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 for One-Shot Detection, Segmentation and Tracking(2 posts)→
More from Multimodal
- Blender scenes too sparse? Iterating references with GPT Image for 14 rounds adds detail — kevinkern · 2026-09-19
- Pika launches Product Ad app to generate high-end product videos with AI — aziz4ai · 2026-09-19
- HeyGen MCP in action: digital-human video built with Hyperframes — HeyGen · 2026-09-19
- Creator Shares 30-Second Epic Solo Battle Video Made with Seedance 2.5, Full Prompt Included — LudovicCreator · 2026-09-19
- Midjourney v8.2 prompt trick: swap one word to reshape the whole image — tisch_eins · 2026-09-19
- Local AI music: YuE2 generates a full cover song on your own machine via Pinokio — cocktailpeanut · 2026-09-19