Generates video frames from text prompt using diffusion process. Modified to use memory-efficient motion optimization with manual gra

Initialize model parameters

Restore saved state to model. Args: model: Model to restore state to key: Identifier for the saved s

One step for the second-order multistep DPMSolver. Args: model_output_list (`List[torch.Tensor]`): The di

One step for the third-order multistep DPMSolver. Args: model_output_list (`List[torch.Tensor]`): The dir

One step for the UniC (B(h) version). Args: this_model_output (`torch.Tensor`): The model outputs at `x_

One step for the UniP (B(h) version). Alternatively, `self.solver_p` is used if is specified. Args: model_output (`torch

Memory-efficient sample optimization to minimize motion variance. Args: model: The transformer-based diffusion m

Resize, center crop and normalize for decord loaded video (torch.Tensor type) Parameters: video - video to process (torch.

Save the current state of model parameters without keeping computation graph. Args: model: Model to save state f

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

Args: iterations: Number of optimization iterations per step lr: Learning rate for optimization start_aft

r""" Initializes the image-to-video generation model components. Args: config (EasyDict): Object containi

r""" Initializes the image-to-video generation model components. Args: config (EasyDict): Object containi

r""" Initializes the Wan text-to-video generation model components. Args: config (EasyDict): Object conta

r""" Initializes the Wan text-to-video generation model components. Args: config (EasyDict): Object conta

Args: api_key: The API key for Dash Scope authentication and access to related services. model_name: Model name, 'qwe

Args: model_name: Use predefined model names such as 'QwenVL2.5_7B' and 'Qwen2.5_14B', which are specific version

Print information about available GPUs

Print current GPU memory status

read video using decord.VideoReader Args: ele (dict): a dict contains the configuration of video. support keys: - vid

read video using torchvision.io.read_video Args: ele (dict): a dict contains the configuration of video. support keys:

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.

Wrapped forward function with gradient checkpointing