diffusers 0.24.0__py3-none-any.whl → 0.25.0__py3-none-any.whl

diffusers/__init__.py

@@ -1,4 +1,4 @@
-__version__ = "0.24.0"
+__version__ = "0.25.0"
 
 from typing import TYPE_CHECKING
 
@@ -94,6 +94,7 @@ else:
             "UNet3DConditionModel",
             "UNetMotionModel",
             "UNetSpatioTemporalConditionModel",
+            "UVit2DModel",
             "VQModel",
         ]
     )
@@ -130,6 +131,7 @@ else:
     )
     _import_structure["schedulers"].extend(
         [
+            "AmusedScheduler",
             "CMStochasticIterativeScheduler",
             "DDIMInverseScheduler",
             "DDIMParallelScheduler",
@@ -201,6 +203,9 @@ else:
         [
             "AltDiffusionImg2ImgPipeline",
             "AltDiffusionPipeline",
+            "AmusedImg2ImgPipeline",
+            "AmusedInpaintPipeline",
+            "AmusedPipeline",
             "AnimateDiffPipeline",
             "AudioLDM2Pipeline",
             "AudioLDM2ProjectionModel",
@@ -468,6 +473,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             UNet3DConditionModel,
             UNetMotionModel,
             UNetSpatioTemporalConditionModel,
+            UVit2DModel,
             VQModel,
         )
         from .optimization import (
@@ -502,6 +508,7 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
             ScoreSdeVePipeline,
         )
         from .schedulers import (
+            AmusedScheduler,
             CMStochasticIterativeScheduler,
             DDIMInverseScheduler,
             DDIMParallelScheduler,
@@ -556,6 +563,9 @@ if TYPE_CHECKING or DIFFUSERS_SLOW_IMPORT:
         from .pipelines import (
             AltDiffusionImg2ImgPipeline,
             AltDiffusionPipeline,
+            AmusedImg2ImgPipeline,
+            AmusedInpaintPipeline,
+            AmusedPipeline,
             AnimateDiffPipeline,
             AudioLDM2Pipeline,
             AudioLDM2ProjectionModel,

diffusers/commands/fp16_safetensors.py

@@ -19,6 +19,7 @@ Usage example:
 
 import glob
 import json
+import warnings
 from argparse import ArgumentParser, Namespace
 from importlib import import_module
 
@@ -32,12 +33,12 @@ from . import BaseDiffusersCLICommand
 
 
 def conversion_command_factory(args: Namespace):
-    return FP16SafetensorsCommand(
-        args.ckpt_id,
-        args.fp16,
-        args.use_safetensors,
-        args.use_auth_token,
-    )
+    if args.use_auth_token:
+        warnings.warn(
+            "The `--use_auth_token` flag is deprecated and will be removed in a future version. Authentication is now"
+            " handled automatically if user is logged in."
+        )
+    return FP16SafetensorsCommand(args.ckpt_id, args.fp16, args.use_safetensors)
 
 
 class FP16SafetensorsCommand(BaseDiffusersCLICommand):
@@ -62,7 +63,7 @@ class FP16SafetensorsCommand(BaseDiffusersCLICommand):
         )
         conversion_parser.set_defaults(func=conversion_command_factory)
 
-    def __init__(self, ckpt_id: str, fp16: bool, use_safetensors: bool, use_auth_token: bool):
+    def __init__(self, ckpt_id: str, fp16: bool, use_safetensors: bool):
         self.logger = logging.get_logger("diffusers-cli/fp16_safetensors")
         self.ckpt_id = ckpt_id
         self.local_ckpt_dir = f"/tmp/{ckpt_id}"
@@ -75,8 +76,6 @@ class FP16SafetensorsCommand(BaseDiffusersCLICommand):
                 "When `use_safetensors` and `fp16` both are False, then this command is of no use."
             )
 
-        self.use_auth_token = use_auth_token
-
     def run(self):
         if version.parse(huggingface_hub.__version__) < version.parse("0.9.0"):
             raise ImportError(
@@ -87,7 +86,7 @@ class FP16SafetensorsCommand(BaseDiffusersCLICommand):
             from huggingface_hub import create_commit
             from huggingface_hub._commit_api import CommitOperationAdd
 
