InvokeAI 4.2.4__tar.gz → 4.2.5__tar.gz

{InvokeAI-4.2.4 → InvokeAI-4.2.5}/InvokeAI.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: InvokeAI
-Version: 4.2.4
+Version: 4.2.5
 Summary: An implementation of Stable Diffusion which provides various new features and options to aid the image generation process
 Author-email: The InvokeAI Project <lincoln.stein@gmail.com>
 License:                                  Apache License

{InvokeAI-4.2.4 → InvokeAI-4.2.5}/InvokeAI.egg-info/SOURCES.txt

@@ -27,17 +27,24 @@ invokeai/app/api/routers/workflows.py
 invokeai/app/assets/images/caution.png
 invokeai/app/invocations/__init__.py
 invokeai/app/invocations/baseinvocation.py
+invokeai/app/invocations/blend_latents.py
 invokeai/app/invocations/collections.py
 invokeai/app/invocations/compel.py
 invokeai/app/invocations/constants.py
 invokeai/app/invocations/controlnet_image_processors.py
+invokeai/app/invocations/create_denoise_mask.py
+invokeai/app/invocations/create_gradient_mask.py
+invokeai/app/invocations/crop_latents.py
 invokeai/app/invocations/cv.py
+invokeai/app/invocations/denoise_latents.py
 invokeai/app/invocations/facetools.py
 invokeai/app/invocations/fields.py
+invokeai/app/invocations/ideal_size.py
 invokeai/app/invocations/image.py
+invokeai/app/invocations/image_to_latents.py
 invokeai/app/invocations/infill.py
 invokeai/app/invocations/ip_adapter.py
-invokeai/app/invocations/latent.py
+invokeai/app/invocations/latents_to_image.py
 invokeai/app/invocations/mask.py
 invokeai/app/invocations/math.py
 invokeai/app/invocations/metadata.py
@@ -46,9 +53,12 @@ invokeai/app/invocations/noise.py
 invokeai/app/invocations/param_easing.py
 invokeai/app/invocations/primitives.py
 invokeai/app/invocations/prompt.py
+invokeai/app/invocations/resize_latents.py
+invokeai/app/invocations/scheduler.py
 invokeai/app/invocations/sdxl.py
 invokeai/app/invocations/strings.py
 invokeai/app/invocations/t2i_adapter.py
+invokeai/app/invocations/tiled_multi_diffusion_denoise_latents.py
 invokeai/app/invocations/tiles.py
 invokeai/app/invocations/upscale.py
 invokeai/app/invocations/util.py
@@ -156,6 +166,7 @@ invokeai/app/services/shared/sqlite_migrator/sqlite_migrator_impl.py
 invokeai/app/services/shared/sqlite_migrator/migrations/__init__.py
 invokeai/app/services/shared/sqlite_migrator/migrations/migration_1.py
 invokeai/app/services/shared/sqlite_migrator/migrations/migration_10.py
+invokeai/app/services/shared/sqlite_migrator/migrations/migration_11.py
 invokeai/app/services/shared/sqlite_migrator/migrations/migration_2.py
 invokeai/app/services/shared/sqlite_migrator/migrations/migration_3.py
 invokeai/app/services/shared/sqlite_migrator/migrations/migration_4.py
@@ -184,7 +195,6 @@ invokeai/app/shared/models.py
 invokeai/app/util/__init__.py
 invokeai/app/util/controlnet_utils.py
 invokeai/app/util/custom_openapi.py
-invokeai/app/util/download_with_progress.py
 invokeai/app/util/metaenum.py
 invokeai/app/util/misc.py
 invokeai/app/util/model_exclude_null.py
@@ -231,6 +241,7 @@ invokeai/backend/ip_adapter/__init__.py
 invokeai/backend/ip_adapter/ip_adapter.py
 invokeai/backend/ip_adapter/ip_attention_weights.py
 invokeai/backend/ip_adapter/resampler.py
+invokeai/backend/model_hash/hash_validator.py
 invokeai/backend/model_hash/model_hash.py
 invokeai/backend/model_manager/__init__.py
 invokeai/backend/model_manager/config.py
@@ -274,6 +285,7 @@ invokeai/backend/model_manager/util/select_hf_files.py
 invokeai/backend/onnx/onnx_runtime.py
 invokeai/backend/stable_diffusion/__init__.py
 invokeai/backend/stable_diffusion/diffusers_pipeline.py
+invokeai/backend/stable_diffusion/multi_diffusion_pipeline.py
 invokeai/backend/stable_diffusion/seamless.py
 invokeai/backend/stable_diffusion/diffusion/__init__.py
 invokeai/backend/stable_diffusion/diffusion/conditioning_data.py
@@ -322,11 +334,11 @@ invokeai/frontend/install/__init__.py
 invokeai/frontend/install/import_images.py
 invokeai/frontend/web/__init__.py
 invokeai/frontend/web/dist/index.html
+invokeai/frontend/web/dist/assets/App-D-nTCJ_n.js
 invokeai/frontend/web/dist/assets/App-DEu4J2pT.css
-invokeai/frontend/web/dist/assets/App-IufUCLxZ.js
-invokeai/frontend/web/dist/assets/ThemeLocaleProvider-CQIRp5vD.js
+invokeai/frontend/web/dist/assets/ThemeLocaleProvider-C00Wxn4y.js
 invokeai/frontend/web/dist/assets/ThemeLocaleProvider-DzjsLZSc.css
-invokeai/frontend/web/dist/assets/index-CSQTzMJa.js
+invokeai/frontend/web/dist/assets/index--24GrIy3.js
 invokeai/frontend/web/dist/assets/inter-cyrillic-ext-wght-normal-DIEz8p5i.woff2
 invokeai/frontend/web/dist/assets/inter-cyrillic-wght-normal-BmJJXa8e.woff2
 invokeai/frontend/web/dist/assets/inter-greek-ext-wght-normal-D5AYLNiq.woff2

