Generate samples from the model and yield intermediate samples from each timestep of diffusion. Arguments are the same as

r"""Class decorator that extends a given class to save its source code when pickled. Example: from src.torch_utils import persistenc

Get the distribution q(x_t | x_0). :param x_start: the [N x C x ...] tensor of noiseless inputs. :param t: the number of d

Slide along the long edge, with the short edge as crop size

`root_name` should NOT start with '/

r"""Broadcasts the given set of scalars to all interested instances of `Collector`, across device and process boundaries. This function is ex

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized port

Create sinusoidal timestep embeddings. :param t: a 1-D Tensor of N indices, one per batch element. These

Create sinusoidal timestep embeddings. :param t: a 1-D Tensor of N indices, one per batch element. These b

Convert tensor data type from uint8 to float, divide value by 255.0 and permute the dimensions of clip tensor Args: clip (tor

Drops labels to enable classifier-free guidance.

Drops text to enable classifier-free guidance.

Drops labels to enable classifier-free guidance.

x: (N, T, patch_size**2 * C) imgs: (N, H, W, C)

x: (N, T, patch_size**2 * C) imgs: (N, H, W, C)

Update the reweighting using losses from a model. Sub-classes should override this method to update the reweighting using

Converts video dataset kwargs to image dataset kwargs

Get a numpy array of weights, one per diffusion step. The weights needn't be normalized, but must be positive.

Function invoked when calling the pipeline for generation. Args: prompt (`str` or `List[str]`, *optional*):

Perform the Decord initialization. Args: results (dict): The resulting dict to be modified and passed to the ne

Args: clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W) Returns: torch.tensor: randomly

Args: clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W) Returns: torch.tensor: scale re

Args: clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W) Returns: torch.tensor: scale re

Args: clip (torch.tensor): Video clip to be cropped. Size is (T, C, H, W) Returns: torch.tensor: center c

Args: clip (torch.tensor): video clip must be normalized. Size is (C, T, H, W)

Args: clip (torch.tensor, dtype=torch.uint8): Size is (T, C, H, W) Return: clip (torch.tensor, dtype=torc

Args: clip (torch.tensor): Size is (T, C, H, W) Return: clip (torch.tensor): Size is (T, C, H, W)

Perform the Decord initialization. Args: results (dict): The resulting dict to be modified and passed to the next

Perform the Decord initialization. Args: results (dict): The resulting dict to be modified and passed to the ne

Perform the Decord initialization. Args: results (dict): The resulting dict to be modified and passed to the next

r"""Convenience getter. `collector[name]` is a synonym for `collector.mean(name)`.