q: [B, Lq, Nq, C1]. k: [B, Lk, Nk, C1]. v: [B, Lk, Nk, C2]. Nq must be divisible by Nk. q_lens

videos: A list of videos each with shape [C, T, H, W].

Sets the discrete timesteps used for the diffusion chain (to be run before inference). Args: num_inference_steps (`int`):

Predict the sample from the previous timestep by reversing the SDE. This function propagates the sample with the multistep DPMSolver.

Returns the smallest integer greater than or equal to 'number' that is divisible by 'factor'.

x: [B, L, N, C]. grid_sizes: [B, 3]. freqs: [M, C // 2].

Returns the closest integer to 'number' that is divisible by 'factor'.

Rescales the image so that the following conditions are met: 1. Both dimensions (height and width) are divisible by 'factor'. 2. The to

r""" Reconstruct video tensors from patch embeddings. Args: x (List[Tensor]): List of patchified features

Returns the largest integer less than or equal to 'number' that is divisible by 'factor'.

r""" Generates video frames from text prompt using diffusion process. Args: input_prompt (`str`): Text pr

"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t

"Dynamic thresholding: At each sampling step we set s to a certain percentile absolute pixel value in xt0 (the prediction of x_0 at t

compatible with diffusers add_noise()

r""" Forward pass through the diffusion model Args: x (List[Tensor]): List of input video tensors, each w

Args: query (torch.tensor): B M H K key (torch.tensor): B M H K shape (tuple): (N_t, N_h, N_w) ref_target_masks: [B, N

Resize image or tensor to the target size without padding.

calculate the number of frames for video used for model inputs. Args: ele (dict): a dict contains the configuration of video.