---
title: WeVisOne-VL-4B
canonical_url: "https://www.modelscope.ai/studios/AI-ModelScope/WeVisOne-VL-4B"
md_url: "https://www.modelscope.ai/studios/AI-ModelScope/WeVisOne-VL-4B.md"
repository: AI-ModelScope/WeVisOne-VL-4B
chinese_name: WeVisOne-VL-4B
last_updated: 2026-10-30
sdk_type: gradio
sdk_version: 6.29.1
downloads: 0
stars: 0
---

# WeVisOne-VL-4B

> WeVisOne-VL-4B - An interactive demo by AI-ModelScope on ModelScope. Tencent WeChat Vision unified perception: grounding, detection, counting, pointing, OCR, VQA, segmentation and alpha matting.

AI-ModelScope/WeVisOne-VL-4B is an interactive demo (Studio) on ModelScope. built with gradio 6.29.1.

- **Repository**: AI-ModelScope/WeVisOne-VL-4B
- **SDK**: gradio
- **SDK version**: 6.29.1
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-10-30

Source: https://www.modelscope.ai/studios/AI-ModelScope/WeVisOne-VL-4B

---

Gradio demo for [tencent-community/WeVisOne-VL-4B](https://modelscope.ai/models/tencent-community/WeVisOne-VL-4B), a unified
visual perception model (grounding, dense detection, counting, pointing, OCR, grounded captioning,
segmentation and alpha matting).

Inference code (`wevisone_vl/`) and rendering helpers (`wv_render.py`) are adapted from the official
[Tencent/WeVisOne-VL](https://github.com/Tencent/WeVisOne-VL) repository (Apache-2.0); the example
images come from that repository's `demo/examples/images`.