UniFace

A lightweight, production-ready face analysis library built on ONNX Runtime

ONNX-optimized RetinaFace, SCRFD, and YOLOv5-Face models with 5-point landmarks.

AdaFace, ArcFace, MobileFace, and SphereFace embeddings for identity verification.

Accurate 106-point facial landmark localization for detailed face analysis.

Age, gender, race (FairFace), and emotion detection from faces.

BiSeNet semantic segmentation with 19 facial component classes.

Real-time gaze direction prediction with MobileGaze models.

Face liveness detection with MiniFASNet to prevent fraud.

Face anonymization with 5 blur methods for privacy protection.

Installation

StandardGPU (CUDA)From Source

pip install uniface

pip install uniface[gpu]

git clone https://github.com/yakhyo/uniface.git
cd uniface
pip install -e .

Get up and running in 5 minutes with common use cases.

Step-by-step examples for common workflows.

Explore individual modules and their APIs.

Learn about the architecture and design principles.

UniFace is released under the MIT License.