fastvideo.v1.pipelines.stages.decoding

Decoding stage for diffusion pipelines.

Module Contents

Classes

DecodingStage

Stage for decoding latent representations into pixel space.

Data

logger

API

class fastvideo.v1.pipelines.stages.decoding.DecodingStage(vae)

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

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

‘init_logger(…)’