Nodes/ComfyUI-SAM-Audio/SAM-Audio Video Separate
ComfyUI Node

SAM-Audio Video Separate

Separates the sound associated with a white mask region from a native ComfyUI VIDEO value, using the video's embedded audio track.

By ethanfel·Created 2 days ago·Updated 2 days ago· 3
SAM-Audio Video Separate
  • pipeline
  • video
  • mask
  • target
  • residual
description
seed0
inference_steps32
chunk_duration10.0
chunk_overlap1.0
Categoryaudio/SAM-Audio

Inputs (8)

NameTypeDefaultDescription
pipelineSAM_AUDIO_PIPELINE
videoVIDEOA native ComfyUI VIDEO containing frames and an embedded audio track.
maskMASKWhite selects the visible object whose sound should be isolated. Use one mask for all frames or one per frame.
descriptionSTRINGOptional text guidance to combine with the visual prompt.
seedINT00–18446744073709550000Controls SAM-Audio's initial noise for reproducible separation.
inference_stepsINT322–128Number of midpoint function evaluations. Higher values are slower and may improve quality.
chunk_durationFLOAT10.00–3600Seconds processed per pass. Use 0 to process the entire clip at once.
chunk_overlapFLOAT1.00–60Seconds shared by adjacent chunks for a smooth crossfade.

Outputs (2)

NameTypeDescription
targetAUDIO
residualAUDIO