Footer

Your go-to destination for discovering trending open-source projects and uncovering the insights that matter

Legal

  • Terms and conditions
  • Privacy policy

More

  • Pricing
  • Advertise
  • onedump
  • gosnakego
  • Contact us

Social

  • X (Twitter)
  • GitHub
Trendshift owl
What they build speaks louder than words
© 2026 Trendshift, created by Julian Li with ❤️
SignalAdvertise
Trendshift
SignalAdvertise
Sign in
Trendshift owl

Discover trends that matter

SignalAdvertise
DailyWeeklyMonthlyYearly
Live mentionsTopics
RepositoriesDevelopers
InsightsStats
Bifrost
Bifrost

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.

#Image recognition#Language model
Visit GitHub
Jupyter Notebook
1k
85
2 contributors
Custom license
AchievementsView all →
FeaturedAdvertise to 180K+ monthly visitors
Bifrost

Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

Momentum

How fast Tencent/WeVisOne-VL is gaining stars, and where it lands on Trendshift and GitHub Trending

Activity and trending

Stars, forks and merged pull requests each day or month, lined up with the repository's rank on Trendshift Trending

Oct 22 – Nov 5, 2026

Stars +933 in 15 days

0100200300
242

Forks +85 in 15 days

01020
18

Merged PRs 0 in 15 days

01

Trendshift Trendingwhere the repository ranked each day it made the top 25

Top 25 in Jupyter Notebook

25523155112121
Oct 22Oct 24Oct 26Oct 28Oct 30Nov 1Nov 3Nov 5
The left and right arrow keys step from day to day; Home and End go to the first and the last

Stars, forks, merged pull requests and Trendshift Trending rank, by day
DayStars gainedForks gainedMerged PRsJupyter Notebook
Thu, Oct 22, 2026+0+00Not trending
Fri, Oct 23, 2026+9+30#25
Sat, Oct 24, 2026+31+10#5
Sun, Oct 25, 2026+90+110#2
Mon, Oct 26, 2026+67+50#3
Tue, Oct 27, 2026+41+80#15
Wed, Oct 28, 2026+68+30#5
Thu, Oct 29, 2026+54+80#11
Fri, Oct 30, 2026+34+40#21
Sat, Oct 31, 2026+18+20Not trending
Sun, Nov 1, 2026+11+00Not trending
Mon, Nov 2, 2026+30+20#21
Tue, Nov 3, 2026+154+90Not trending
Wed, Nov 4, 2026+242+180Not trending
Thu, Nov 5, 2026+84+110Not trending
Total+933+850
  • 1#1 on the list
  • 7Rank that day
  • Not trending

Mentions and achievements

Where people are talking about Tencent/WeVisOne-VL, and every badge it has earned
    1. Nov 41 post

      • WeChat's vision team released WeVisOne-VL, open-source 2B and 4B models that find and count objects, read text and make precise masks with no separate SAM model. #WeVisOne #WeChat

        Read full on X, posted by @iCleanAI

        @iCleanAI · x.com

    2. Nov 33 posts

      • 微信这次开源的视觉模型，有点东西啊！🤔 WeVisOne-VL 只有 4B 参数，却能识字、识别物体、精准抠图，连头发丝都不放过。 官方评测中，部分指标甚至超过 8B、9B 模型。 最香的是，模型够小，还能本地部署。 以后处理和前任的合照，终于不用上传云端了。🤣

        Read full on X, posted by @AndyL5cc

        @AndyL5cc · x.com

      • https://t.co/0avwyxie0m

        Read full on X, posted by @Presidentlin

        @Presidentlin · x.com

      • 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…

        Read full on X, posted by @Weixin_WeChat

        @Weixin_WeChat · x.com

    3. 9 days earlier
    4. Oct 251 post

      • 1️⃣ 架构减法：用 9.6M 像素解码器取代沉重的串联管线 过去 VLM 做精细分割或抠图，主流做法是把 LLM 作为提示词生成器去调 SAM。WeVisOne-VL 直接用 <0>~<1000> 坐标词元 + <OBJ> 触发词元，将隐藏状态与多层级 ViT 特征喂给一个 9.6M 的超轻量 Pixel Decoder，单次前向推理即可输出从点、框到发丝级 Alpha Matte…

        Read full on X, posted by @mylifcc

        @mylifcc · x.com

    You might also like

    Repositories close to Tencent/WeVisOne-VL
    FeaturedAdvertise to 180K+ monthly visitors
    Bifrost

    Fastest Enterprise AI Gateway for Routing, Governing, and Securing all your AI Traffic

    songtianhui/SimpleSeg

    Python

    Towards Pixel-Level VLM Perception via Simple Points Prediction

    1074

    IDEA-Research/Rex-Omni

    Jupyter Notebook

    [CVPR2026] Detect Anything via Next Point Prediction

    1.6k118

    better-chao/perceptual_abilities_evaluation

    Python

    Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation

    1343

    SeerRay-Lab/Xiaomi-Lens-0

    Python

    [Technical Report] Locate, Segment, and Reason.

    1037

    WongKinYiu/GeneralistYOLO

    Python

    Generalist YOLO: Towards Real-Time End-to-End Multi-Task Visual Language Models

    966

    deepseek-ai/DeepSeek-VL

    Python

    DeepSeek-VL: Towards Real-World Vision-Language Understanding

    4.2k614

    NVlabs/Eagle

    Python

    Eagle: Frontier Vision-Language Models with Data-Centric Strategies

    3.8k384

    OpenSenseNova/SenseNova-Vision

    Python

    Vision as Unified Multimodal Generation

    72744

    facebookresearch/sam3

    Python

    The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

    12.2k1.9k