{InvokeAI-4.2.4 → InvokeAI-4.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: InvokeAI
-Version: 4.2.4
+Version: 4.2.5
 Summary: An implementation of Stable Diffusion which provides various new features and options to aid the image generation process
 Author-email: The InvokeAI Project <lincoln.stein@gmail.com>
 License:                                  Apache License

{InvokeAI-4.2.4 → InvokeAI-4.2.5}/invokeai/app/api/dependencies.py

@@ -93,7 +93,7 @@ class ApiDependencies:
         conditioning = ObjectSerializerForwardCache(
             ObjectSerializerDisk[ConditioningFieldData](output_folder / "conditioning", ephemeral=True)
         )
-        download_queue_service = DownloadQueueService(event_bus=events)
+        download_queue_service = DownloadQueueService(app_config=configuration, event_bus=events)
         model_images_service = ModelImageFileStorageDisk(model_images_folder / "model_images")
         model_manager = ModelManagerService.build_model_manager(
             app_config=configuration,

{InvokeAI-4.2.4 → InvokeAI-4.2.5}/invokeai/app/api/routers/model_manager.py

@@ -9,7 +9,7 @@ from copy import deepcopy
 from typing import Any, Dict, List, Optional, Type
 
 from fastapi import Body, Path, Query, Response, UploadFile
-from fastapi.responses import FileResponse
+from fastapi.responses import FileResponse, HTMLResponse
 from fastapi.routing import APIRouter
 from PIL import Image
 from pydantic import AnyHttpUrl, BaseModel, ConfigDict, Field
@@ -502,6 +502,133 @@ async def install_model(
     return result
 
