waifu2x ncnn Vulkan

ncnn implementation of waifu2x converter. Runs fast on Intel / AMD / Nvidia / Apple-Silicon with Vulkan API.

waifu2x-ncnn-vulkan uses ncnn project as the universal neural network inference framework.

Download

Download Windows/Linux/MacOS Executable for Intel/AMD/Nvidia GPU

https://github.com/nihui/waifu2x-ncnn-vulkan/releases

This package includes all the binaries and models required. It is portable, so no CUDA or Caffe runtime environment is needed :)

Usages

Example Command

waifu2x-ncnn-vulkan.exe -i input.jpg -o output.png -n 2 -s 2

Full Usages

Usage: waifu2x-ncnn-vulkan -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
  -n noise-level       denoise level (-1/0/1/2/3, default=0)
  -s scale             upscale ratio (1/2/4/8/16/32, default=2)
  -t tile-size         tile size (>=32/0=auto, default=0) can be 0,0,0 for multi-gpu
  -m model-path        waifu2x model path (default=models-cunet)
  -g gpu-id            gpu device to use (-1=cpu, default=auto) 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-path and output-path accept either file path or directory path
• noise-level = noise level, large value means strong denoise effect, -1 = no effect
• scale = scale level, 1 = no scaling, 2 = upscale 2x
• tile-size = tile size, use smaller value to reduce GPU memory usage, default selects automatically
• load:proc:save = thread count for the three stages (image decoding + waifu2x 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 a crash or error, try upgrading 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

Build from Source

1. Download and setup the Vulkan SDK from https://vulkan.lunarg.com/

• For Linux distributions, you can either get the essential build requirements from package manager

dnf install vulkan-headers vulkan-loader-devel

apt-get install libvulkan-dev

pacman -S vulkan-headers vulkan-icd-loader

2. Clone this project with all submodules

git clone https://github.com/nihui/waifu2x-ncnn-vulkan.git
cd waifu2x-ncnn-vulkan
git submodule update --init --recursive

3. Build with CMake

• You can pass -DUSE_STATIC_MOLTENVK=ON option to avoid linking the vulkan loader library on MacOS

mkdir build
cd build
cmake ../src
cmake --build . -j 4

Speed Comparison with waifu2x-caffe-cui

Environment

• Windows 10 1809
• AMD R7-1700
• Nvidia GTX-1070
• Nvidia driver 419.67
• CUDA 10.1.105
• cuDNN 10.1

Measure-Command { waifu2x-ncnn-vulkan.exe -i input.png -o output.png -n 2 -s 2 -t [block size] -m [model dir] }

Measure-Command { waifu2x-caffe-cui.exe -t 0 --gpu 0 -b 1 -c [block size] -p cudnn --model_dir [model dir] -s 2 -n 2 -m noise_scale -i input.png -o output.png }

cunet

upconv_7_anime_style_art_rgb

Sample Images

Original Image

Upscale 2x with ImageMagick

convert origin.jpg -resize 200% output.png

Upscale 2x with ImageMagick Lanczo4 Filter

convert origin.jpg -filter Lanczos -resize 200% output.png

Upscale 2x with waifu2x noise=2 scale=2

waifu2x-ncnn-vulkan.exe -i origin.jpg -o output.png -n 2 -s 2

Original waifu2x Project

• https://github.com/nagadomi/waifu2x
• https://github.com/lltcggie/waifu2x-caffe

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