ComfyUI Node: SAM3 Video Segmentation

Authored by PozzettiAndrea

Created

Updated

368 stars

Category

SAM3/video

Inputs

video_frames IMAGE
prompt_mode
  • text
  • point
  • box
text_prompt STRING
positive_points SAM3_POINTS_PROMPT
negative_points SAM3_POINTS_PROMPT
positive_boxes SAM3_BOXES_PROMPT
negative_boxes SAM3_BOXES_PROMPT
frame_idx INT
score_threshold FLOAT

Outputs

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

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