-        model_index = hf_hub_download(repo_id=self.ckpt_id, filename="model_index.json", token=self.use_auth_token)
+        model_index = hf_hub_download(repo_id=self.ckpt_id, filename="model_index.json")
         with open(model_index, "r") as f:
             pipeline_class_name = json.load(f)["_class_name"]
         pipeline_class = getattr(import_module("diffusers"), pipeline_class_name)
@@ -96,7 +95,7 @@ class FP16SafetensorsCommand(BaseDiffusersCLICommand):
         # Load the appropriate pipeline. We could have use `DiffusionPipeline`
         # here, but just to avoid any rough edge cases.
         pipeline = pipeline_class.from_pretrained(
-            self.ckpt_id, torch_dtype=torch.float16 if self.fp16 else torch.float32, use_auth_token=self.use_auth_token
+            self.ckpt_id, torch_dtype=torch.float16 if self.fp16 else torch.float32
         )
         pipeline.save_pretrained(
             self.local_ckpt_dir,

diffusers/configuration_utils.py

@@ -27,12 +27,16 @@ from typing import Any, Dict, Tuple, Union
 
 import numpy as np
 from huggingface_hub import create_repo, hf_hub_download
-from huggingface_hub.utils import EntryNotFoundError, RepositoryNotFoundError, RevisionNotFoundError
+from huggingface_hub.utils import (
+    EntryNotFoundError,
+    RepositoryNotFoundError,
+    RevisionNotFoundError,
+    validate_hf_hub_args,
+)
 from requests import HTTPError
 
 from . import __version__
 from .utils import (
-    DIFFUSERS_CACHE,
     HUGGINGFACE_CO_RESOLVE_ENDPOINT,
     DummyObject,
     deprecate,
@@ -275,6 +279,7 @@ class ConfigMixin:
         return cls.load_config(*args, **kwargs)
 
     @classmethod
+    @validate_hf_hub_args
     def load_config(
         cls,
         pretrained_model_name_or_path: Union[str, os.PathLike],
@@ -311,7 +316,7 @@ class ConfigMixin:
             local_files_only (`bool`, *optional*, defaults to `False`):
                 Whether to only load local model weights and configuration files or not. If set to `True`, the model
                 won't be downloaded from the Hub.
-            use_auth_token (`str` or *bool*, *optional*):
+            token (`str` or *bool*, *optional*):
                 The token to use as HTTP bearer authorization for remote files. If `True`, the token generated from
                 `diffusers-cli login` (stored in `~/.huggingface`) is used.
             revision (`str`, *optional*, defaults to `"main"`):
@@ -329,11 +334,11 @@ class ConfigMixin:
                 A dictionary of all the parameters stored in a JSON configuration file.
 
         """
-        cache_dir = kwargs.pop("cache_dir", DIFFUSERS_CACHE)
+        cache_dir = kwargs.pop("cache_dir", None)
         force_download = kwargs.pop("force_download", False)
         resume_download = kwargs.pop("resume_download", False)
         proxies = kwargs.pop("proxies", None)
-        use_auth_token = kwargs.pop("use_auth_token", None)
+        token = kwargs.pop("token", None)
         local_files_only = kwargs.pop("local_files_only", False)
         revision = kwargs.pop("revision", None)
         _ = kwargs.pop("mirror", None)
@@ -376,7 +381,7 @@ class ConfigMixin:
                     proxies=proxies,
                     resume_download=resume_download,
                     local_files_only=local_files_only,
-                    use_auth_token=use_auth_token,
+                    token=token,
                     user_agent=user_agent,
                     subfolder=subfolder,
                     revision=revision,
@@ -385,8 +390,7 @@ class ConfigMixin:
                 raise EnvironmentError(
                     f"{pretrained_model_name_or_path} is not a local folder and is not a valid model identifier"
                     " listed on 'https://huggingface.co/models'\nIf this is a private repository, make sure to pass a"
-                    " token having permission to this repo with `use_auth_token` or log in with `huggingface-cli"
-                    " login`."
+                    " token having permission to this repo with `token` or log in with `huggingface-cli login`."
                 )
             except RevisionNotFoundError:
                 raise EnvironmentError(

diffusers/dependency_versions_table.py

@@ -30,9 +30,10 @@ deps = {
     "pytest-timeout": "pytest-timeout",
     "pytest-xdist": "pytest-xdist",
     "python": "python>=3.8.0",
-    "ruff": "ruff>=0.1.5,<=0.2",
+    "ruff": "ruff==0.1.5",
     "safetensors": "safetensors>=0.3.1",
     "sentencepiece": "sentencepiece>=0.1.91,!=0.1.92",
+    "GitPython": "GitPython<3.1.19",
     "scipy": "scipy",
     "onnx": "onnx",
     "regex": "regex!=2019.12.17",

diffusers/experimental/rl/value_guided_sampling.py

@@ -113,7 +113,7 @@ class ValueGuidedRLPipeline(DiffusionPipeline):
             prev_x = self.unet(x.permute(0, 2, 1), timesteps).sample.permute(0, 2, 1)
 
