Utilities
Utility and helper functions for working with 🤗 Diffusers.
numpy_to_pil
Convert a numpy image or a batch of images to a PIL image.
pt_to_pil
Convert a torch image to a PIL image.
load_image
diffusers.utils.load_image
< source >( image: typing.Union[str, PIL.Image.Image] convert_method: typing.Optional[typing.Callable[[PIL.Image.Image], PIL.Image.Image]] = None ) → PIL.Image.Image
Parameters
- image (
strorPIL.Image.Image) — The image to convert to the PIL Image format. - convert_method (Callable[[PIL.Image.Image], PIL.Image.Image], optional) —
A conversion method to apply to the image after loading it. When set to
Nonethe image will be converted “RGB”.
Returns
PIL.Image.Image
A PIL Image.
Loads image to a PIL Image.
export_to_gif
diffusers.utils.export_to_gif
< source >( image: typing.List[PIL.Image.Image] output_gif_path: str = None fps: int = 10 )
export_to_video
diffusers.utils.export_to_video
< source >( video_frames: typing.Union[typing.List[numpy.ndarray], typing.List[PIL.Image.Image]] output_video_path: str = None fps: int = 10 )
make_image_grid
diffusers.utils.make_image_grid
< source >( images: typing.List[PIL.Image.Image] rows: int cols: int resize: int = None )
Prepares a single grid of images. Useful for visualization purposes.
randn_tensor
diffusers.utils.torch_utils.randn_tensor
< source >( shape: typing.Union[typing.Tuple, typing.List] generator: typing.Union[typing.List[ForwardRef('torch.Generator')], ForwardRef('torch.Generator'), NoneType] = None device: typing.Optional[ForwardRef('torch.device')] = None dtype: typing.Optional[ForwardRef('torch.dtype')] = None layout: typing.Optional[ForwardRef('torch.layout')] = None )
A helper function to create random tensors on the desired device with the desired dtype. When
passing a list of generators, you can seed each batch size individually. If CPU generators are passed, the tensor
is always created on the CPU.