bibddlZddlmZmZmZddlZddlZddlZddl m Z m Z m Z Gdde Z y)N)ListOptionalUnion)VaeImageProcessoris_valid_imageis_valid_image_imagelistc eZdZdZd deedeedejfdZ d dejde de e jeje ejjffd Zy) VideoProcessorzSimple video processor.Nheightwidthreturnc t|tr`t|dtjrC|djdk(r1t j dttj|d}t|tr`t|dtjrC|djdk(r1t j dttj|d}t|tjtjfr|jdk(r t|}nYt|trt|ds t|r|g}n,t|trt|dr|}n tdtj|Dcgc]}|j!|||c}d}|j#dd d d d }|Scc}w) a Preprocesses input video(s). Args: video (`List[PIL.Image]`, `List[List[PIL.Image]]`, `torch.Tensor`, `np.array`, `List[torch.Tensor]`, `List[np.array]`): The input video. It can be one of the following: * List of the PIL images. * List of list of PIL images. * 4D Torch tensors (expected shape for each tensor `(num_frames, num_channels, height, width)`). * 4D NumPy arrays (expected shape for each array `(num_frames, height, width, num_channels)`). * List of 4D Torch tensors (expected shape for each tensor `(num_frames, num_channels, height, width)`). * List of 4D NumPy arrays (expected shape for each array `(num_frames, height, width, num_channels)`). * 5D NumPy arrays: expected shape for each array `(batch_size, num_frames, height, width, num_channels)`. * 5D Torch tensors: expected shape for each array `(batch_size, num_frames, num_channels, height, width)`. height (`int`, *optional*, defaults to `None`): The height in preprocessed frames of the video. If `None`, will use the `get_default_height_width()` to get default height. width (`int`, *optional*`, defaults to `None`): The width in preprocessed frames of the video. If `None`, will use get_default_height_width()` to get the default width. rzPassing `video` as a list of 5d np.ndarray is deprecated.Please concatenate the list along the batch dimension and pass it as a single 5d np.ndarray)axiszPassing `video` as a list of 5d torch.Tensor is deprecated.Please concatenate the list along the batch dimension and pass it as a single 5d torch.TensorzeInput is in incorrect format. Currently, we only support numpy.ndarray, torch.Tensor, PIL.Image.Image)r r )dimr) isinstancelistnpndarrayndimwarningswarn FutureWarning concatenatetorchTensorcatrr ValueErrorstack preprocesspermute)selfvideor r imgs T/home/cdr/jupyterlab/.venv/lib/python3.12/site-packages/diffusers/video_processor.pypreprocess_videozVideoProcessor.preprocess_videosx2 eT "z%(BJJ'GERSHMM]^L^ MMn  NN5q1E eT "z%(ELL'IeTUhmm_`N` MMp  IIe!,E ebjj%,,7 8UZZ1_KE t $a)AE]^cEdGE t $)A%()KEw  Y^_RUT__Su_M_efg aAq!, `sG r' output_typecR|jd}g}t|D]<}||jdddd}|j||}|j |>|dk(rt j |}|S|dk(rtj |}|S|dk(st|d|S) z Converts a video tensor to a list of frames for export. Args: video (`torch.Tensor`): The video as a tensor. output_type (`str`, defaults to `"np"`): Output type of the postprocessed `video` tensor. rrrrrptpilz9 does not exist. Please choose one of ['np', 'pt', 'pil']) shaperanger% postprocessappendrr#rr")r&r'r+ batch_sizeoutputs batch_idx batch_vid batch_outputs r)postprocess_videoz VideoProcessor.postprocess_videoYs[[^ z* )Ii(00Aq!> ?r9r )rtypingrrrnumpyrr@rimage_processorrrr r rBr9r)rFs.(( XXX&Xr9