayout} onChange={onChangeShouldAutoLayout} />
+            </FormControl>
+            <Spacer />
+            <Button onClick={loadWorkflow} size="sm" flexShrink={0}>
+              {t('workflows.loadWorkflow')}
+            </Button>
+          </Flex>
+          <FormControl orientation="vertical" h="50%">
+            <FormLabel>{t('nodes.graph')}</FormLabel>
+            <Textarea
+              h="full"
+              value={graphRaw}
+              fontFamily="monospace"
+              whiteSpace="pre-wrap"
+              overflowWrap="normal"
+              onChange={onChangeGraphRaw}
+            />
+          </FormControl>
+          <FormControl orientation="vertical" h="50%">
+            <FormLabel>{t('nodes.workflow')}</FormLabel>
+            <Textarea
+              h="full"
+              value={workflowRaw}
+              fontFamily="monospace"
+              whiteSpace="pre-wrap"
+              overflowWrap="normal"
+              onChange={onChangeWorkflowRaw}
+            />
+          </FormControl>
+        </ModalBody>
+      </ModalContent>
+    </Modal>
+  );
+};

invokeai/frontend/web/src/features/workflowLibrary/components/WorkflowLibraryMenu/LoadWorkflowFromGraphMenuItem.tsx

@@ -0,0 +1,18 @@
+import { MenuItem } from '@invoke-ai/ui-library';
+import { useLoadWorkflowFromGraphModal } from 'features/workflowLibrary/components/LoadWorkflowFromGraphModal/LoadWorkflowFromGraphModal';
+import { memo } from 'react';
+import { useTranslation } from 'react-i18next';
+import { PiFlaskBold } from 'react-icons/pi';
+
+const LoadWorkflowFromGraphMenuItem = () => {
+  const { t } = useTranslation();
+  const { onOpen } = useLoadWorkflowFromGraphModal();
+
+  return (
+    <MenuItem as="button" icon={<PiFlaskBold />} onClick={onOpen}>
+      {t('workflows.loadFromGraph')}
+    </MenuItem>
+  );
+};
+
+export default memo(LoadWorkflowFromGraphMenuItem);

invokeai/frontend/web/src/features/workflowLibrary/components/WorkflowLibraryMenu/WorkflowLibraryMenu.tsx

@@ -6,8 +6,10 @@ import {
   MenuList,
   useDisclosure,
   useGlobalMenuClose,
+  useShiftModifier,
 } from '@invoke-ai/ui-library';
 import DownloadWorkflowMenuItem from 'features/workflowLibrary/components/WorkflowLibraryMenu/DownloadWorkflowMenuItem';
+import LoadWorkflowFromGraphMenuItem from 'features/workflowLibrary/components/WorkflowLibraryMenu/LoadWorkflowFromGraphMenuItem';
 import { NewWorkflowMenuItem } from 'features/workflowLibrary/components/WorkflowLibraryMenu/NewWorkflowMenuItem';
 import SaveWorkflowAsMenuItem from 'features/workflowLibrary/components/WorkflowLibraryMenu/SaveWorkflowAsMenuItem';
 import SaveWorkflowMenuItem from 'features/workflowLibrary/components/WorkflowLibraryMenu/SaveWorkflowMenuItem';
@@ -20,6 +22,7 @@ import { PiDotsThreeOutlineFill } from 'react-icons/pi';
 const WorkflowLibraryMenu = () => {
   const { t } = useTranslation();
   const { isOpen, onOpen, onClose } = useDisclosure();
+  const shift = useShiftModifier();
   useGlobalMenuClose(onClose);
   return (
     <Menu isOpen={isOpen} onOpen={onOpen} onClose={onClose}>
@@ -38,6 +41,8 @@ const WorkflowLibraryMenu = () => {
         <DownloadWorkflowMenuItem />
         <MenuDivider />
         <SettingsMenuItem />
+        {shift && <MenuDivider />}
+        {shift && <LoadWorkflowFromGraphMenuItem />}
       </MenuList>
     </Menu>
   );

invokeai/frontend/web/src/services/api/types.ts

@@ -134,7 +134,6 @@ export type CollectInvocation = S['CollectInvocation'];
 export type ImageResizeInvocation = S['ImageResizeInvocation'];
 export type InfillPatchMatchInvocation = S['InfillPatchMatchInvocation'];
 export type InfillTileInvocation = S['InfillTileInvocation'];
-export type CreateDenoiseMaskInvocation = S['CreateDenoiseMaskInvocation'];
 export type CreateGradientMaskInvocation = S['CreateGradientMaskInvocation'];
 export type CanvasPasteBackInvocation = S['CanvasPasteBackInvocation'];
 export type NoiseInvocation = S['NoiseInvocation'];

