Compute attention with explicit attention weights for visualization. Returns both output and attention weights.

The index for the first timestep. It should be set from pipeline with `set_begin_index` method.

The index for the first timestep. It should be set from pipeline with `set_begin_index` method.

Calculate width and height given an aspect ratio (h:w), total area, and divisibility constraint. Args: aspect_ratio (str):

Destroy the sequence parallel group.

x: [B, L, C].

x: [B, L, C].

imgs: [B, 3, H, W] of torch.float32. - mean: [0.48145466, 0.4578275, 0.40821073] - std: [0.26862954, 0.2613025

x: [B, L1, C]. context: [B, L2, C] or None. mask: [B, L2] or [B, L1, L2] or None.

Fix bfloat16 support for nearest neighbor interpolation.

Fix bfloat16 support for nearest neighbor interpolation.

x: [B, L, C].

ids: [B, L] of torch.LongTensor.

r""" Args: x(Tensor): Shape [B, L, C]

r""" Args: x(Tensor): Shape [B, L, C]

r""" Args: x(Tensor): Shape [B, L, C] seq_lens(Tensor): Shape [B] grid_sizes(Tensor): Shape [B, 3], the se

r""" Args: x(Tensor): Shape [B, L1, C] context(Tensor): Shape [B, L2, C] context_lens(Tensor): Shape [B]

r""" Args: x(Tensor): Shape [B, L1, C] context(Tensor): Shape [B, L2, C] context_lens(Tensor): Shape [B]

r""" Args: x(Tensor): Shape [B, L, C] e(Tensor): Shape [B, L1, 6, C] seq_lens(Tensor): Shape [B], length o

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