SAM 3.1 is out! It's open source and available through the Meta API and Hugging Face for…
This is a AI post classified by Jev as AI image (a model release), kept by the AI Radar because it carries real work, not commentary.
SAM 3.1 is out! It's open source and available through the Meta API and Hugging Face for image and video segmentation. SAM is a standard foundation model for computer vision at this point. The changes from SAM 3 are mostly architectural, which make inference ~7× faster in some cases for segmentation of lots of objects without sacrificing accuracy. I tried it with the prompt "hot air balloon." 🎈
Posted by Matt Deitke (14.9k followers) 2 h ago · 40 likes · 1.8k views · view the original post on X. Kept by the AI Radar as AI image.
More AI work like this
- Love these — @NeoAIForecast
- A "Google nano banana" level NS/FW anatomy image model you can run your laptop locally. — @0x0SojalSec
- A few Qwen image 2.1 images generated on my NVIDIA DGX Spark at home while I’m flying at… — @MichaelGannotti
- If you're running Qwen-Image-2.1 — @ItsmeAjayKV
- Qwen Image 2.1. — @NeoAIForecast
- We made an easy image loader for Qwen Image 2.1. Now you can generate your images on the… — @Blackfrost_AI
- The masculine urge to spend dozens of hours beating impossibly difficult, entirely… — @thefinnmckenty
- Just run some quick tests for Qwen-Image-2.1 and compare to Krea2. — @jmurillocode
Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 35.3k posts from 5k X accounts over the last 14 days, 1.5k tools, 19 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-21 02:10 UTC. Full method.