Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
-
Updated
May 24, 2022 - Python
{{ message }}
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
AI无损放大工具
NCNN implementation of Real-ESRGAN. Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration.
An Android application for super-resolution & interpolation. Contains RealSR-NCNN, SRMD-NCNN, RealCUGAN-NCNN, Real-ESRGAN-NCNN, Waifu2x-NCNN, nearest, bilinear, bicubic, AVIR.
PyTorch implementation of Real-ESRGAN model
A Real-ESRGAN model trained on a custom dataset
Efficient ML Filter Runtimes for VapourSynth (with built-in support for waifu2x, DPIR, RealESRGANv2, and Real-CUGAN)
Real-ESRGAN function for VapourSynth
Simple inference codes for Neural Network (AI) models
Augmentations for Neural Networks. Implementation of Torchvision's transforms using OpenCV and additional augmentations for super-resolution, restoration and image to image translation.
PyTorch implements `Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data` paper.
Построено на базе Real-ESRGAN. Улучшает качество изображения аниме в разы
State of the art image upscaling, directly in your browser.
AI-powered Image Resize Tool
Upscale any number of videos using this colab notebook!
Add a description, image, and links to the real-esrgan topic page so that developers can more easily learn about it.
To associate your repository with the real-esrgan topic, visit your repo's landing page and select "manage topics."
The ability to change which augmentation preset is being used at different points in training would be great. For example, at 10k iterations, resrgan_blur could be used, but at 30k it's automatically switched to bsrgan_blur.
This was discussed in the #trainner channel on the GU Discord server
Edit: A possible expansion on this idea, augmentation preset strengths. I'm not sure how it'd functi