             # TODO: verify deprecation of this kwarg
-            x = self.scheduler.step(prev_x, i, x, predict_epsilon=False)["prev_sample"]
+            x = self.scheduler.step(prev_x, i, x)["prev_sample"]
 
             # apply conditions to the trajectory (set the initial state)
             x = self.reset_x0(x, conditions, self.action_dim)

diffusers/image_processor.py

@@ -18,7 +18,7 @@ from typing import List, Optional, Tuple, Union
 import numpy as np
 import PIL.Image
 import torch
-from PIL import Image
+from PIL import Image, ImageFilter, ImageOps
 
 from .configuration_utils import ConfigMixin, register_to_config
 from .utils import CONFIG_NAME, PIL_INTERPOLATION, deprecate
@@ -88,7 +88,7 @@ class VaeImageProcessor(ConfigMixin):
             self.config.do_convert_rgb = False
 
     @staticmethod
-    def numpy_to_pil(images: np.ndarray) -> PIL.Image.Image:
+    def numpy_to_pil(images: np.ndarray) -> List[PIL.Image.Image]:
         """
         Convert a numpy image or a batch of images to a PIL image.
         """
@@ -166,54 +166,178 @@ class VaeImageProcessor(ConfigMixin):
 
         return image
 
-    def get_default_height_width(
-        self,
-        image: Union[PIL.Image.Image, np.ndarray, torch.Tensor],
-        height: Optional[int] = None,
-        width: Optional[int] = None,
-    ) -> Tuple[int, int]:
+    @staticmethod
+    def blur(image: PIL.Image.Image, blur_factor: int = 4) -> PIL.Image.Image:
         """
-        This function return the height and width that are downscaled to the next integer multiple of
-        `vae_scale_factor`.
+        Blurs an image.
+        """
+        image = image.filter(ImageFilter.GaussianBlur(blur_factor))
+
+        return image
+
+    @staticmethod
+    def get_crop_region(mask_image: PIL.Image.Image, width: int, height: int, pad=0):
+        """
+        Finds a rectangular region that contains all masked ares in an image, and expands region to match the aspect ratio of the original image;
+        for example, if user drew mask in a 128x32 region, and the dimensions for processing are 512x512, the region will be expanded to 128x128.
 
