# pixpark/gpupixel

Real-time image filter engine based on GPU

Repository: https://github.com/pixpark/gpupixel
Canonical: https://ross.abutalabs.com/products/gpupixel
Homepage: https://gpupixel.pixpark.net/
Language: C++
License: Apache-2.0
License Family: permissive
Topics: beautyface, filter, gpu, android, ios, thinface, gpuimage, image, opengl, video, face-detection, landmarks, ai, webrtc
Last push: 2026-08-26T03:16:10+00:00

## Health v2 (maintenance only)
Score: 88/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 67, longevity 100
- inputs: {"age_days": 1527, "days_push": 7, "days_rel": 222, "gap_med": 18, "n_releases_24m": 8}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2371, forks 341 (observed 2026-08-28T04:06:41.805073+00:00)

## What it is
GPUPixel is a high-performance, cross-platform real-time image and video filter library written in C++11 and built on OpenGL/ES. It provides built-in beauty filters (whitening, smoothing, face thinning) with face landmark detection and supports chaining filters for complex effects on iOS, Android, Mac, Windows, and Linux.

## Use cases
- apply real-time beauty filters to live video streams
- smooth skin and whiten face in a camera app
- add face thinning effects to a WebRTC video call
- process YUV video frames with GPU filters
- build a live streaming app with face beautification
- chain multiple image filters for real-time video effects

## When to choose
- you need real-time GPU-accelerated image or video filtering on mobile or desktop
- you want built-in beauty effects like smoothing, whitening, and face reshaping
- you need a lightweight C++ library compatible with any OpenGL/ES platform
- you are building live streaming or video calling apps with beautification

## When to avoid
- you need offline batch image editing rather than real-time processing
- your platform lacks OpenGL/ES support
- you need general-purpose image editing features beyond filters and face effects
- you prefer a high-level SDK with managed services over a C++ library

## Facets
- artifact type: library
- maturity: active
- function: image-processing, computer-vision, video-processing, graphics
- domain: image-processing, computer-vision, cross-platform, mobile-development
- platform: windows, cpp
- tags: beauty-filter, face-landmarks, gpu-accelerated, opengl-es, live-streaming, webrtc, face-thinning, skin-smoothing, video, ios, android, macos, linux, gpu

## Member repositories
- pixpark/gpupixel (main) score 88

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:41.805073+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 2026-08-30T02:35:23.020249+00:00, confidence not recorded.
  - readme: https://github.com/pixpark/gpupixel (fetched 2026-08-28T04:06:41.805073+00:00, sha 32377b2d1d25)
  - homepage: https://gpupixel.pixpark.net/ (fetched 2026-08-29T10:16:11.876095+00:00, sha 8ee1177bfd55)
  - site_page: https://gpupixel.pixpark.net/about/contact (fetched 2026-08-29T10:16:11.878581+00:00, sha 29137217329d)
- Data as of 2026-08-30T08:39:29.467469+00:00.