UniFace: All-in-One Face Analysis Toolkit for Production
UniFace is a lightweight, production-ready face analysis library built on ONNX Runtime. It provides a unified API for face detection, recognition, landmark detection, attribute analysis, face parsing, gaze estimation, anti-spoofing, and privacy features.
Documentation Moved
The comprehensive documentation for UniFace has been moved to a dedicated documentation site with tutorials, API references, and guides.
Interactive Notebooks
Run examples directly in your browser with Google Colab:
| Notebook | Colab | Description |
|---|---|---|
| Face Detection |  |
Detect faces and 5-point landmarks |
| Face Alignment | |
Align faces for recognition |
| Face Verification | |
Compare faces for identity |
| Face Search | |
Find a person in group photos |
| Face Analyzer | |
All-in-one face analysis |
| Face Parsing | |
Semantic face segmentation |
| Face Anonymization | |
Privacy-preserving blur |
| Gaze Estimation | |
Gaze direction estimation |
Quick Install
pip install uniface
For GPU support:
pip install uniface[gpu]
Resources:
- Documentation: yakhyo.github.io/uniface
- GitHub: github.com/yakhyo/uniface
- PyPI: pypi.org/project/uniface