fastvideo.v1.pipelines.stages.decoding

fastvideo.v1.pipelines.stages.decoding#

Decoding stage for diffusion pipelines.

Module Contents#

Classes#

DecodingStage

Stage for decoding latent representations into pixel space.

Data#

API#

class fastvideo.v1.pipelines.stages.decoding.DecodingStage(vae)[source]#

Bases: fastvideo.v1.pipelines.stages.base.PipelineStage

Stage for decoding latent representations into pixel space.

This stage handles the decoding of latent representations into the final output format (e.g., pixel values).

Initialization

forward(batch: fastvideo.v1.pipelines.pipeline_batch_info.ForwardBatch, fastvideo_args: fastvideo.v1.fastvideo_args.FastVideoArgs) fastvideo.v1.pipelines.pipeline_batch_info.ForwardBatch[source]#

Decode latent representations into pixel space.

Parameters:
  • batch – The current batch information.

  • fastvideo_args – The inference arguments.

Returns:

The batch with decoded outputs.

fastvideo.v1.pipelines.stages.decoding.logger[source]#

β€˜init_logger(…)’