Scenario
← All Models
Image

SAM 3.1 Image

Use it ↗

SAM 3.1 by Meta segments any image into isolated object masks. Guide detection with a text prompt or up to 10 bounding boxes. Outputs one PNG mask per object.

Segment images with Meta SAM 3.1: text and/or box prompting, or interactive tracking (points, box, mask).

More models from Meta