ComfyUI Node: SAM3 Video Segmentation

Authored by PozzettiAndrea

Created

Updated

554 stars

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

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

View Nodes

Looking for a different node?

More nodes in ComfyUI-SAM3

Other SAM3/video nodes

Run ComfyUI workflows without the setup

No installs, no CUDA version roulette, no GPU sitting idle on your bill. Bring a workflow and run it in the browser.

Learn more