ComfyUI Node: SAM3 Propagate

Authored by PozzettiAndrea

Created

Updated

368 stars

Category

SAM3/video

Inputs

sam3_model SAM3_MODEL
video_state SAM3_VIDEO_STATE
start_frame INT
end_frame INT
direction
  • forward
  • backward
  • both
offload_model BOOLEAN

Outputs

SAM3_VIDEO_MASKS

SAM3_VIDEO_SCORES

SAM3_VIDEO_STATE

Extension: ComfyUI-SAM3

ComfyUI integration for Meta's SAM3 model enabling open-vocabulary image segmentation using natural language text prompts, with automatic model download, geometric refinement, and flexible confidence thresholds.

Authored by PozzettiAndrea

View Nodes

Run ComfyUI workflows in the Cloud!

No downloads or installs are required. Pay only for active GPU usage, not idle time. No complex setups and dependency issues

Learn more