stages

fastvideo.pipelines.basic.stable_audio.stages.StableAudioConditioningStage

StableAudioConditioningStage(conditioner)

Run the conditioner over the prompt + duration and stash the DiT-ready (cross_attn_cond, cross_attn_mask, global_embed) triple on batch.extra (plus the negative-prompt triple when CFG is on).

fastvideo.pipelines.basic.stable_audio.stages.StableAudioConditioningStage.verify_input

verify_input(batch, fastvideo_args)

fastvideo.pipelines.basic.stable_audio.stages.StableAudioConditioningStage.verify_output

verify_output(batch, fastvideo_args)

fastvideo.pipelines.basic.stable_audio.stages.StableAudioConditioningStage.forward

forward(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> ForwardBatch

fastvideo.pipelines.basic.stable_audio.stages.StableAudioDecodingStage

StableAudioDecodingStage(vae)

Decode latent → audio waveform + slice to [start, end].

fastvideo.pipelines.basic.stable_audio.stages.StableAudioDecodingStage.verify_input

verify_input(batch, fastvideo_args)

fastvideo.pipelines.basic.stable_audio.stages.StableAudioDecodingStage.verify_output

verify_output(batch, fastvideo_args)

fastvideo.pipelines.basic.stable_audio.stages.StableAudioDecodingStage.forward

forward(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> ForwardBatch

fastvideo.pipelines.basic.stable_audio.stages.StableAudioDenoisingStage

StableAudioDenoisingStage(transformer)

k-diffusion dpmpp-3m-sde sampling loop.

fastvideo.pipelines.basic.stable_audio.stages.StableAudioDenoisingStage.verify_input

verify_input(batch, fastvideo_args)

fastvideo.pipelines.basic.stable_audio.stages.StableAudioDenoisingStage.verify_output

verify_output(batch, fastvideo_args)

fastvideo.pipelines.basic.stable_audio.stages.StableAudioDenoisingStage.forward

forward(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> ForwardBatch

fastvideo.pipelines.basic.stable_audio.stages.StableAudioLatentPreparationStage

StableAudioLatentPreparationStage(io_channels: int = 64, sample_size: int = 2097152, vae = None, sample_rate: int = 44100, audio_channels: int = 2)

fastvideo.pipelines.basic.stable_audio.stages.StableAudioLatentPreparationStage.verify_input

verify_input(batch, fastvideo_args)

fastvideo.pipelines.basic.stable_audio.stages.StableAudioLatentPreparationStage.verify_output

verify_output(batch, fastvideo_args)

fastvideo.pipelines.basic.stable_audio.stages.StableAudioLatentPreparationStage.forward

forward(batch: ForwardBatch, fastvideo_args: FastVideoArgs) -> ForwardBatch