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].
272 Jan 3, 2023
248 Jan 6, 2023
20 Dec 6, 2022
6 Dec 14, 2022
21 Dec 22, 2022
2.4k Dec 30, 2022
70 Jan 4, 2023
26 Dec 5, 2022
16 Oct 24, 2022
75 Dec 16, 2022
2.4k Jan 4, 2023
22 Nov 16, 2022