Meta releases open-source SAM 3.1 with up to 7× faster inference for dense segmentation
armand_ruiz · x · 2026-09-21
- Meta has released SAM 3.1, open source and available via the Meta API and Hugging Face for both image and video segmentation.
- The changes from SAM 3 are mostly architectural, making inference up to 7× faster in some cases when segmenting many objects, without sacrificing accuracy.
- Author Matt Deitke tested it with the prompt "hot air balloon" 🎈. SAM has become a standard foundation model for computer vision.
Related event: Meta Open-Sources SAM 3.1 with Up to 7x Faster Inference(2 posts)→
More from Multimodal
- Open-source full-duplex speech model caramel-1: 413M params, sounds human but can't hold a conversation — alexcovo_eth · 2026-11-12
- H3-Image touts 16MP generation and realtime inference via 2-step LoRA on ZeroGPU — linoy_tsaban · 2026-11-12
- MiniMax H3 Image renders 4K portrait in half the time Seedream 5.5 takes for 2K — heyronir · 2026-11-12
- Endless screensaver of self-assembling quantum cryostats, made with Gemini 4 Carbon — hapticdata · 2026-11-12
- Apple's ADM 3 Cloud image model ranks #42 in editing and #85 in text-to-image on Artificial Analysis arena — ArtificialAnlys · 2026-11-12
- Adobe Firefly debuts Story Builder tool for streamlined visual storytelling — LudovicCreator · 2026-11-12