v4.0.3

chenglou/pretextv4.0.3Aug 23, 2026by github-actions[bot]

AI Summary

Adds image-level tagging capabilities and improves annotation precision, chatbot provider switching, and overlapping mask exports.

Key Highlights

Added comprehensive image-level tag management including creation, editing, reordering, batch deletion, and copy-all.
Enhanced annotation precision with refined canvas selection and keyboard movement.
Fixed chatbot provider switching by restoring editable custom model names.
Resolved overlapping mask exports to honor label priority and shape layer order.

New Features

Image-level tag creation, editing, reordering, batch deletion, copy-all, and auto-labeling support.

Full Release Notes

> PyPI: https://pypi.org/project/x-anylabeling-cvhub/

> [!NOTE]
> Due to compatibility issues across different systems, if the precompiled version doesn’t 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.

X-AnyLabeling 4.0.3 adds image-level tagging and improves annotation precision, chatbot provider switching, and overlapping mask exports.

### 🚀 New Features

- Add image-level tag creation, editing, reordering, batch deletion, copy-all, and auto-labeling support. (#1320)

### 🐛 Bug Fixes

- Refine canvas selection and keyboard movement for precise annotation adjustments, and restore shape fill after transforms. (#1429)
- Restore editable custom model names when switching chatbot providers. (#1430)
- Honor label priority and shape layer order when exporting overlapping segmentation masks. (#1431)

### 🛠️ Improvements

- Refresh the interface preview in the English and Chinese README files.

### 🌟 Contributors

A total of 2 developers contributed to this release.

Thank @zhixuwei, @CVHub520

**Full Changelog**: https://github.com/CVHub520/X-AnyLabeling/compare/v4.0.2...v4.0.3