neosr-project/neosr
neosr is an open-source framework for training super-resolution models.
This framework helps image professionals, researchers, and enthusiasts improve the quality of their low-resolution images. You provide degraded photos, anime, illustrations, or even medical scans, and it outputs enhanced, higher-resolution versions. This is for anyone needing to restore or upscale images for better clarity or detail.
304 stars. No commits in the last 6 months.
Use this if you need a reliable and efficient way to train custom models to upscale and restore various types of images with state-of-the-art results.
Not ideal if you're looking for a simple 'one-click' image upscaler without any interest in the underlying model training or configuration.
Stars
304
Forks
46
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 02, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/neosr-project/neosr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
HasnainRaz/Fast-SRGAN
A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps
NatLabRockies/sup3r
The Super-Resolution for Renewable Resource Data (sup3r) software uses generative adversarial...
the-database/traiNNer-redux
Deep learning training framework for image super resolution and restoration.
eugenesiow/super-image
Image super resolution models for PyTorch.
movehand/raisr
A Python implementation of RAISR