 
+@model_manager_router.get(
+    "/install/huggingface",
+    operation_id="install_hugging_face_model",
+    responses={
+        201: {"description": "The model is being installed"},
+        400: {"description": "Bad request"},
+        409: {"description": "There is already a model corresponding to this path or repo_id"},
+    },
+    status_code=201,
+    response_class=HTMLResponse,
+)
+async def install_hugging_face_model(
+    source: str = Query(description="HuggingFace repo_id to install"),
+) -> HTMLResponse:
+    """Install a Hugging Face model using a string identifier."""
+
+    def generate_html(title: str, heading: str, repo_id: str, is_error: bool, message: str | None = "") -> str:
+        if message:
+            message = f"<p>{message}</p>"
+        title_class = "error" if is_error else "success"
+        return f"""
+            <html>
+
+            <head>
+                <title>{title}</title>
+                <style>
+                    body {{
+                        text-align: center;
+                        background-color: hsl(220 12% 10% / 1);
+                        font-family: Helvetica, sans-serif;
+                        color: hsl(220 12% 86% / 1);
+                    }}
+
+                    .repo-id {{
+                        color: hsl(220 12% 68% / 1);
+                    }}
+
+                    .error {{
+                        color: hsl(0 42% 68% / 1)
+                    }}
+
+                    .message-box {{
+                        display: inline-block;
+                        border-radius: 5px;
+                        background-color: hsl(220 12% 20% / 1);
+                        padding-inline-end: 30px;
+                        padding: 20px;
+                        padding-inline-start: 30px;
+                        padding-inline-end: 30px;
+                    }}
+
+                    .container {{
+                        display: flex;
+                        width: 100%;
+                        height: 100%;
+                        align-items: center;
+                        justify-content: center;
+                    }}
+
+                    a {{
+                        color: inherit
+                    }}
+
+                    a:visited {{
+                        color: inherit
+                    }}
+
+                    a:active {{
+                        color: inherit
+                    }}
+                </style>
+            </head>
+
+            <body style="background-color: hsl(220 12% 10% / 1);">
+                <div class="container">
+                    <div class="message-box">
+                        <h2 class="{title_class}">{heading}</h2>
+                        {message}
+                        <p class="repo-id">Repo ID: {repo_id}</p>
+                    </div>
+                </div>
+            </body>
+
+            </html>
+        """
+
+    try:
+        metadata = HuggingFaceMetadataFetch().from_id(source)
+        assert isinstance(metadata, ModelMetadataWithFiles)
+    except UnknownMetadataException:
+        title = "Unable to Install Model"
+        heading = "No HuggingFace repository found with that repo ID."
+        message = "Ensure the repo ID is correct and try again."
+        return HTMLResponse(content=generate_html(title, heading, source, True, message), status_code=400)
+
+    logger = ApiDependencies.invoker.services.logger
+
+    try:
+        installer = ApiDependencies.invoker.services.model_manager.install
+        if metadata.is_diffusers:
+            installer.heuristic_import(
+                source=source,
+                inplace=False,
+            )
+        elif metadata.ckpt_urls is not None and len(metadata.ckpt_urls) == 1:
+            installer.heuristic_import(
+                source=str(metadata.ckpt_urls[0]),
+                inplace=False,
+            )
+        else:
+            title = "Unable to Install Model"
+            heading = "This HuggingFace repo has multiple models."
+            message = "Please use the Model Manager to install this model."
+            return HTMLResponse(content=generate_html(title, heading, source, True, message), status_code=200)
+
+        title = "Model Install Started"
+        heading = "Your HuggingFace model is installing now."
+        message = "You can close this tab and check the Model Manager for installation progress."
+        return HTMLResponse(content=generate_html(title, heading, source, False, message), status_code=201)
+    except Exception as e:
+        logger.error(str(e))
+        title = "Unable to Install Model"
+        heading = "There was an problem installing this model."
+        message = 'Please use the Model Manager directly to install this model. If the issue persists, ask for help on <a href="https://discord.gg/ZmtBAhwWhy">discord</a>.'
+        return HTMLResponse(content=generate_html(title, heading, source, True, message), status_code=500)
+
+
 @model_manager_router.get(
     "/install",
     operation_id="list_model_installs",

