r""" Initialize the diffusion model backbone. Args: model_type (`str`, *optional*, defaults to 't2v'): Mo

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

Initialize the DMD (Distribution Matching Distillation) module. This class is self-contained and compute generator and fake score los

Initialize the Diffusion loss module.

Initialize the GAN module. This class is self-contained and compute generator and fake score losses in the forward pass.

Initialize the Re-DMD (Rewarded Distribution Matching Distillation) module. This class is self-contained and compute rewarded generat

Initialize the DMD (Distribution Matching Distillation) module. This class is self-contained and compute generator and fake score los

Initialize the DMD (Distribution Matching Distillation) module. This class is self-contained and compute generator and fake score los

Initialize the ODERegression module. This class is self-contained and compute generator losses in the forward pass given prec

Initialize pretrained TAEHV from the given checkpoint. Arg: checkpoint_path: path to weight file to load. taehv.pth for Hunyuan,

r""" Feature extraction through the diffusion model Args: x (List[Tensor]): List of input video tensors,

Randomly generate a timestep tensor based on the generator's task type. It uniformly samples a timestep from the range [min_timestep,

Pad the sequences to the maximum length.

Pad the sequences to the maximum length.

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

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:

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

Optionally simulate the generator's input from noise using backward simulation and then run the generator for one-step. Input

Optionally simulate the generator's input from noise using backward simulation and then run the generator for one-step. Input

Diffusion forward corruption process. Input: - clean_latent: the clean latent with shape [B*T, C, H, W] - noi

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.

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]

Setup the optimizer. We provide a reasonable default that works well. If you want to use something else, you can pass a tuple in the

Generate image/videos from noise and train the critic with generated samples. The noisy input to the generator is backward simulated.

Generate image/videos from noise and train the critic with generated samples. The noisy input to the generator is backward simulated.