         Args:
-            image(`PIL.Image.Image`, `np.ndarray` or `torch.Tensor`):
-                The image input, can be a PIL image, numpy array or pytorch tensor. if it is a numpy array, should have
-                shape `[batch, height, width]` or `[batch, height, width, channel]` if it is a pytorch tensor, should
-                have shape `[batch, channel, height, width]`.
-            height (`int`, *optional*, defaults to `None`):
-                The height in preprocessed image. If `None`, will use the height of `image` input.
-            width (`int`, *optional*`, defaults to `None`):
-                The width in preprocessed. If `None`, will use the width of the `image` input.
+            mask_image (PIL.Image.Image): Mask image.
+            width (int): Width of the image to be processed.
+            height (int): Height of the image to be processed.
+            pad (int, optional): Padding to be added to the crop region. Defaults to 0.
+
+        Returns:
+            tuple: (x1, y1, x2, y2) represent a rectangular region that contains all masked ares in an image and matches the original aspect ratio.
+        """
+
+        mask_image = mask_image.convert("L")
+        mask = np.array(mask_image)
+
+        # 1. find a rectangular region that contains all masked ares in an image
+        h, w = mask.shape
+        crop_left = 0
+        for i in range(w):
+            if not (mask[:, i] == 0).all():
+                break
+            crop_left += 1
+
+        crop_right = 0
+        for i in reversed(range(w)):
+            if not (mask[:, i] == 0).all():
+                break
+            crop_right += 1
+
+        crop_top = 0
+        for i in range(h):
+            if not (mask[i] == 0).all():
+                break
+            crop_top += 1
+
+        crop_bottom = 0
+        for i in reversed(range(h)):
+            if not (mask[i] == 0).all():
+                break
+            crop_bottom += 1
+
+        # 2. add padding to the crop region
+        x1, y1, x2, y2 = (
+            int(max(crop_left - pad, 0)),
+            int(max(crop_top - pad, 0)),
+            int(min(w - crop_right + pad, w)),
+            int(min(h - crop_bottom + pad, h)),
+        )
+
+        # 3. expands crop region to match the aspect ratio of the image to be processed
+        ratio_crop_region = (x2 - x1) / (y2 - y1)
+        ratio_processing = width / height
+
+        if ratio_crop_region > ratio_processing:
+            desired_height = (x2 - x1) / ratio_processing
+            desired_height_diff = int(desired_height - (y2 - y1))
+            y1 -= desired_height_diff // 2
+            y2 += desired_height_diff - desired_height_diff // 2
+            if y2 >= mask_image.height:
+                diff = y2 - mask_image.height
+                y2 -= diff
+                y1 -= diff
+            if y1 < 0:
+                y2 -= y1
+                y1 -= y1
+            if y2 >= mask_image.height:
+                y2 = mask_image.height
+        else:
+            desired_width = (y2 - y1) * ratio_processing
+            desired_width_diff = int(desired_width - (x2 - x1))
+            x1 -= desired_width_diff // 2
+            x2 += desired_width_diff - desired_width_diff // 2
+            if x2 >= mask_image.width:
+                diff = x2 - mask_image.width
+                x2 -= diff
+                x1 -= diff
+            if x1 < 0:
+                x2 -= x1
+                x1 -= x1
+            if x2 >= mask_image.width:
+                x2 = mask_image.width
+
+        return x1, y1, x2, y2
+
+    def _resize_and_fill(
+        self,
+        image: PIL.Image.Image,
+        width: int,
+        height: int,
+    ) -> PIL.Image.Image:
         """
+        Resize the image to fit within the specified width and height, maintaining the aspect ratio, and then center the image within the dimensions, filling empty with data from image.
 
-        if height is None:
-            if isinstance(image, PIL.Image.Image):
-                height = image.height
-            elif isinstance(image, torch.Tensor):
-                height = image.shape[2]
-            else:
-                height = image.shape[1]
+        Args:
+            image: The image to resize.
+            width: The width to resize the image to.
+            height: The height to resize the image to.
+        """
+
+        ratio = width / height
+        src_ratio = image.width / image.height
+
+        src_w = width if ratio < src_ratio else image.width * height // image.height
+        src_h = height if ratio >= src_ratio else image.height * width // image.width
+
+        resized = image.resize((src_w, src_h), resample=PIL_INTERPOLATION["lanczos"])
+        res = Image.new("RGB", (width, height))
+        res.paste(resized, box=(width // 2 - src_w // 2, height // 2 - src_h // 2))
+
+        if ratio < src_ratio:
+            fill_height = height // 2 - src_h // 2
+            if fill_height > 0:
+                res.paste(resized.resize((width, fill_height), box=(0, 0, width, 0)), box=(0, 0))
+                res.paste(
+                    resized.resize((width, fill_height), box=(0, resized.height, width, resized.height)),
+                    box=(0, fill_height + src_h),
+                )
+        elif ratio > src_ratio:
+            fill_width = width // 2 - src_w // 2
+            if fill_width > 0:
+                res.paste(resized.resize((fill_width, height), box=(0, 0, 0, height)), box=(0, 0))
+                res.paste(
+                    resized.resize((fill_width, height), box=(resized.width, 0, resized.width, height)),
+                    box=(fill_width + src_w, 0),
+                )
+
+        return res
+
+    def _resize_and_crop(
+        self,
+        image: PIL.Image.Image,
+        width: int,
+        height: int,
+    ) -> PIL.Image.Image:
+        """
+        Resize the image to fit within the specified width and height, maintaining the aspect ratio, and then center the image within the dimensions, cropping the excess.
 
