MCPcopy Index your code
hub / github.com/huggingface/diffusers / preprocess_video

Method preprocess_video

src/diffusers/video_processor.py:28–91  ·  view source on GitHub ↗

r""" Preprocesses input video(s). Keyword arguments will be forwarded to `VaeImageProcessor.preprocess`. Args: video (`list[PIL.Image]`, `list[list[PIL.Image]]`, `torch.Tensor`, `np.array`, `list[torch.Tensor]`, `list[np.array]`): The input video. It can

(self, video, height: int | None = None, width: int | None = None, **kwargs)

Source from the content-addressed store, hash-verified

26 r"""Simple video processor."""
27
28 def preprocess_video(self, video, height: int | None = None, width: int | None = None, **kwargs) -> torch.Tensor:
29 r"""
30 Preprocesses input video(s). Keyword arguments will be forwarded to `VaeImageProcessor.preprocess`.
31
32 Args:
33 video (`list[PIL.Image]`, `list[list[PIL.Image]]`, `torch.Tensor`, `np.array`, `list[torch.Tensor]`, `list[np.array]`):
34 The input video. It can be one of the following:
35 * list of the PIL images.
36 * list of list of PIL images.
37 * 4D Torch tensors (expected shape for each tensor `(num_frames, num_channels, height, width)`).
38 * 4D NumPy arrays (expected shape for each array `(num_frames, height, width, num_channels)`).
39 * list of 4D Torch tensors (expected shape for each tensor `(num_frames, num_channels, height,
40 width)`).
41 * list of 4D NumPy arrays (expected shape for each array `(num_frames, height, width, num_channels)`).
42 * 5D NumPy arrays: expected shape for each array `(batch_size, num_frames, height, width,
43 num_channels)`.
44 * 5D Torch tensors: expected shape for each array `(batch_size, num_frames, num_channels, height,
45 width)`.
46 height (`int`, *optional*, defaults to `None`):
47 The height in preprocessed frames of the video. If `None`, will use the `get_default_height_width()` to
48 get default height.
49 width (`int`, *optional*`, defaults to `None`):
50 The width in preprocessed frames of the video. If `None`, will use get_default_height_width()` to get
51 the default width.
52
53 Returns:
54 `torch.Tensor` of shape `(batch_size, num_channels, num_frames, height, width)`:
55 A 5D tensor holding the batched channels-first video(s).
56 """
57 if isinstance(video, list) and isinstance(video[0], np.ndarray) and video[0].ndim == 5:
58 warnings.warn(
59 "Passing `video` as a list of 5d np.ndarray is deprecated."
60 "Please concatenate the list along the batch dimension and pass it as a single 5d np.ndarray",
61 FutureWarning,
62 )
63 video = np.concatenate(video, axis=0)
64 if isinstance(video, list) and isinstance(video[0], torch.Tensor) and video[0].ndim == 5:
65 warnings.warn(
66 "Passing `video` as a list of 5d torch.Tensor is deprecated."
67 "Please concatenate the list along the batch dimension and pass it as a single 5d torch.Tensor",
68 FutureWarning,
69 )
70 video = torch.cat(video, axis=0)
71
72 # ensure the input is a list of videos:
73 # - if it is a batch of videos (5d torch.Tensor or np.ndarray), it is converted to a list of videos (a list of 4d torch.Tensor or np.ndarray)
74 # - if it is a single video, it is converted to a list of one video.
75 if isinstance(video, (np.ndarray, torch.Tensor)) and video.ndim == 5:
76 video = list(video)
77 elif isinstance(video, list) and is_valid_image(video[0]) or is_valid_image_imagelist(video):
78 video = [video]
79 elif isinstance(video, list) and is_valid_image_imagelist(video[0]):
80 video = video
81 else:
82 raise ValueError(
83 "Input is in incorrect format. Currently, we only support numpy.ndarray, torch.Tensor, PIL.Image.Image"
84 )
85

Callers 15

__call__Method · 0.80
__call__Method · 0.80
preprocess_conditionsMethod · 0.80
__call__Method · 0.80
__call__Method · 0.80
prepare_latentsMethod · 0.80
__call__Method · 0.80
__call__Method · 0.80
__call__Method · 0.80

Calls 3

is_valid_imageFunction · 0.85
is_valid_image_imagelistFunction · 0.85
preprocessMethod · 0.45

Tested by 3