X-AnyLabeling

<div align="center">
  <p>
    <a href="https://github.com/CVHub520/X-AnyLabeling/" target="_blank">
      <img alt="X-AnyLabeling" height="200px" src="anylabeling/resources/images/logo.png"></a>
  </p>

[English](README.md) | [简体中文](README_zh-CN.md)

</div>

<p align="center">
    <a href="./LICENSE"><img src="https://img.shields.io/badge/License-GPL%20v3-blue.svg"></a>
    <a href="https://github.com/CVHub520/X-AnyLabeling/releases/latest"><img src="https://img.shields.io/github/v/release/CVHub520/X-AnyLabeling?color=ffa"></a>
    <a href="https://pypi.org/project/x-anylabeling-cvhub/"><img src="https://img.shields.io/pypi/v/x-anylabeling-cvhub?logo=pypi&logoColor=white"></a>
    <a href="./pyproject.toml"><img src="https://img.shields.io/badge/python-3.11+-aff.svg"></a>
    <a href="https://github.com/CVHub520/X-AnyLabeling/releases/latest"><img src="https://img.shields.io/badge/os-linux%2C%20win%2C%20mac-pink.svg"></a>
    <a href="https://github.com/CVHub520/X-AnyLabeling/releases"><img src="https://img.shields.io/github/downloads/CVHub520/X-AnyLabeling/total?label=downloads"></a>
    <a href="https://modelscope.cn/collections/X-AnyLabeling-7b0e1798bcda43"><img src="https://img.shields.io/badge/modelscope-X--AnyLabeling-6750FF?link=https%3A%2F%2Fmodelscope.cn%2Fcollections%2FX-AnyLabeling-7b0e1798bcda43"></a>
</p>

<img src="assets/resources/interface.webp" alt="X-AnyLabeling interface" width="100%" />

<p align="center">
  <a href="https://xanylabeling.com/docs/x-anylabeling/point_cloud" target="_blank"><img src="assets/resources/pointcloud/pointcloud-3d-det.png" alt="3D Point Cloud Detection" width="50%" /></a><a href="https://xanylabeling.com/docs/x-anylabeling/point_cloud" target="_blank"><img src="assets/resources/pointcloud/pointcloud-3d-seg.png" alt="3D Point Cloud Segmentation" width="50%" /></a>
<br />
  <img src="assets/resources/pointcloud/pointcloud-captions-en.svg" alt="Left: 3D Point Cloud Detection; right: 3D Point Cloud Segmentation" width="100%" />
</p>

## 🥳 What's New

- `2026-11-04`: Add support for [SAM 3.1 Video](./examples/interactive_video_object_segmentation/sam3/README.md) with text-prompted multi-object tracking and interactive point segmentation.
- `2026-11-03`: Add an adjustable image grid with optional cell labels for inspecting annotations.
- `2026-11-01`: Add support for the [RelateAnything](./examples/relation/relateanything/README.md) object relation prediction model.
- `2026-10-31`: Add object-level multi-task attribute annotation with AI-assisted labeling and concurrent inference.
- `2026-10-30`: Add support for the [Unlimited-OCR-2](./examples/document_parsing/unlimited_ocr_2/README.md) model with image and PDF document parsing with multi-page context.
- `2026-10-28`: Add support for the [WeVisOne-VL](./examples/vision_foundation/wevisone_vl/README.md) model with detection, referring localization, pointing, counting, OCR, text grounding, segmentation, text and box matting, visual prompting, and freeform i