ComfyUI-SAM3

by PozzettiAndrea0 starssuccess

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.

View on GitHub

Nodes (14)

(down)Load SAM3 ModelLoadSAM3ModelSAM3
SAM3 BBox Collector 📦SAM3BBoxCollectorSAM3
SAM3 Combine BoxesSAM3CombineBoxesSAM3/prompts
SAM3 Combine PointsSAM3CombinePointsSAM3/prompts
SAM3 Create BoxSAM3CreateBoxSAM3/prompts
SAM3 Create PointSAM3CreatePointSAM3/prompts
SAM3 Text SegmentationSAM3GroundingSAM3/Grounding
SAM3 Multi-Region Collector 🎯SAM3MultiRegionCollectorSAM3
SAM3 Multiprompt SegmentationSAM3MultipromptSegmentationSAM3
SAM3 Point CollectorSAM3PointCollectorSAM3
SAM3 PropagateSAM3PropagateSAM3/video
SAM3 Point SegmentationSAM3SegmentationSAM3
SAM3 Video OutputSAM3VideoOutputSAM3/video
SAM3 Video SegmentationSAM3VideoSegmentationSAM3/video