Real-ESRGAN ncnn Vulkan
This project is the ncnn implementation of Real-ESRGAN. Real-ESRGAN ncnn Vulkan heavily borrows from realsr-ncnn-vulkan. Many thanks to nihui, ncnn and realsr-ncnn-vulkan
Real-ESRGAN aims at developing Practical Algorithms for General Image Restoration. We also optimize it for anime images.
Contents
If Real-ESRGAN is helpful in your photos/projects, please help to
Other recommended projects:
📖
Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data
[Paper] [Project Page] [Demo]
Xintao Wang, Liangbin Xie, Chao Dong, Ying Shan
Tencent ARC Lab; Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences
⏳
TODO List
- Support further cheap arbitrary resize (e.g., bicubic, bilinear) for the model outputs
- Bug: Some PCs will output black images
- Add the guidance for ncnn model conversion
- Support face restoration - GFPGAN
💻
Usages
Example Command
realesrgan-ncnn-vulkan.exe -i input.jpg -o output.png -n realesrgan-x4plus-anime
Full Usages
Usage: realesrgan-ncnn-vulkan.exe -i infile -o outfile [options]...
-h show this help
-v verbose output
-i input-path input image path (jpg/png/webp) or directory
-o output-path output image path (jpg/png/webp) or directory
-s scale upscale ratio (4, default=4)
-t tile-size tile size (>=32/0=auto, default=0) can be 0,0,0 for multi-gpu
-m model-path folder path to pre-trained models(default=models)
-n model-name model name (default=realesrgan-x4plus, can be realesrgan-x4plus | realesrgan-x4plus-anime | realesrnet-x4plus)
-g gpu-id gpu device to use (default=0) can be 0,1,2 for multi-gpu
-j load:proc:save thread count for load/proc/save (default=1:2:2) can be 1:2,2,2:2 for multi-gpu
-x enable tta mode
-f format output image format (jpg/png/webp, default=ext/png)
input-pathandoutput-pathaccept either file path or directory pathscale= scale level, 4 = upscale 4xtile-size= tile size, use smaller value to reduce GPU memory usage, default selects automaticallyload:proc:save= thread count for the three stages (image decoding + model upscaling + image encoding), using larger values may increase GPU usage and consume more GPU memory. You can tune this configuration with "4:4:4" for many small-size images, and "2:2:2" for large-size images. The default setting usually works fine for most situations. If you find that your GPU is hungry, try increasing thread count to achieve faster processing.format= the format of the image to be output, png is better supported, however webp generally yields smaller file sizes, both are losslessly encoded
If you encounter crash or error, try to upgrade your GPU driver
- Intel: https://downloadcenter.intel.com/product/80939/Graphics-Drivers
- AMD: https://www.amd.com/en/support
- NVIDIA: https://www.nvidia.com/Download/index.aspx
🌏
Other Open-Source Code Used
- https://github.com/Tencent/ncnn for fast neural network inference on ALL PLATFORMS
- https://github.com/webmproject/libwebp for encoding and decoding Webp images on ALL PLATFORMS
- https://github.com/nothings/stb for decoding and encoding image on Linux / MacOS
- https://github.com/tronkko/dirent for listing files in directory on Windows
📜
BibTeX
@InProceedings{wang2021realesrgan,
author = {Xintao Wang and Liangbin Xie and Chao Dong and Ying Shan},
title = {Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data},
booktitle = {International Conference on Computer Vision Workshops (ICCVW)},
date = {2021}
}
📧
Contact
If you have any question, please email [email protected] or [email protected].
31 Nov 06, 2022
1 Nov 12, 2021
251 Dec 08, 2022
15 May 23, 2022
3 Mar 30, 2022
5 Oct 30, 2022
50 Oct 08, 2021
3.3k Jan 05, 2023
366 Dec 28, 2022
65 Dec 07, 2022
8 Dec 19, 2022
96 Jan 06, 2023
52 Jan 09, 2023
1.4k Jan 08, 2023
32 Nov 22, 2022
253 Sep 14, 2022
75 Dec 30, 2022
230 Jan 05, 2023
7 Oct 30, 2022
41 Oct 10, 2022