v3.3.6
CVHub520/X-AnyLabelingv3.3.6Jan 23, 2026by CVHub520
AI Summary
This is a major feature release adding the Rex-Omni unified vision model, YOLO26 object detection, configurable working directory, and persistent remote server settings.
Key Highlights
- Added Rex-Omni unified vision model support
- Added YOLO26 object detection model
- Added option to export existing model or retrain when model detected in project directory
- Added '--work-dir' parameter for configurable working directory
- Persisted remote server settings in user config
New Features
- Add Rex-Omni unified vision model support
- Add YOLO26 object detection model
- Add option to export existing model or retrain when model detected in project directory
- Add '--work-dir' parameter for configurable working directory
- Persist remote server settings in user config
- Streamline argument handling for multiprocessing support in PyInstaller builds
Full Release Notes
<img width="2366" height="1192" alt="image" src="https://github.com/user-attachments/assets/21c6b36b-30f8-4a09-bf52-00b7cab2c54b" /> <p align="center"> Video Demo: <a href="https://youtu.be/wUTFtcFhfoY">Youtube</a> & <a href="https://www.bilibili.com/video/BV15sz7BqETx">Bilibili</a> </p> > PyPI: https://pypi.org/project/x-anylabeling-cvhub/ > Baidu Cloud: https://pan.baidu.com/s/1pgaw02inCvbEgOme9ajDJA?pwd=e528 > [!NOTE] > Due to compatibility issues across different systems, if the precompiled version doesnβt work properly on your machine, you can try building and running it from source instead. For details, check out the official installation guide and user documentation. ### π New Features - Add Rex-Omni unified vision model support (#1223) - Add YOLO26 object detection model (#1226) - Add option to export existing model or retrain when a model is detected in the project directory (#1226) - Add '--work-dir' parameter for configurable working directory (#1226) - Persist remote server settings in user config (#1267) - Streamline argument handling for multiprocessing support in PyInstaller builds (#1180) ### π Bug Fixes - Fix the problem with the display of the title progress ### π οΈ Improvements - Add FAQ entry for YOLO-Pose keypoint ID issue (#1270) - Update installation guides ### π Contributors A total of 2 developers contributed to this release. Thank @zhixuwei, @CVHub520 **Full Changelog**: https://github.com/CVHub520/X-AnyLabeling/compare/v3.3.5...v3.3.6