x_main: [B, n, D2], fp32 or bf16, recommended to be fp32 dx: [B, n, D2], bf16 dx_momentum: [B, n, D2], same dtype as x_main momentum_

r""" Generates video frames from input image and text prompt using diffusion process. Args: input_prompt (`str`):

Perform inference on the given noise and text prompts. Inputs: noise (torch.Tensor): The input noise tensor of shape

Run inference with the given diffusion / distilled generators. Input: - noise: a tensor sampled from N(0, 1) with shape

r""" Initialize model parameters using Xavier initialization.

A few custom initialization steps that should be called after the object is created. Currently, the only one we have is to bind a few

In previous fwd pass: dx0 = lr0 * dh * x2 * sigma * (1 + x0 * (1 - sigma)) dx2 = lr2 * dh * silu(x0) hidden_lr1 = lr1 * x2 * silu(x0)

Args: W0, W2: [B, M, K] or [B, Hidden, D] W1: [B, K, M] or [B, D, Hidden] X: [M, N, K] or [B, num_Tokens, D]

Args: W0, W2: [B, M, K] or [B, Hidden, D] W1: [B, K, M] or [B, D, Hidden] X: [M, N, K] or [B, num_Tokens, D]

Will be used to apply activation checkpointing to the WanAttentionBlock. Check if the submodule is a WanAttentionBlock.

Save a video tensor to disk using imageio. Args: video_tensor (torch.Tensor): Video tensor of shape [b, f, c, h, w] in uint8 for

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. Ar

Ensures interchangeability with schedulers that need to scale the denoising model input depending on the current timestep. A

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_index

Sets the begin index for the scheduler. This function should be run from pipeline before the inference. Args: begin_inde

Adjusts the state of each module in the object. Parameters: - module_grad (dict): A dictionary where each key is the name of

Adjusts the state of each module in the object. Parameters: - module_grad (dict): A dictionary where each key is the name of

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

Note: 1. need all rank have the same size and type of x.

The index counter for current timestep. It will increase 1 after each scheduler step.

The index counter for current timestep. It will increase 1 after each scheduler step.

Convert a string to a boolean. Supported true values: 'yes', 'true', 't', 'y', '1' Supported false values: 'no', 'false', 'f', 'n', '0'

x: A list of videos each with shape [C, T, H, W]. t: [B]. context: A list of text embeddings each with s

Convert str to bool/int/float if possible

XLMRobertaLarge adapted from Huggingface.