Ë ¢Ùbi‰ãó„—ddlmZddlmZmZddlZddlZddl Z ddl m Z eGd„de ««Z eGd„de ««Z y) é)Ú dataclass)ÚListÚUnionN)Ú BaseOutputcó0—eZdZUdZej ed<y)ÚHunyuanVideoPipelineOutputa¶ Output class for HunyuanVideo pipelines. Args: frames (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]): List of video outputs - It can be a nested list of length `batch_size,` with each sub-list containing denoised PIL image sequences of length `num_frames.` It can also be a NumPy array or Torch tensor of shape `(batch_size, num_frames, channels, height, width)`. ÚframesN)Ú__name__Ú __module__Ú __qualname__Ú__doc__ÚtorchÚTensorÚ__annotations__©óúl/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/diffusers/pipelines/hunyuan_video/pipeline_output.pyrr s…ñð L‰LÔrrcó —eZdZUdZeej eje e e jje ej fe d<y)Ú#HunyuanVideoFramepackPipelineOutputa) Output class for HunyuanVideo pipelines. Args: frames (`torch.Tensor`, `np.ndarray`, or List[List[PIL.Image.Image]]): List of video outputs - It can be a nested list of length `batch_size,` with each sub-list containing denoised PIL image sequences of length `num_frames.` It can also be a NumPy array or Torch tensor of shape `(batch_size, num_frames, channels, height, width)`. Or, a list of torch tensors where each tensor corresponds to a latent that decodes to multiple frames. r N) r r r r rrrÚnpÚndarrayrÚPILÚImagerrrrrrs@…ñ ð %—,‘, § ¡ ¨D°°c·i±i·o±oÑ1FÑ,GÈÈeÏlÉlÑI[Ð[Ñ \Ô\rr)Ú dataclassesrÚtypingrrÚnumpyrÚ PIL.ImagerrÚdiffusers.utilsrrrrrrúrsPðÝ!ßãÛÛ å&ð ô  ó ó ð ð ô ]¨*ó ]ó ñ ]r