o pi@s\ddlZddlmZmZmZddlZddlZddlZddl m Z m Z m Z Gddde Z dS)N)ListOptionalUnion)VaeImageProcessoris_valid_imageis_valid_image_imagelistc @sdeZdZdZd deedeedejfddZ dd ejd e de e j eje ejjffd d ZdS)VideoProcessorzSimple video processor.Nheightwidthreturncs*t|tr!t|dtjr!|djdkr!tdttj|dd}t|trBt|dt j rB|djdkrBtdtt j |dd}t|tjt j frU|jdkrUt|}n%t|tr`t |dsdt |rh|g}nt|trvt |drv|}ntdt jfdd|Ddd }|dd d d d }|S)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.Imagecsg|] }j|dqS))r r ) preprocess).0imgr selfr W/home/ubuntu/SoloSpeech/.venv/lib/python3.10/site-packages/diffusers/video_processor.py Rsz3VideoProcessor.preprocess_video..)dimr) isinstancelistnpndarrayndimwarningswarn FutureWarning concatenatetorchTensorcatrr ValueErrorstackpermute)rvideor r rrrpreprocess_videos0((  zVideoProcessor.preprocess_videorr* output_typecCs|jd}g}t|D]}||dddd}|||}||q |dkr.t|}|S|dkr9t|}|S|dksDt|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(r$r')rr*r, batch_sizeoutputs batch_idx batch_vid batch_outputrrrpostprocess_videoYs      z VideoProcessor.postprocess_video)NN)r)__name__ __module__ __qualname____doc__rintr$r%r+strrrrrPILImager8rrrrr s">r )r typingrrrnumpyrr?r$image_processorrrrr rrrrs