fastvideo.v1.training.wan_i2v_training_pipeline

`fastvideo.v1.training.wan_i2v_training_pipeline`#

A training pipeline for Wan.

`logger`
`vsa_available`

class fastvideo.v1.training.wan_i2v_training_pipeline.WanI2VTrainingPipeline(model_path: str, fastvideo_args: fastvideo.v1.fastvideo_args.TrainingArgs, required_config_modules: list[str] | None = None, loaded_modules: dict[str, torch.nn.Module] | None = None)[source]#

A training pipeline for Wan.

Initialization

Initialize the pipeline. After init, the pipeline should be ready to use. The pipeline should be stateless and not hold any batch state.

create_training_stages(training_args: fastvideo.v1.fastvideo_args.TrainingArgs)[source]#: May be used in future refactors.

initialize_pipeline(fastvideo_args: fastvideo.v1.fastvideo_args.FastVideoArgs)[source]#

initialize_validation_pipeline(training_args: fastvideo.v1.fastvideo_args.TrainingArgs)[source]#

fastvideo.v1.training.wan_i2v_training_pipeline.logger[source]#: ‘init_logger(…)’

fastvideo.v1.training.wan_i2v_training_pipeline.main(args) → None[source]#

fastvideo.v1.training.wan_i2v_training_pipeline.vsa_available[source]#: ‘is_vsa_available(…)’