onuralpszr/GFPGAN-ncnn-vulkan

[WIP] NCNN with Vulkan implementation of GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration

50
/ 100
Established

This project helps restore clarity and detail to damaged or low-quality face images, such as those from old photos, security cameras, or social media. It takes a blurry or degraded face image and outputs a significantly improved, clearer version. This is ideal for anyone working with historical images, surveillance footage, or digital media that needs high-quality facial representations.

Use this if you need to quickly and efficiently enhance the quality of poor-resolution or damaged face images, especially for real-time applications on devices like smartphones or drones.

Not ideal if your primary goal is to restore general scenes or objects rather than specifically faces, or if you need to colorize black and white photos (as this feature is planned but not yet implemented).

image-restoration digital-archiving surveillance-enhancement media-quality-improvement historical-photo-restoration
No Package No Dependents
Maintenance 10 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

53

Forks

10

Language

C++

License

GPL-3.0

Last pushed

Feb 15, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/onuralpszr/GFPGAN-ncnn-vulkan"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.