Generate a bivariate generalized Gaussian kernel. Described in `Parameter Estimation For Multivariate Generalized Gaussian Distribut

Generate a plateau-like anisotropic kernel. 1 / (1+x^(beta)) Ref: https://stats.stackexchange.com/questions/203629/is-there-a-plateau-shaped

Bound `z`, an array of shape (..., d).

Build module from config or return the module itself. Args: module (Union[dict, nn.Module]): The module to build. builder (Regist

Converts a `code` to an index in the codebook.

Prepare the input just before the forward function. This method will move the tensors to the right device. Usually this method does not need t

Compute the gradient of the classifier, i.e. nabla_{x} log p_t(cond | x_t).

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

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_prog

Denoise at the final step, which is equivalent to solve the ODE from lambda_s to infty by first-order discretization.

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

Downloads a pre-trained DiT model from the web.

The adaptive step size solver based on singlestep DPM-Solver. Args: x: A pytorch tensor. The initial value at time `t_T`

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). This is the same as the DropConnect impl I created for E

Export the video frames to a video file using imageio lib to Avoid "green screen" issue (for example CogVideoX)

Export the video frames to a video file using imageio lib to Avoid "green screen" issue (for example CogVideoX)

Finds a pre-trained DiT model, downloading it if necessary. Alternatively, loads a model from a local path.

Apply Fourier transform to the input tensor and separate it into low-frequency and high-frequency components. Args: x (torch.Tensor): In

Apply Fourier transform to the input tensor and separate it into low-frequency and high-frequency components. Args: x (torch.Tensor): In