InvokeAI-4.2.5/invokeai/app/invocations/blend_latents.py

@@ -0,0 +1,98 @@
+from typing import Any, Union
+
+import numpy as np
+import numpy.typing as npt
+import torch
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, invocation
+from invokeai.app.invocations.fields import FieldDescriptions, Input, InputField, LatentsField
+from invokeai.app.invocations.primitives import LatentsOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.util.devices import TorchDevice
+
+
+@invocation(
+    "lblend",
+    title="Blend Latents",
+    tags=["latents", "blend"],
+    category="latents",
+    version="1.0.3",
+)
+class BlendLatentsInvocation(BaseInvocation):
+    """Blend two latents using a given alpha. Latents must have same size."""
+
+    latents_a: LatentsField = InputField(
+        description=FieldDescriptions.latents,
+        input=Input.Connection,
+    )
+    latents_b: LatentsField = InputField(
+        description=FieldDescriptions.latents,
+        input=Input.Connection,
+    )
+    alpha: float = InputField(default=0.5, description=FieldDescriptions.blend_alpha)
+
+    def invoke(self, context: InvocationContext) -> LatentsOutput:
+        latents_a = context.tensors.load(self.latents_a.latents_name)
+        latents_b = context.tensors.load(self.latents_b.latents_name)
+
+        if latents_a.shape != latents_b.shape:
+            raise Exception("Latents to blend must be the same size.")
+
+        device = TorchDevice.choose_torch_device()
+
+        def slerp(
+            t: Union[float, npt.NDArray[Any]],  # FIXME: maybe use np.float32 here?
+            v0: Union[torch.Tensor, npt.NDArray[Any]],
+            v1: Union[torch.Tensor, npt.NDArray[Any]],
+            DOT_THRESHOLD: float = 0.9995,
+        ) -> Union[torch.Tensor, npt.NDArray[Any]]:
+            """
+            Spherical linear interpolation
+            Args:
+                t (float/np.ndarray): Float value between 0.0 and 1.0
+                v0 (np.ndarray): Starting vector
+                v1 (np.ndarray): Final vector
+                DOT_THRESHOLD (float): Threshold for considering the two vectors as
+                                    colineal. Not recommended to alter this.
+            Returns:
+                v2 (np.ndarray): Interpolation vector between v0 and v1
+            """
+            inputs_are_torch = False
+            if not isinstance(v0, np.ndarray):
+                inputs_are_torch = True
+                v0 = v0.detach().cpu().numpy()
+            if not isinstance(v1, np.ndarray):
+                inputs_are_torch = True
+                v1 = v1.detach().cpu().numpy()
+
+            dot = np.sum(v0 * v1 / (np.linalg.norm(v0) * np.linalg.norm(v1)))
+            if np.abs(dot) > DOT_THRESHOLD:
+                v2 = (1 - t) * v0 + t * v1
+            else:
+                theta_0 = np.arccos(dot)
+                sin_theta_0 = np.sin(theta_0)
+                theta_t = theta_0 * t
+                sin_theta_t = np.sin(theta_t)
+                s0 = np.sin(theta_0 - theta_t) / sin_theta_0
+                s1 = sin_theta_t / sin_theta_0
+                v2 = s0 * v0 + s1 * v1
+
+            if inputs_are_torch:
+                v2_torch: torch.Tensor = torch.from_numpy(v2).to(device)
+                return v2_torch
+            else:
+                assert isinstance(v2, np.ndarray)
+                return v2
+
+        # blend
+        bl = slerp(self.alpha, latents_a, latents_b)
+        assert isinstance(bl, torch.Tensor)
+        blended_latents: torch.Tensor = bl  # for type checking convenience
+
+        # https://discuss.huggingface.co/t/memory-usage-by-later-pipeline-stages/23699
+        blended_latents = blended_latents.to("cpu")
+
+        TorchDevice.empty_cache()
+
+        name = context.tensors.save(tensor=blended_latents)
+        return LatentsOutput.build(latents_name=name, latents=blended_latents, seed=self.latents_a.seed)

