Method preprocess

src/diffusers/image_processor.py:265–352

Preprocess the image input. Accepted formats are PIL images, NumPy arrays or PyTorch tensors.

(
        self,
        image: Union[torch.FloatTensor, PIL.Image.Image, np.ndarray],
        height: Optional[int] = None,
        width: Optional[int] = None,
    )

        return image

    def preprocess(
        self,
        image: Union[torch.FloatTensor, PIL.Image.Image, np.ndarray],
        height: Optional[int] = None,
        width: Optional[int] = None,
    ) -> torch.Tensor:
        """
        Preprocess the image input. Accepted formats are PIL images, NumPy arrays or 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(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. channnel 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, supported_formats):
            image = [image]
        elif not (isinstance(image, list) and all(isinstance(i, supported_formats) for i in image)):
            raise ValueError(
                f"Input is in incorrect format: {[type(i) for i in image]}. Currently, we only support {', '.join(supported_formats)}"
            )

        if isinstance(image[0], PIL.Image.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

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

            image = self.numpy_to_pt(image)

            height, width = self.get_default_height_width(image, height, width)
            if self.config.do_resize:
                image = self.resize(image, height, width)

        elif isinstance(image[0], torch.Tensor):
            image = torch.cat(image, axis=0) if image[0].ndim == 4 else torch.stack(image, axis=0)