Meta ships SAM 3.1 on Model API: detection, segmentation, tracking in one call
AIatMeta · x · 2026-09-19
Meta has released Segment Anything Model 3.1 on its Meta Model API, pitched as a fast, lightweight model.
- Find objects in images and video with a short phrase
- One API call returns detections, pixel-precise segmentation masks, and identity-preserving video tracks
- The inference endpoint is tuned for SAM 3.1's architecture
Related event: Meta Launches SAM 3.1 API: Detection, Segmentation and Tracking in One Call(5 posts)→
More from Multimodal
- Free course covers the 4 hard problems of production generative media agents — Al_Grigor · 2026-11-04
- PixelBench: testing multimodal models pixel-by-pixel instead of with QA — bdsqlsz · 2026-11-04
- Kitten-TTS 2 offers free voice cloning on laptops, no GPU needed — solyarisoftware · 2026-11-04
- "We'll Take Your RAM": a fully local-hardware cyberpunk meme from 2030 San Francisco — Wonderful-Yak-3348 · 2026-11-04
- Openfilm: open-source AI video agent turns coding agents into video makers — solyarisoftware · 2026-11-04
- Microsoft reopens VibeVoice: 10-second voice cloning, 90-minute local TTS — solyarisoftware · 2026-11-04