{InvokeAI-4.2.4 → InvokeAI-4.2.5}/invokeai/app/invocations/compel.py

@@ -81,9 +81,13 @@ class CompelInvocation(BaseInvocation):
 
         with (
             # apply all patches while the model is on the target device
-            text_encoder_info as text_encoder,
+            text_encoder_info.model_on_device() as (model_state_dict, text_encoder),
             tokenizer_info as tokenizer,
-            ModelPatcher.apply_lora_text_encoder(text_encoder, _lora_loader()),
+            ModelPatcher.apply_lora_text_encoder(
+                text_encoder,
+                loras=_lora_loader(),
+                model_state_dict=model_state_dict,
+            ),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
             ModelPatcher.apply_clip_skip(text_encoder, self.clip.skipped_layers),
             ModelPatcher.apply_ti(tokenizer, text_encoder, ti_list) as (
@@ -172,9 +176,14 @@ class SDXLPromptInvocationBase:
 
         with (
             # apply all patches while the model is on the target device
-            text_encoder_info as text_encoder,
+            text_encoder_info.model_on_device() as (state_dict, text_encoder),
             tokenizer_info as tokenizer,
-            ModelPatcher.apply_lora(text_encoder, _lora_loader(), lora_prefix),
+            ModelPatcher.apply_lora(
+                text_encoder,
+                loras=_lora_loader(),
+                prefix=lora_prefix,
+                model_state_dict=state_dict,
+            ),
             # Apply CLIP Skip after LoRA to prevent LoRA application from failing on skipped layers.
             ModelPatcher.apply_clip_skip(text_encoder, clip_field.skipped_layers),
             ModelPatcher.apply_ti(tokenizer, text_encoder, ti_list) as (

{InvokeAI-4.2.4 → InvokeAI-4.2.5}/invokeai/app/invocations/constants.py

@@ -1,6 +1,7 @@
 from typing import Literal
 
 from invokeai.backend.stable_diffusion.schedulers import SCHEDULER_MAP
+from invokeai.backend.util.devices import TorchDevice
 
 LATENT_SCALE_FACTOR = 8
 """
@@ -15,3 +16,5 @@ SCHEDULER_NAME_VALUES = Literal[tuple(SCHEDULER_MAP.keys())]
 
 IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F"]
 """A literal type for PIL image modes supported by Invoke"""
+
+DEFAULT_PRECISION = TorchDevice.choose_torch_dtype()

{InvokeAI-4.2.4 → InvokeAI-4.2.5}/invokeai/app/invocations/controlnet_image_processors.py

@@ -2,6 +2,7 @@
 # initial implementation by Gregg Helt, 2023
 # heavily leverages controlnet_aux package: https://github.com/patrickvonplaten/controlnet_aux
 from builtins import bool, float
+from pathlib import Path
 from typing import Dict, List, Literal, Union
 
 import cv2
@@ -36,12 +37,13 @@ from invokeai.app.invocations.util import validate_begin_end_step, validate_weig
 from invokeai.app.services.shared.invocation_context import InvocationContext
 from invokeai.app.util.controlnet_utils import CONTROLNET_MODE_VALUES, CONTROLNET_RESIZE_VALUES, heuristic_resize
 from invokeai.backend.image_util.canny import get_canny_edges
-from invokeai.backend.image_util.depth_anything import DepthAnythingDetector
-from invokeai.backend.image_util.dw_openpose import DWOpenposeDetector
+from invokeai.backend.image_util.depth_anything import DEPTH_ANYTHING_MODELS, DepthAnythingDetector
+from invokeai.backend.image_util.dw_openpose import DWPOSE_MODELS, DWOpenposeDetector
 from invokeai.backend.image_util.hed import HEDProcessor
 from invokeai.backend.image_util.lineart import LineartProcessor
 from invokeai.backend.image_util.lineart_anime import LineartAnimeProcessor
 from invokeai.backend.image_util.util import np_to_pil, pil_to_np
+from invokeai.backend.util.devices import TorchDevice
 
 from .baseinvocation import BaseInvocation, BaseInvocationOutput, Classification, invocation, invocation_output
 
