wevisone-vl
wevisone-vl is Apache 2.0, 2B/4B weights and demo. It is ranked #144 on the AI Radar, in Open & local models, first seen 9 days ago and shared in 5 posts (150.6k views).
What wevisone-vl says about itself
WeVisOne-VL is a powerful VLM by the WeChat Vision Team at Tencent, unifying object-level and pixel-level perception from points and boxes to masks and alpha mattes. - Tencent/WeVisOne-VL
GitHub - Tencent/WeVisOne-VL: WeVisOne-VL is a powerful VLM by the WeChat Vision Team at Tencent, unifying object-level and pixel-level perception from points and boxes to masks and alpha mattes. · GitHub Skip to content Navigation Menu Sign in Appearance settings Search / Sign in Sign up Appearance settings You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session. You switched accounts on another tab or window. Reload to refresh your session. Dismiss alert {{ message }} Repository navigation WeVisOne-VL Public Notifications You must be signed in to…
What people said about wevisone-vl on X
we gave our AI an eye for detail. 👀 Meet WeVisOne-VL, an open-source 2B/4B model from our Weixin Vision team. It finds and counts objects, reads text, and makes precise masks and cutouts—no separate SAM needed. Not in the image? "None." https://github.com/Tencent/WeVisOne-VL
— @Weixin_WeChat, 3 days ago · 567 likes · see the post
🔥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 =…
— @NFT_Chen, 3 days ago · 158 likes · see the post
👀 腾讯刚开源了 WeVisOne-VL，一个模型就能把找东西、数东西、读文字、抠图这些活一起包了。 WeVisOne-VL 出自腾讯微信视觉，有 2B 和 4B 两个版本，Apache 2.0 协议；README 报告 4B 版在 LVIS 检测上 F1 为 55.3，最强基线是 50.7。 做视觉应用常见的情况是：检测用一个模型，分割再接一个 SAM，OCR 又是一套，抠图还得另找，光是把几个模型的输入输出串起来就够喝一壶。 WeVisOne-VL 把目标检测、指代定位、计数、OCR、指代分割和可提示抠图都统一成结构化文本输出，掩码和 alpha 抠图靠一个约 960 万参数的小像素解码器出，不依赖 SAM。…
— @Ryrenz, 9 days ago · 101 likes · see the post
Alternatives to wevisone-vl
- kimi-k3.1-pro — Releasing the model weights of Kimi K3.1 Pro
- unsloth.ai — Guide to running Mistral Large 4 GGUFs locally with Unsloth and llama.cpp.
- niklaslenz.com — Play the world in your browser. Every number, the exact command and the raw output
- qwen3.8-flash-next-gguf — Image-Text-to-Text model with 177B parameters. Download, explore files and run it on Hugging Face.
- project-maya — Plus a round of fixes, UI improvements and community PRs.
- twil-8b — Text Generation model with 9B parameters. Download, explore files and run it on Hugging Face.
wevisone-vl in numbers
- Rank on the AI Radar: #144 of 10412
- Shared in 5 posts by 5 accounts: @Weixin_WeChat, @NFT_Chen, @Ryrenz, @TencentAI_News
- 150.6k views on those posts
- First seen 9 days ago, last shared 3 days ago
- Pricing seen by AGK Intelligence: open source
- Market: Open & local models
FAQ
What is wevisone-vl?
Apache 2.0, 2B/4B weights and demo It was first shared on X 9 days ago and is ranked #144 on the AI Radar.
Is wevisone-vl free?
It is open source.
Who shared wevisone-vl?
5 accounts on X, including @Weixin_WeChat, @NFT_Chen, @Ryrenz, in 5 posts totalling 150.6k views.
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. 65.5k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 16:50 UTC. Full method.