Segment Anything Model 3
ModelUnified open-weights model for detecting, segmenting and tracking objects in images and video using text, exemplar and visual prompts.
- Nov 19, 2025
- —
- textimagevideo
- —
- —
- 1
Releases
Nov 19, 2025Segment Anything Model 3 releasedOpen weights
Meta released SAM 3 for text-, exemplar- and visual-prompted detection, segmentation and tracking in images and video.