Extract values from a 1-D numpy array for a batch of indices. :param arr: the 1-D numpy array. :param timesteps: a tensor of indices i

Take the mean over all non-batch dimensions.

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

Apply the model to get p(x_{t-1} | x_t), as well as a prediction of the initial x, x_0. :param model: the model, which tak

Compute the mean and variance of the diffusion posterior: q(x_{t-1} | x_t, x_0)

Get a term for the variational lower-bound. The resulting units are bits (rather than nats, as one might expect). This all

A fast approximation of the cumulative distribution function of the standard normal.

Compute what the p_mean_variance output would have been, should the model's score function be conditioned by cond_fn. See

Compute the KL divergence between two gaussians. Shapes are automatically broadcasted, so batches can be compared to scalars, among ot

Diffuse the data for a given number of diffusion steps. In other words, sample from q(x_t | x_0). :param x_start: the init

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

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

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().

Generate samples from the model using DDIM. Same usage as p_sample_loop().

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""" Args: sample (`torch.FloatTensor`): (batch, channel, height, width) noisy inputs tensor timestep (`torch.FloatTen

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

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

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

Generate samples from the model. :param model: the model module. :param shape: the shape of the samples, (N, C, H, W).

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

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

Importance-sample timesteps for a batch. :param batch_size: the number of timesteps. :param device: the torch device to sa

r""" Enable sliced attention computation. When this option is enabled, the attention module will split the input tensor in slices, to

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

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

Drops text to enable classifier-free guidance.

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

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

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