@@ -139,6 +141,7 @@ class ImageProcessorInvocation(BaseInvocation, WithMetadata, WithBoard):
         return context.images.get_pil(self.image.image_name, "RGB")
 
     def invoke(self, context: InvocationContext) -> ImageOutput:
+        self._context = context
         raw_image = self.load_image(context)
         # image type should be PIL.PngImagePlugin.PngImageFile ?
         processed_image = self.run_processor(raw_image)
@@ -284,7 +287,8 @@ class MidasDepthImageProcessorInvocation(ImageProcessorInvocation):
     # depth_and_normal not supported in controlnet_aux v0.0.3
     # depth_and_normal: bool = InputField(default=False, description="whether to use depth and normal mode")
 
-    def run_processor(self, image):
+    def run_processor(self, image: Image.Image) -> Image.Image:
+        # TODO: replace from_pretrained() calls with context.models.download_and_cache() (or similar)
         midas_processor = MidasDetector.from_pretrained("lllyasviel/Annotators")
         processed_image = midas_processor(
             image,
@@ -311,7 +315,7 @@ class NormalbaeImageProcessorInvocation(ImageProcessorInvocation):
     detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
     image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
-    def run_processor(self, image):
+    def run_processor(self, image: Image.Image) -> Image.Image:
         normalbae_processor = NormalBaeDetector.from_pretrained("lllyasviel/Annotators")
         processed_image = normalbae_processor(
             image, detect_resolution=self.detect_resolution, image_resolution=self.image_resolution
@@ -330,7 +334,7 @@ class MlsdImageProcessorInvocation(ImageProcessorInvocation):
     thr_v: float = InputField(default=0.1, ge=0, description="MLSD parameter `thr_v`")
     thr_d: float = InputField(default=0.1, ge=0, description="MLSD parameter `thr_d`")
 
-    def run_processor(self, image):
+    def run_processor(self, image: Image.Image) -> Image.Image:
         mlsd_processor = MLSDdetector.from_pretrained("lllyasviel/Annotators")
         processed_image = mlsd_processor(
             image,
@@ -353,7 +357,7 @@ class PidiImageProcessorInvocation(ImageProcessorInvocation):
     safe: bool = InputField(default=False, description=FieldDescriptions.safe_mode)
     scribble: bool = InputField(default=False, description=FieldDescriptions.scribble_mode)
 
-    def run_processor(self, image):
+    def run_processor(self, image: Image.Image) -> Image.Image:
         pidi_processor = PidiNetDetector.from_pretrained("lllyasviel/Annotators")
         processed_image = pidi_processor(
             image,
@@ -381,7 +385,7 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
     w: int = InputField(default=512, ge=0, description="Content shuffle `w` parameter")
     f: int = InputField(default=256, ge=0, description="Content shuffle `f` parameter")
 
-    def run_processor(self, image):
+    def run_processor(self, image: Image.Image) -> Image.Image:
         content_shuffle_processor = ContentShuffleDetector()
         processed_image = content_shuffle_processor(
             image,
@@ -405,7 +409,7 @@ class ContentShuffleImageProcessorInvocation(ImageProcessorInvocation):
 class ZoeDepthImageProcessorInvocation(ImageProcessorInvocation):
     """Applies Zoe depth processing to image"""
 
