Fast CUDA implementation of `bias_act()` using custom ops.

Slow reference implementation of `bias_act()` using standard TensorFlow ops.

r"""Check that the given object is pickleable, raising an exception if it is not. This function is expected to be considerably more efficient

r"""Query the source code of a given Python module.

Get the prior KL term for the variational lower-bound, measured in bits-per-dim. This term can't be optimized, as it only

r"""Get or create a Python module for the given source code.

r"""Synchronize the global cumulative counters across devices and processes. Called internally by `Collector.update()`.

Slow reference implementation of `upfirdn2d()` using standard PyTorch ops.

Create a beta schedule that discretizes the given alpha_t_bar function, which defines the cumulative product of (1-beta) over time from t =

Finds the python object with the given name and calls it as a function.

Flush, close possible files, and remove stdout/stderr mirroring.

Compute the mean for the previous step, given a function cond_fn that computes the gradient of a conditional log probability with r

Sample x_{t-1} from the model using DDIM. Same usage as p_sample().

Use DDIM to sample from the model and yield intermediate samples from each timestep of DDIM. Same usage as p_sample_loop_p

Compute the log-likelihood of a Gaussian distribution discretizing to a given image. :param x: the target images. It is assumed that t

r""" Encodes the prompt into text encoder hidden states. Args: prompt (`str` or `List[str]`, *optional*):

Finds the class folders in a dataset. See :class:`DatasetFolder` for details.

Finds the class folders in a dataset. See :class:`DatasetFolder` for details.

Forward pass of Latte. x: (N, F, C, H, W) tensor of video inputs t: (N,) tensor of diffusion timesteps y: (N,) te

Forward pass of Latte. x: (N, F, C, H, W) tensor of video inputs t: (N,) tensor of diffusion timesteps y: (N,) tensor

grid_size: int of the grid height and width return: pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim]

grid_size: int of the grid height and width return: pos_embed: [grid_size*grid_size, embed_dim] or [1+grid_size*grid_size, embed_dim] (w/

This is the deprecated API for creating beta schedules. See get_named_beta_schedule() for the new library of schedules.

Finds the python object with the given name.

Args: clip (torch.tensor): Video clip to be normalized. Size is (T, C, H, W) Returns: flipped clip (torch.tensor): Size i

Determine whether the given object is a top-level function, i.e., defined at module scope using 'def'.

Determine whether the given object is a valid URL string.

Run sampling.

Args: clip (torch.tensor): Video clip to be normalized. Size is (T, C, H, W) mean (tuple): pixel RGB mean. Size is (3)

r"""Returns the number of scalars that were accumulated for the given statistic between the last two calls to `update()`, or zero if n

Sample x_{t-1} from the model at the given timestep. :param model: the model to sample from. :param x: the current tensor