Method preprocess

src/diffusers/image_processor.py:607–736

Preprocess the image input. Args: image (`PipelineImageInput`): The image input, accepted formats are PIL images, NumPy arrays, PyTorch tensors; Also accept list of supported formats. height (`int`, *optional*):

(
        self,
        image: PipelineImageInput,
        height: int | None = None,
        width: int | None = None,
        resize_mode: str = "default",  # "default", "fill", "crop"
        crops_coords: tuple[int, int, int, int] | None = None,
    )

        return height, width

    def preprocess(
        self,
        image: PipelineImageInput,
        height: int | None = None,
        width: int | None = None,
        resize_mode: str = "default",  # "default", "fill", "crop"
        crops_coords: tuple[int, int, int, int] | None = None,
    ) -> torch.Tensor:
        """
        Preprocess the image input.

        Args:
            image (`PipelineImageInput`):
                The image input, accepted formats are PIL images, NumPy arrays, PyTorch tensors; Also accept list of
                supported formats.
            height (`int`, *optional*):
                The height in preprocessed image. If `None`, will use the `get_default_height_width()` to get default
                height.
            width (`int`, *optional*):
                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.

        Returns:
            `torch.Tensor`:
                The preprocessed image.
        """
        supported_formats = (PIL.Image.Image, np.ndarray, torch.Tensor)

        # Expand the missing dimension for 3-dimensional pytorch tensor or numpy array that represents grayscale image
        if self.config.do_convert_grayscale and isinstance(image, (torch.Tensor, np.ndarray)) and image.ndim == 3:
            if isinstance(image, torch.Tensor):
                # if image is a pytorch tensor could have 2 possible shapes:
                #    1. batch x height x width: we should insert the channel dimension at position 1
                #    2. channel x height x width: we should insert batch dimension at position 0,
                #       however, since both channel and batch dimension has same size 1, it is same to insert at position 1
                #    for simplicity, we insert a dimension of size 1 at position 1 for both cases
                image = image.unsqueeze(1)
            else:
                # if it is a numpy array, it could have 2 possible shapes:
                #   1. batch x height x width: insert channel dimension on last position
                #   2. height x width x channel: insert batch dimension on first position
                if image.shape[-1] == 1:
                    image = np.expand_dims(image, axis=0)
                else:
                    image = np.expand_dims(image, axis=-1)

        if isinstance(image, list) and isinstance(image[0], np.ndarray) and image[0].ndim == 4:
            warnings.warn(
                "Passing `image` as a list of 4d np.ndarray is deprecated."