{"skill":{"slug":"sam","displayName":"Segment Anything","summary":"Use SAM (Segment Anything Model) to remove image backgrounds and extract foreground subjects as transparent PNGs. Use when users want to remove backgrounds,...","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":308,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1773492637505,"updatedAt":1777529889770},"latestVersion":{"version":"1.0.0","createdAt":1773492637505,"changelog":"- Initial release of \"sam-segmentation\" skill for background removal and image segmentation.\n- Extracts foreground subjects from images using Meta's Segment Anything Model (SAM) and saves as transparent PNGs.\n- Supports multiple model sizes (`vit_b`, `vit_l`, `vit_h`) for different speed and quality needs.\n- Allows foreground hint points, grid-sweep mode for extracting all distinct elements, and various mask filtering parameters.\n- Automatically installs needed dependencies (`segment_anything`, Pillow, numpy, torch, torchvision) on first use.\n- Model checkpoint is auto-downloaded if not provided.","license":"MIT-0"},"metadata":{"os":null,"systems":null},"owner":{"handle":"scikkk","userId":"s171sgccp6wt09makas274ye9584ktsf","displayName":"scikkk","image":"https://avatars.githubusercontent.com/u/77485593?v=4"},"moderation":null}