Nodes/ComfyUI_CineStyle/CS Video Segment (SAM3.1)
ComfyUI Node

CS Video Segment (SAM3.1)

Define semantic, mask, bounding-box, and positive/negative point prompts on any video frame, then propagate them in both directions.

By chflame163·Created 6 days ago·Updated 3 days ago· 8
CS Video Segment (SAM3.1)
  • model
  • images
  • video_input
  • proxy_video
  • MASK
  • anchor_mask
  • video_info
anchor_frame0
propagation_directionboth
max_objects16
prompt_data{"version":2,"objects":[]}
Category😺dzNodes/CineStyle/Video

Inputs (8)

NameTypeDefaultDescription
modelMODELOfficial ComfyUI SAM3/SAM3.1 model.
anchor_frameINT00–10000000Frame where the selector prompt is defined.
propagation_directionCOMBObothPropagate toward both sides of the anchor or only one side.
max_objectsINT161–64Maximum SAM3.1 multiplex object slots.
imagesoptIMAGEVideo frames as an IMAGE batch. Connect CS Load Video for Selector input.
video_inputoptVIDEOOptional VIDEO input from CS Load Video.
proxy_videooptVIDEOOptional VIDEO used only by Selector preview.
prompt_dataoptSTRING{"version":2,"objects":[]}Selector multi-object semantic, mask, bbox, and point prompts.

Outputs (3)

NameTypeDescription
MASKMASK
anchor_maskMASK
video_infoDICT