-        if width is None:
-            if isinstance(image, PIL.Image.Image):
-                width = image.width
-            elif isinstance(image, torch.Tensor):
-                width = image.shape[3]
-            else:
-                width = image.shape[2]
+        Args:
+            image: The image to resize.
+            width: The width to resize the image to.
+            height: The height to resize the image to.
+        """
+        ratio = width / height
+        src_ratio = image.width / image.height
 
-        width, height = (
-            x - x % self.config.vae_scale_factor for x in (width, height)
-        )  # resize to integer multiple of vae_scale_factor
+        src_w = width if ratio > src_ratio else image.width * height // image.height
+        src_h = height if ratio <= src_ratio else image.height * width // image.width
 
-        return height, width
+        resized = image.resize((src_w, src_h), resample=PIL_INTERPOLATION["lanczos"])
+        res = Image.new("RGB", (width, height))
+        res.paste(resized, box=(width // 2 - src_w // 2, height // 2 - src_h // 2))
+        return res
 
     def resize(
         self,
         image: Union[PIL.Image.Image, np.ndarray, torch.Tensor],
-        height: Optional[int] = None,
-        width: Optional[int] = None,
+        height: int,
+        width: int,
+        resize_mode: str = "default",  # "defalt", "fill", "crop"
     ) -> Union[PIL.Image.Image, np.ndarray, torch.Tensor]:
         """
         Resize image.
@@ -221,17 +345,35 @@ class VaeImageProcessor(ConfigMixin):
         Args:
             image (`PIL.Image.Image`, `np.ndarray` or `torch.Tensor`):
                 The image input, can be a PIL image, numpy array or pytorch tensor.
-            height (`int`, *optional*, defaults to `None`):
+            height (`int`):
                 The height to resize to.
-            width (`int`, *optional*`, defaults to `None`):
+            width (`int`):
                 The width to resize to.
+            resize_mode (`str`, *optional*, defaults to `default`):
+                The resize mode to use, can be one of `default` or `fill`. If `default`, will resize the image to fit
+                within the specified width and height, and it may not maintaining the original aspect ratio.
+                If `fill`, will resize the image to fit within the specified width and height, maintaining the aspect ratio, and then center the image
+                within the dimensions, filling empty with data from image.
+                If `crop`, will resize the image to fit within the specified width and height, maintaining the aspect ratio, and then center the image
+                within the dimensions, cropping the excess.
+                Note that resize_mode `fill` and `crop` are only supported for PIL image input.
 
         Returns:
             `PIL.Image.Image`, `np.ndarray` or `torch.Tensor`:
                 The resized image.
         """
+        if resize_mode != "default" and not isinstance(image, PIL.Image.Image):
+            raise ValueError(f"Only PIL image input is supported for resize_mode {resize_mode}")
         if isinstance(image, PIL.Image.Image):
-            image = image.resize((width, height), resample=PIL_INTERPOLATION[self.config.resample])
+            if resize_mode == "default":
+                image = image.resize((width, height), resample=PIL_INTERPOLATION[self.config.resample])
+            elif resize_mode == "fill":
+                image = self._resize_and_fill(image, width, height)
+            elif resize_mode == "crop":
+                image = self._resize_and_crop(image, width, height)
+            else:
+                raise ValueError(f"resize_mode {resize_mode} is not supported")
+
         elif isinstance(image, torch.Tensor):
             image = torch.nn.functional.interpolate(
                 image,
@@ -262,14 +404,77 @@ class VaeImageProcessor(ConfigMixin):
         image[image >= 0.5] = 1
         return image
 
