Dev Radar
Support
LiveUpdated 2026-11-03 14:22 UTC

🔥厉害了!微信视觉团队直接开源2B/4B视觉大模型 WeVisOne-VL,一个模型搞定检测+抠图!真正做到物体级 + 像素级统一感知!

🔥厉害了!微信视觉团队直接开源2B/4B视觉大模型 WeVisOne-VL,一个模型搞定检测+抠图!真正做到物体级 + 像素级统一感知! 核心亮点: 🔹检测、指代、计数、指点、OCR、分割、Alpha抠图,全部一个模型搞定 🔹仅…🔥厉害了!微信视觉团队直接开源2B/4B视觉大模型 WeVisOne-VL,一个模型搞定检测+抠图!真正做到物体级 + 像素级统一感知! 核心亮点: 🔹检测、指代、计数、指点、OCR、分割、Alpha抠图,全部一个模型搞定 🔹仅…🔥厉害了!微信视觉团队直接开源2B/4B视觉大模型 WeVisOne-VL,一个模型搞定检测+抠图!真正做到物体级 + 像素级统一感知! 核心亮点: 🔹检测、指代、计数、指点、OCR、分割、Alpha抠图,全部一个模型搞定 🔹仅…🔥厉害了!微信视觉团队直接开源2B/4B视觉大模型 WeVisOne-VL,一个模型搞定检测+抠图!真正做到物体级 + 像素级统一感知! 核心亮点: 🔹检测、指代、计数、指点、OCR、分割、Alpha抠图,全部一个模型搞定 🔹仅…

This is a dev post classified by AGK Intelligence as Other (a tool drop), kept by the Dev Radar because it carries real work, not commentary.

🔥厉害了!微信视觉团队直接开源2B/4B视觉大模型 WeVisOne-VL,一个模型搞定检测+抠图!真正做到物体级 + 像素级统一感知! 核心亮点: 🔹检测、指代、计数、指点、OCR、分割、Alpha抠图,全部一个模型搞定 🔹仅 9.6M 轻量 Pixel Decoder,不需要单独的 SAM 🔹图里没有目标?直接回 None,拒识率 96.4%,拒绝瞎框 🔹基于 Qwen3-VL,30+ 基准全面领先 快速上手: 1️⃣git clone https://github.com/Tencent/WeVisOne-VL.git && pip install -e . 2️⃣model = WeVisOneVL("tencent/WeVisOne-VL-4B")(或换 2B) 3️⃣model.predict(image, task="matting", query="person") 直接出高精度抠图 在线 Demo 已开放: •2B:https://huggingface.co/spaces/hugging-apps/wevisone-vl-2b •4B:https://huggingface.co/spaces/hugging-apps/wevisone-vl-4b GitHub:https://github.com/Tencent/WeVisOne-VL
 #

Posted by SuSu_酥酥👅 (26k followers) 57 min ago · 16 likes · 1.7k views · view the original post on X. Kept by the Dev Radar as Other. Tools mentioned: wevisone-vl.git, wevisone-vl-2b, wevisone-vl-4b, wevisone-vl.

More dev work like this

Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 31.4k posts from 5k X accounts over the last 21 days, 9.1k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-03 14:22 UTC. Full method.