-    def run_processor(self, image):
+    def run_processor(self, image: Image.Image) -> Image.Image:
         zoe_depth_processor = ZoeDetector.from_pretrained("lllyasviel/Annotators")
         processed_image = zoe_depth_processor(image)
         return processed_image
@@ -426,7 +430,7 @@ class MediapipeFaceProcessorInvocation(ImageProcessorInvocation):
     detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
     image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
-    def run_processor(self, image):
+    def run_processor(self, image: Image.Image) -> Image.Image:
         mediapipe_face_processor = MediapipeFaceDetector()
         processed_image = mediapipe_face_processor(
             image,
@@ -454,7 +458,7 @@ class LeresImageProcessorInvocation(ImageProcessorInvocation):
     detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
     image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
-    def run_processor(self, image):
+    def run_processor(self, image: Image.Image) -> Image.Image:
         leres_processor = LeresDetector.from_pretrained("lllyasviel/Annotators")
         processed_image = leres_processor(
             image,
@@ -496,8 +500,8 @@ class TileResamplerProcessorInvocation(ImageProcessorInvocation):
         np_img = cv2.resize(np_img, (W, H), interpolation=cv2.INTER_AREA)
         return np_img
 
-    def run_processor(self, img):
-        np_img = np.array(img, dtype=np.uint8)
+    def run_processor(self, image: Image.Image) -> Image.Image:
+        np_img = np.array(image, dtype=np.uint8)
         processed_np_image = self.tile_resample(
             np_img,
             # res=self.tile_size,
@@ -520,7 +524,7 @@ class SegmentAnythingProcessorInvocation(ImageProcessorInvocation):
     detect_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.detect_res)
     image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
-    def run_processor(self, image):
+    def run_processor(self, image: Image.Image) -> Image.Image:
         # segment_anything_processor = SamDetector.from_pretrained("ybelkada/segment-anything", subfolder="checkpoints")
         segment_anything_processor = SamDetectorReproducibleColors.from_pretrained(
             "ybelkada/segment-anything", subfolder="checkpoints"
@@ -566,7 +570,7 @@ class ColorMapImageProcessorInvocation(ImageProcessorInvocation):
 
     color_map_tile_size: int = InputField(default=64, ge=1, description=FieldDescriptions.tile_size)
 
-    def run_processor(self, image: Image.Image):
+    def run_processor(self, image: Image.Image) -> Image.Image:
         np_image = np.array(image, dtype=np.uint8)
         height, width = np_image.shape[:2]
 
@@ -601,12 +605,18 @@ class DepthAnythingImageProcessorInvocation(ImageProcessorInvocation):
     )
     resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
-    def run_processor(self, image: Image.Image):
-        depth_anything_detector = DepthAnythingDetector()
-        depth_anything_detector.load_model(model_size=self.model_size)
+    def run_processor(self, image: Image.Image) -> Image.Image:
+        def loader(model_path: Path):
+            return DepthAnythingDetector.load_model(
+                model_path, model_size=self.model_size, device=TorchDevice.choose_torch_device()
+            )
 
-        processed_image = depth_anything_detector(image=image, resolution=self.resolution)
-        return processed_image
+        with self._context.models.load_remote_model(
+            source=DEPTH_ANYTHING_MODELS[self.model_size], loader=loader
+        ) as model:
+            depth_anything_detector = DepthAnythingDetector(model, TorchDevice.choose_torch_device())
+            processed_image = depth_anything_detector(image=image, resolution=self.resolution)
+            return processed_image
 
 
 @invocation(
@@ -624,8 +634,11 @@ class DWOpenposeImageProcessorInvocation(ImageProcessorInvocation):
     draw_hands: bool = InputField(default=False)
     image_resolution: int = InputField(default=512, ge=1, description=FieldDescriptions.image_res)
 
-    def run_processor(self, image: Image.Image):
-        dw_openpose = DWOpenposeDetector()
+    def run_processor(self, image: Image.Image) -> Image.Image:
+        onnx_det = self._context.models.download_and_cache_model(DWPOSE_MODELS["yolox_l.onnx"])
+        onnx_pose = self._context.models.download_and_cache_model(DWPOSE_MODELS["dw-ll_ucoco_384.onnx"])
+
+        dw_openpose = DWOpenposeDetector(onnx_det=onnx_det, onnx_pose=onnx_pose)
         processed_image = dw_openpose(
             image,
             draw_face=self.draw_face,

