Method preprocess

src/diffusers/image_processor.py:1154–1267

r""" Preprocess the image input. Accepted formats are PIL images, NumPy arrays, or PyTorch tensors. Args: rgb (`torch.Tensor | PIL.Image.Image | np.ndarray`): The RGB input image, which can be a single image or a batch. depth (`torch.Tensor |

(
        self,
        rgb: torch.Tensor | PIL.Image.Image | np.ndarray,
        depth: torch.Tensor | PIL.Image.Image | np.ndarray,
        height: int | None = None,
        width: int | None = None,
        target_res: int | None = None,
    )

            raise Exception(f"This type {output_type} is not supported")

    def preprocess(
        self,
        rgb: torch.Tensor | PIL.Image.Image | np.ndarray,
        depth: torch.Tensor | PIL.Image.Image | np.ndarray,
        height: int | None = None,
        width: int | None = None,
        target_res: int | None = None,
    ) -> torch.Tensor:
        r"""
        Preprocess the image input. Accepted formats are PIL images, NumPy arrays, or PyTorch tensors.

        Args:
            rgb (`torch.Tensor | PIL.Image.Image | np.ndarray`):
                The RGB input image, which can be a single image or a batch.
            depth (`torch.Tensor | PIL.Image.Image | np.ndarray`):
                The depth input image, which can be a single image or a batch.
            height (`int | None`, *optional*, defaults to `None`):
                The desired height of the processed image. If `None`, defaults to the height of the input image.
            width (`int | None`, *optional*, defaults to `None`):
                The desired width of the processed image. If `None`, defaults to the width of the input image.
            target_res (`int | None`, *optional*, defaults to `None`):
                Target resolution for resizing the images. If specified, overrides height and width.

        Returns:
            `tuple[torch.Tensor, torch.Tensor]`:
                A tuple containing the processed RGB and depth images as PyTorch tensors.
        """
        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(rgb, (torch.Tensor, np.ndarray)) and rgb.ndim == 3:
            raise Exception("This is not yet supported")

        if isinstance(rgb, supported_formats):
            rgb = [rgb]
            depth = [depth]
        elif not (isinstance(rgb, list) and all(isinstance(i, supported_formats) for i in rgb)):
            raise ValueError(
                f"Input is in incorrect format: {[type(i) for i in rgb]}. Currently, we only support {', '.join(supported_formats)}"
            )

        if isinstance(rgb[0], PIL.Image.Image):
            if self.config.do_convert_rgb:
                raise Exception("This is not yet supported")
                # rgb = [self.convert_to_rgb(i) for i in rgb]
                # depth = [self.convert_to_depth(i) for i in depth]  #TODO define convert_to_depth
            if self.config.do_resize or target_res:
                height, width = self.get_default_height_width(rgb[0], height, width) if not target_res else target_res
                rgb = [self.resize(i, height, width) for i in rgb]
                depth = [self.resize(i, height, width) for i in depth]
            rgb = self.pil_to_numpy(rgb)  # to np
            rgb = self.numpy_to_pt(rgb)  # to pt

            depth = self.depth_pil_to_numpy(depth)  # to np
            depth = self.numpy_to_pt(depth)  # to pt

        elif isinstance(rgb[0], np.ndarray):
            rgb = np.concatenate(rgb, axis=0) if rgb[0].ndim == 4 else np.stack(rgb, axis=0)