yangxy/GPEN

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

2612 stars · 452 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

GPEN (GAN Prior Embedded Network) is a deep learning library for blind face restoration of low-quality, in-the-wild photos. It also supports face colorization, face inpainting, super-resolution, and segmentation-to-face synthesis.

Use cases

• restore blurry old photos of faces
• enhance low-resolution selfies
• colorize black and white portraits
• inpaint missing regions in face images
• upscale face images 4x
• generate faces from segmentation maps

When to choose

• you need state-of-the-art blind face restoration on real-world degraded photos
• you want high-resolution face enhancement up to 1024/2048
• you need face colorization or inpainting alongside restoration

When to avoid

• you need general non-face image restoration
• you require a permissive license for commercial use (no license is specified)
• you lack a GPU and want fast CPU inference

Facets

library · maturity maintenance

image-processing machine-learning deep-learning computer-vision image-processing deep-learning artificial-intelligence python cross-platform face-restoration gan blind-face-restoration face-inpainting face-colorization image-enhancement super-resolution cvpr2021 gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="yangxy/GPEN")