Segment images and video
Identify object regions in images or video frames.
Desired outcome
Object masks over visual content.
Explore from the outcome
Where this function can lead
These documented connections are starting points for selection, not a ranked list.
Model releases
Identifiable models documented for this function.
- SAM 2.1 Hiera Large
Segments prompted objects in images and follows their masks through video frames.
Link evidence: SAM 2.1 Hiera Large model card
Typical inputs
- Image or video and selection prompts
Typical outputs
- Segmentation masks
Sources
Last reviewed 2026-09-30