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.

x of shape [B, f, c, h, w]

Convert the diffusion network's noise prediction to x0 predidction. noise: the predicted noise with shape [B, C, H, W] xt: th

Convert the diffusion network's velocity prediction to x0 predidction. velocity: the predicted noise with shape [B, C, H, W]

Convert the diffusion network's x0 prediction to noise predidction. x0: the predicted clean data with shape [B, C, H, W] xt:

A method to decode a latent representation to an image or video. Input: a tensor with shape [B, F, C, H // S, W // S] where S is the

latents: [batch_size, num_frames, num_channels, height, width] output: [batch_size, num_channels, num_frames, height, width]

Activates gradient checkpointing for the current model (may be referred to as *activation checkpointing* or *checkpoint activations*

Input: - videos_rgb: a tensor with shape [B, F+1, C, H, W] in RGB format, [0-1] Output: - video_rgb: a tensor

x: [b, l, d]

x: [b, l, d]

x: (b, l, d)

x: (b, l, d)

Returns: W: [num_heads, out_features, in_features] W = W_left @ W_right + I * 0.5 where I is the identity

Args: W0_W2: [B, 2M, K] or [B, 2 * Hidden, D] W1: [B, K, M] or [B, D, Hidden] K, V: [M, N,

x: [B, D1, D2] x_add: [B, D1, D2] tgt_scale: [B, D1] eps: float tgt_dtype: if None, will use the same dtype a

Args: W0_W2: [B, 2 * Hidden, D] W1: [B, K, M] or [B, D, Hidden] X: [M, N, K] or [B, num_Tokens,

A method to run diffusion model. Input: - noisy_image_or_video: a tensor with shape [B, F, C, H, W] where the number of

A method to tokenize text prompts with a tokenizer and encode them into a latent representation. Input: a list of strings.

Only support training right now Input: - data_dict: a dictionary containing the input data. all data tha

Only support training right now Input: - data_dict: a dictionary containing the input data. all data tha

Only support training right now Input: - data_dict: a dictionary containing the input data. all data tha

Input: - text_prompts: a list of text prompts. Output: dict: - prompt_embeds: a tensor with s

Input: - text_prompts: a list of text prompts. Output: dict: - prompt_embeds: a tensor with s

A method to run diffusion model. Input: - noisy_image_or_video: a tensor with shape [B, F, C, H, W] where the number of

A method to run diffusion model. Input: - noisy_image_or_video: a tensor with shape [B, F, C, H, W] where the number of

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

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

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

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.

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, num_heads, C / num_heads] seq_lens(Tensor): Shape [B] grid_sizes(Tensor

r""" Args: x(Tensor): Shape [B, L, num_heads, C / num_heads] seq_lens(Tensor): Shape [B] grid_sizes(Tensor

r""" Args: x(Tensor): Shape [B, L, num_heads, C / num_heads] seq_lens(Tensor): Shape [B] grid_sizes(Tensor

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, 6, C] seq_lens(Tensor): Shape [B], length of ea

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

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

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

r""" Args: x(Tensor): Shape [B, L, num_heads, C / num_heads] seq_lens(Tensor): Shape [B] grid_sizes(Tensor

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, 6, C] seq_lens(Tensor): Shape [B], length of ea

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

x of shape [B, C, F, H, W]

r""" Args: x (Tensor): chunked_x, where the seq_len dimension is the seq_len for each ar chunk! Shape [real_batch

r""" Args: x (Tensor): chunked_x, where the seq_len dimension is the seq_len for each ar chunk! Shape [real_batch