Fanghua-Yu/SUPIR
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
SUPIR helps photographers, graphic designers, and marketers transform low-quality, blurry, or pixelated images into photo-realistic, high-resolution versions. You provide a degraded image, and SUPIR generates a much clearer, more detailed, and visually appealing output. This is ideal for anyone needing to enhance image quality for print, web, or promotional materials.
5,476 stars. No commits in the last 6 months.
Use this if you need to dramatically improve the quality of degraded photographs, scale them up for larger displays, or generate highly detailed, realistic images from lower-quality inputs.
Not ideal if you're looking for simple, quick adjustments to already good-quality photos or if you require extreme precision to the original image's imperfections.
Stars
5,476
Forks
470
Language
Python
License
—
Category
Last pushed
May 12, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Fanghua-Yu/SUPIR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
Maclory/SPSR
Pytorch implementation of Structure-Preserving Super Resolution with Gradient Guidance (CVPR...
The-Harsh-Vardhan/HNDSR
A hybrid Neural Operator-Diffusion model for continuous-scale satellite image super-resolution....
lusinlu/gradient-variance-loss
Code of the ICASSP 2022 paper "Gradient Variance Loss for Structure Enhanced Super-Resolution"