the-database/traiNNer-redux
Deep learning training framework for image super resolution and restoration.
This project helps you train custom deep learning models to enhance the quality of images and videos. You feed it pairs of low-quality and high-quality images or video frames, and it produces a model capable of 'upscaling' or restoring new, unseen low-quality content. This is for AI researchers, hobbyists, or media professionals who want to develop specialized image or video enhancement tools.
106 stars.
Use this if you need to create a bespoke AI model for improving image or video resolution and clarity for specific types of content.
Not ideal if you're looking for an out-of-the-box solution to enhance images; this tool requires you to train your own models.
Stars
106
Forks
21
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/the-database/traiNNer-redux"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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...
eugenesiow/super-image
Image super resolution models for PyTorch.
movehand/raisr
A Python implementation of RAISR
jiny2001/dcscn-super-resolution
A tensorflow implementation of "Fast and Accurate Image Super Resolution by Deep CNN with Skip...