InvokeAI-4.2.5/invokeai/app/invocations/create_denoise_mask.py

@@ -0,0 +1,80 @@
+from typing import Optional
+
+import torch
+import torchvision.transforms as T
+from PIL import Image
+from torchvision.transforms.functional import resize as tv_resize
+
+from invokeai.app.invocations.baseinvocation import BaseInvocation, invocation
+from invokeai.app.invocations.constants import DEFAULT_PRECISION
+from invokeai.app.invocations.fields import FieldDescriptions, ImageField, Input, InputField
+from invokeai.app.invocations.image_to_latents import ImageToLatentsInvocation
+from invokeai.app.invocations.model import VAEField
+from invokeai.app.invocations.primitives import DenoiseMaskOutput
+from invokeai.app.services.shared.invocation_context import InvocationContext
+from invokeai.backend.stable_diffusion.diffusers_pipeline import image_resized_to_grid_as_tensor
+
+
+@invocation(
+    "create_denoise_mask",
+    title="Create Denoise Mask",
+    tags=["mask", "denoise"],
+    category="latents",
+    version="1.0.2",
+)
+class CreateDenoiseMaskInvocation(BaseInvocation):
+    """Creates mask for denoising model run."""
+
+    vae: VAEField = InputField(description=FieldDescriptions.vae, input=Input.Connection, ui_order=0)
+    image: Optional[ImageField] = InputField(default=None, description="Image which will be masked", ui_order=1)
+    mask: ImageField = InputField(description="The mask to use when pasting", ui_order=2)
+    tiled: bool = InputField(default=False, description=FieldDescriptions.tiled, ui_order=3)
+    fp32: bool = InputField(
+        default=DEFAULT_PRECISION == torch.float32,
+        description=FieldDescriptions.fp32,
+        ui_order=4,
+    )
+
+    def prep_mask_tensor(self, mask_image: Image.Image) -> torch.Tensor:
+        if mask_image.mode != "L":
+            mask_image = mask_image.convert("L")
+        mask_tensor: torch.Tensor = image_resized_to_grid_as_tensor(mask_image, normalize=False)
+        if mask_tensor.dim() == 3:
+            mask_tensor = mask_tensor.unsqueeze(0)
+        # if shape is not None:
+        #    mask_tensor = tv_resize(mask_tensor, shape, T.InterpolationMode.BILINEAR)
+        return mask_tensor
+
+    @torch.no_grad()
+    def invoke(self, context: InvocationContext) -> DenoiseMaskOutput:
+        if self.image is not None:
+            image = context.images.get_pil(self.image.image_name)
+            image_tensor = image_resized_to_grid_as_tensor(image.convert("RGB"))
+            if image_tensor.dim() == 3:
+                image_tensor = image_tensor.unsqueeze(0)
+        else:
+            image_tensor = None
+
+        mask = self.prep_mask_tensor(
+            context.images.get_pil(self.mask.image_name),
+        )
+
+        if image_tensor is not None:
+            vae_info = context.models.load(self.vae.vae)
+
+            img_mask = tv_resize(mask, image_tensor.shape[-2:], T.InterpolationMode.BILINEAR, antialias=False)
+            masked_image = image_tensor * torch.where(img_mask < 0.5, 0.0, 1.0)
+            # TODO:
+            masked_latents = ImageToLatentsInvocation.vae_encode(vae_info, self.fp32, self.tiled, masked_image.clone())
+
+            masked_latents_name = context.tensors.save(tensor=masked_latents)
+        else:
+            masked_latents_name = None
+
+        mask_name = context.tensors.save(tensor=mask)
+
+        return DenoiseMaskOutput.build(
+            mask_name=mask_name,
+            masked_latents_name=masked_latents_name,
+            gradient=False,
+        )