+    def get_default_height_width(
+        self,
+        image: Union[PIL.Image.Image, np.ndarray, torch.Tensor],
+        height: Optional[int] = None,
+        width: Optional[int] = None,
+    ) -> Tuple[int, int]:
+        """
+        This function return the height and width that are downscaled to the next integer multiple of
+        `vae_scale_factor`.
+
+        Args:
+            image(`PIL.Image.Image`, `np.ndarray` or `torch.Tensor`):
+                The image input, can be a PIL image, numpy array or pytorch tensor. if it is a numpy array, should have
+                shape `[batch, height, width]` or `[batch, height, width, channel]` if it is a pytorch tensor, should
+                have shape `[batch, channel, height, width]`.
+            height (`int`, *optional*, defaults to `None`):
+                The height in preprocessed image. If `None`, will use the height of `image` input.
+            width (`int`, *optional*`, defaults to `None`):
+                The width in preprocessed. If `None`, will use the width of the `image` input.
+        """
+
+        if height is None:
+            if isinstance(image, PIL.Image.Image):
+                height = image.height
+            elif isinstance(image, torch.Tensor):
+                height = image.shape[2]
+            else:
+                height = image.shape[1]
+
+        if width is None:
+            if isinstance(image, PIL.Image.Image):
+                width = image.width
+            elif isinstance(image, torch.Tensor):
+                width = image.shape[3]
+            else:
+                width = image.shape[2]
+
+        width, height = (
+            x - x % self.config.vae_scale_factor for x in (width, height)
+        )  # resize to integer multiple of vae_scale_factor
+
+        return height, width
+
     def preprocess(
         self,
-        image: Union[torch.FloatTensor, PIL.Image.Image, np.ndarray],
+        image: PipelineImageInput,
         height: Optional[int] = None,
         width: Optional[int] = None,
+        resize_mode: str = "default",  # "defalt", "fill", "crop"
+        crops_coords: Optional[Tuple[int, int, int, int]] = None,
     ) -> torch.Tensor:
         """
-        Preprocess the image input. Accepted formats are PIL images, NumPy arrays or PyTorch tensors.
+        Preprocess the image input.
+
+        Args:
+            image (`pipeline_image_input`):
+                The image input, accepted formats are PIL images, NumPy arrays, PyTorch tensors; Also accept list of supported formats.
+            height (`int`, *optional*, defaults to `None`):
+                The height in preprocessed image. If `None`, will use the `get_default_height_width()` to get default height.
+            width (`int`, *optional*`, defaults to `None`):
+                The width in preprocessed. If `None`, will use  get_default_height_width()` to get the default width.
+            resize_mode (`str`, *optional*, defaults to `default`):
+                The resize mode, can be one of `default` or `fill`. If `default`, will resize the image to fit
+                within the specified width and height, and it may not maintaining the original aspect ratio.
+                If `fill`, will resize the image to fit within the specified width and height, maintaining the aspect ratio, and then center the image
+                within the dimensions, filling empty with data from image.
+                If `crop`, will resize the image to fit within the specified width and height, maintaining the aspect ratio, and then center the image
+                within the dimensions, cropping the excess.
+                Note that resize_mode `fill` and `crop` are only supported for PIL image input.
+            crops_coords (`List[Tuple[int, int, int, int]]`, *optional*, defaults to `None`):
+                The crop coordinates for each image in the batch. If `None`, will not crop the image.
         """
         supported_formats = (PIL.Image.Image, np.ndarray, torch.Tensor)
 
@@ -299,13 +504,15 @@ class VaeImageProcessor(ConfigMixin):
             )
 
         if isinstance(image[0], PIL.Image.Image):
+            if crops_coords is not None:
+                image = [i.crop(crops_coords) for i in image]
+            if self.config.do_resize:
+                height, width = self.get_default_height_width(image[0], height, width)
+                image = [self.resize(i, height, width, resize_mode=resize_mode) for i in image]
             if self.config.do_convert_rgb:
                 image = [self.convert_to_rgb(i) for i in image]
             elif self.config.do_convert_grayscale:
                 image = [self.convert_to_grayscale(i) for i in image]
-            if self.config.do_resize:
-                height, width = self.get_default_height_width(image[0], height, width)
-                image = [self.resize(i, height, width) for i in image]
             image = self.pil_to_numpy(image)  # to np
             image = self.numpy_to_pt(image)  # to pt
 
@@ -406,6 +613,39 @@ class VaeImageProcessor(ConfigMixin):
         if output_type == "pil":
             return self.numpy_to_pil(image)
 
+    def apply_overlay(
+        self,
+        mask: PIL.Image.Image,
+        init_image: PIL.Image.Image,
+        image: PIL.Image.Image,
+        crop_coords: Optional[Tuple[int, int, int, int]] = None,
+    ) -> PIL.Image.Image:
+        """
+        overlay the inpaint output to the original image
+        """
+
+        width, height = image.width, image.height
+
+        init_image = self.resize(init_image, width=width, height=height)
+        mask = self.resize(mask, width=width, height=height)
+
+        init_image_masked = PIL.Image.new("RGBa", (width, height))
+        init_image_masked.paste(init_image.convert("RGBA").convert("RGBa"), mask=ImageOps.invert(mask.convert("L")))
+        init_image_masked = init_image_masked.convert("RGBA")
+
+        if crop_coords is not None:
+            x, y, w, h = crop_coords
+            base_image = PIL.Image.new("RGBA", (width, height))
+            image = self.resize(image, height=h, width=w, resize_mode="crop")
+            base_image.paste(image, (x, y))
+            image = base_image.convert("RGB")
+
+        image = image.convert("RGBA")
+        image.alpha_composite(init_image_masked)
+        image = image.convert("RGB")
+
+        return image
+
 
 class VaeImageProcessorLDM3D(VaeImageProcessor):
     """