AIJupyter Notebook★ 1,189⑂ 100 forks
Tencent/WeVisOne-VL
Unified Visual Perception VLM
WeVisOne-VL unifies object-level and pixel-level visual perception, handling points, boxes, masks, and alpha mattes in a single vision-language model.
// KEY FEATURES
- Unifies object detection, segmentation, and matting in one model
- Supports point, box, mask, and alpha matte inputs and outputs
- Built by Tencent's WeChat Vision Team for advanced VL tasks
New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram