fastvideo.v1.configs.pipelines.registry
#
Registry for pipeline weight-specific configurations.
Module Contents#
Functions#
Get the appropriate configuration class for a given pipeline name or path. |
Data#
API#
- fastvideo.v1.configs.pipelines.registry.PIPELINE_DETECTOR: Dict[str, Callable[[str], bool]][source]#
None
- fastvideo.v1.configs.pipelines.registry.PIPELINE_FALLBACK_CONFIG: Dict[str, Type[fastvideo.v1.configs.pipelines.base.PipelineConfig]][source]#
None
- fastvideo.v1.configs.pipelines.registry.PIPE_NAME_TO_CONFIG: Dict[str, Type[fastvideo.v1.configs.pipelines.base.PipelineConfig]][source]#
None
- fastvideo.v1.configs.pipelines.registry.get_pipeline_config_cls_from_name(pipeline_name_or_path: str) Type[fastvideo.v1.configs.pipelines.base.PipelineConfig] [source]#
Get the appropriate configuration class for a given pipeline name or path.
This function implements a multi-step lookup process to find the most suitable configuration class for a given pipeline. It follows this order:
Exact match in the PIPE_NAME_TO_CONFIG
Partial match in the PIPE_NAME_TO_CONFIG
Fallback to class name in the model_index.json
else raise an error
- Parameters:
pipeline_name_or_path (str) –
The name or path of the pipeline. This can be:
A registered model ID (e.g., “FastVideo/FastHunyuan-diffusers”)
A local path to a model directory
A model ID that will be downloaded
- Returns:
The configuration class that best matches the pipeline. This will be one of: - A specific weight configuration class if an exact match is found - A fallback configuration class based on the pipeline architecture - The base PipelineConfig class if no matches are found
- Return type:
Type[PipelineConfig]
.. note::
For local paths, the function will verify the model configuration
For remote models, it will attempt to download the model index
Warning messages are logged when falling back to less specific configurations