Class VaeImageProcessor

diffusers/src/diffusers/image_processor.py:27–252

Image processor for VAE. Args: do_resize (`bool`, *optional*, defaults to `True`): Whether to downscale the image's (height, width) dimensions to multiples of `vae_scale_factor`. Can accept `height` and `width` arguments from [`image_processor.VaeImageProces

class VaeImageProcessor(ConfigMixin):
    """
    Image processor for VAE.

    Args:
        do_resize (`bool`, *optional*, defaults to `True`):
            Whether to downscale the image's (height, width) dimensions to multiples of `vae_scale_factor`. Can accept
            `height` and `width` arguments from [`image_processor.VaeImageProcessor.preprocess`] method.
        vae_scale_factor (`int`, *optional*, defaults to `8`):
            VAE scale factor. If `do_resize` is `True`, the image is automatically resized to multiples of this factor.
        resample (`str`, *optional*, defaults to `lanczos`):
            Resampling filter to use when resizing the image.
        do_normalize (`bool`, *optional*, defaults to `True`):
            Whether to normalize the image to [-1,1].
        do_convert_rgb (`bool`, *optional*, defaults to be `False`):
            Whether to convert the images to RGB format.
    """

    config_name = CONFIG_NAME

    @register_to_config
    def __init__(
        self,
        do_resize: bool = True,
        vae_scale_factor: int = 8,
        resample: str = "lanczos",
        do_normalize: bool = True,
        do_convert_rgb: bool = False,
    ):
        super().__init__()

    @staticmethod
    def numpy_to_pil(images: np.ndarray) -> PIL.Image.Image:
        """
        Convert a numpy image or a batch of images to a PIL image.
        """
        if images.ndim == 3:
            images = images[None, ...]
        images = (images * 255).round().astype("uint8")
        if images.shape[-1] == 1:
            # special case for grayscale (single channel) images
            pil_images = [Image.fromarray(image.squeeze(), mode="L") for image in images]
        else:
            pil_images = [Image.fromarray(image) for image in images]

        return pil_images

    @staticmethod
    def pil_to_numpy(images: Union[List[PIL.Image.Image], PIL.Image.Image]) -> np.ndarray:
        """
        Convert a PIL image or a list of PIL images to NumPy arrays.
        """
        if not isinstance(images, list):
            images = [images]
        images = [np.array(image).astype(np.float32) / 255.0 for image in images]
        images = np.stack(images, axis=0)

        return images