# yakhyo/uniface

UniFace: A Unified Face Analysis Library for Python | Detection, alignment, landmarks, face-mesh, recognition, parsing, gaze, attributes and anti-spoofing under one API.

Repository: https://github.com/yakhyo/uniface
Canonical: https://ross.abutalabs.com/products/uniface
Homepage: https://yakhyo.github.io/uniface/
Language: Python
License: MIT
License Family: permissive
Topics: face-detection, face-recognition, face-analysis, gaze-estimation, face-parsing, face-segmentation, onnxruntime, face-mesh, computer-vision, deep-learning, face-anonymization, face-anti-spoofing, face-attributes, face-quality-assessment, face-tracking, facial-landmarks, head-pose-estimation, portrait-matting, python, face-alignment
Last push: 2026-08-23T14:56:26+00:00

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 98, longevity 46
- inputs: {"age_days": 657, "days_push": 10, "days_rel": 19, "gap_med": 6.0, "n_releases_24m": 33}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1586, forks 212 (observed 2026-08-28T04:05:07.416057+00:00)

## What it is
UniFace is a unified Python library for face analysis that bundles detection, recognition, landmark localization, face parsing, gaze estimation, attribute prediction, tracking, quality assessment, and anti-spoofing behind a single API. It runs inference on ONNX Runtime with automatic acceleration on CPU, Apple Silicon, and NVIDIA CUDA.

## Use cases
- detect and recognize faces in images
- extract face embeddings for identity verification
- estimate age and gender from face photos
- detect face liveness to prevent spoofing attacks
- track faces across video frames with persistent IDs
- estimate gaze direction and head pose
- blur or anonymize faces for privacy
- segment facial components from an image

## When to choose
- you need multiple face analysis tasks under one consistent Python API
- you want production-ready ONNX Runtime inference with CPU and GPU support
- you need face recognition, landmarks, parsing, and anti-spoofing without gluing together several repos

## When to avoid
- you need to train face models from scratch rather than run inference
- you need non-face general object detection or segmentation
- you require a framework other than Python

## Facets
- artifact type: library
- maturity: active
- function: computer-vision, machine-learning, image-processing, sdk
- domain: computer-vision, deep-learning, artificial-intelligence, image-processing
- platform: python, cross-platform, windows
- tags: face-detection, face-recognition, facial-landmarks, face-parsing, gaze-estimation, anti-spoofing, face-tracking, onnxruntime, face-attributes, portrait-matting, head-pose-estimation, face-anonymization, macos, linux, gpu

## Member repositories
- yakhyo/uniface (main) score 88

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:07.416057+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:55:30.621806+00:00, confidence not recorded.
  - readme: https://github.com/yakhyo/uniface (fetched 2026-08-28T04:05:07.416057+00:00, sha ed57991a98fd)
  - homepage: https://yakhyo.github.io/uniface/ (fetched 2026-08-29T11:26:08.623927+00:00, sha de7c38c917a0)
  - registry_pypi: https://pypi.org/pypi/uniface/json (fetched 2026-08-29T11:26:08.634055+00:00, sha 8ea1fc30051c)
- Data as of 2026-08-30T08:39:29.467469+00:00.