invokeai/invocation_api/__init__.py

@@ -27,6 +27,7 @@ from invokeai.app.invocations.fields import (
     OutputField,
     UIComponent,
     UIType,
+    WithBoard,
     WithMetadata,
     WithWorkflow,
 )
@@ -75,7 +76,6 @@ from invokeai.backend.stable_diffusion.diffusers_pipeline import PipelineInterme
 from invokeai.backend.stable_diffusion.diffusion.conditioning_data import (
     BasicConditioningInfo,
     ConditioningFieldData,
-    ExtraConditioningInfo,
     SDXLConditioningInfo,
 )
 from invokeai.backend.util.devices import CPU_DEVICE, CUDA_DEVICE, MPS_DEVICE, choose_precision, choose_torch_device
@@ -105,6 +105,7 @@ __all__ = [
     "OutputField",
     "UIComponent",
     "UIType",
+    "WithBoard",
     "WithMetadata",
     "WithWorkflow",
     # invokeai.app.invocations.latent
@@ -149,7 +150,6 @@ __all__ = [
     # invokeai.backend.stable_diffusion.diffusion.conditioning_data
     "BasicConditioningInfo",
     "ConditioningFieldData",
-    "ExtraConditioningInfo",
     "SDXLConditioningInfo",
     # invokeai.backend.stable_diffusion.diffusers_pipeline
     "PipelineIntermediateState",

invokeai/version/invokeai_version.py

@@ -1 +1 @@
-__version__ = "4.0.3"
+__version__ = "4.0.4"

pyproject.toml

@@ -33,7 +33,7 @@ classifiers = [
 ]
 dependencies = [
   # Core generation dependencies, pinned for reproducible builds.
-  "accelerate==0.28.0",
+  "accelerate==0.29.2",
   "clip_anytorch==2.5.2",       # replacing "clip @ https://github.com/openai/CLIP/archive/eaa22acb90a5876642d0507623e859909230a52d.zip",
   "compel==2.0.2",
   "controlnet-aux==0.0.7",
@@ -47,16 +47,16 @@ dependencies = [
   "pytorch-lightning==2.1.3",
   "safetensors==0.4.2",
   "timm==0.6.13",               # needed to override timm latest in controlnet_aux, see  https://github.com/isl-org/ZoeDepth/issues/26
-  "torch==2.2.1",
+  "torch==2.2.2",
   "torchmetrics==0.11.4",
   "torchsde==0.2.6",
-  "torchvision==0.17.1",
-  "transformers==4.39.1",
+  "torchvision==0.17.2",
+  "transformers==4.39.3",
 
   # Core application dependencies, pinned for reproducible builds.
   "fastapi-events==0.11.0",
   "fastapi==0.110.0",
-  "huggingface-hub==0.21.4",
+  "huggingface-hub==0.22.2",
   "pydantic-settings==2.2.1",
   "pydantic==2.6.3",
   "python-socketio==5.11.1",
@@ -96,7 +96,7 @@ dependencies = [
 [project.optional-dependencies]
 "xformers" = [
   # Core generation dependencies, pinned for reproducible builds.
-  "xformers==0.0.25; sys_platform!='darwin'",
+  "xformers==0.0.25post1; sys_platform!='darwin'",
   # Auxiliary dependencies, pinned only if necessary.
   "triton; sys_platform=='linux'",
 ]
@@ -256,7 +256,6 @@ module = [
   "invokeai.backend.model_management.seamless",
   "invokeai.backend.model_management.util",
   "invokeai.backend.stable_diffusion.diffusers_pipeline",
-  "invokeai.backend.stable_diffusion.diffusion.cross_attention_control",
   "invokeai.backend.stable_diffusion.diffusion.shared_invokeai_diffusion",
   "invokeai.backend.util.hotfixes",
   "invokeai.backend.util.mps_fixes",

tests/app/services/model_install/test_model_install.py

@@ -3,6 +3,7 @@ Test the model installer
 """
 
 import platform
+import time
 import uuid
 from pathlib import Path
 from typing import Any, Dict
@@ -255,6 +256,10 @@ def test_huggingface_download(mm2_installer: ModelInstallServiceBase, mm2_app_co
     assert isinstance(bus, EventServiceBase)
     assert store is not None
 
+    # test hypothesis that there is a race condition between
+    # creating temporary directory and downloading into it.
+    time.sleep(2)  
+    
     job = mm2_installer.import_model(source)
     job_list = mm2_installer.wait_for_installs(timeout=10)
     assert len(job_list) == 1

tests/backend/ip_adapter/test_ip_adapter.py

@@ -1,8 +1,8 @@
 import pytest
 import torch
 
-from invokeai.backend.ip_adapter.unet_patcher import UNetPatcher
 from invokeai.backend.model_manager import BaseModelType, ModelType, SubModelType
+from invokeai.backend.stable_diffusion.diffusion.unet_attention_patcher import UNetAttentionPatcher
 from invokeai.backend.util.test_utils import install_and_load_model
 
 
@@ -77,7 +77,7 @@ def test_ip_adapter_unet_patch(model_params, model_installer, torch_device):
         ip_embeds = torch.randn((1, 3, 4, 768)).to(torch_device)
 
         cross_attention_kwargs = {"ip_adapter_image_prompt_embeds": [ip_embeds]}
-        ip_adapter_unet_patcher = UNetPatcher([ip_adapter])
+        ip_adapter_unet_patcher = UNetAttentionPatcher([ip_adapter])
         with ip_adapter_unet_patcher.apply_ip_adapter_attention(unet):
             output = unet(**dummy_unet_input, cross_attention_kwargs=cross_attention_kwargs).sample