---
title: WeVisOne-VL-4B
emoji: 🎯
colorFrom: pink
colorTo: red
sdk: gradio
sdk_version: 6.30.0
app_file: app.py
python_version: "3.12"
short_description: Detect, ground, count, OCR, segment & matte with one VLM
startup_duration_timeout: 1h
models:
  - tencent/WeVisOne-VL-4B
---

Gradio demo for [tencent/WeVisOne-VL-4B](https://huggingface.co/tencent/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`.