Fast waifu2x converter with GPU optimization. Using GLSL.

• Linux with GLEW
• macOS with GLEW
• Windows with GLFW and GLEW

• You can download this program from here.

$ #/usr/bin/ruby -e "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/master/install)"
$ brew install glfw
$ make

# #dnf install mesa-libgbm-devel libdrm-devel mesa-libGL-devel mesa-libGLU-devel mesa-libEGL-devel mesa-libGLES-devel
# dnf install glfw-devel
$ make

1. Installing OpenGL

• nupengl.core with NuGet

2. Linking OpenGL

• Choose ‘Linker-> General’.
• In the ‘Additional Dependencies’ field click on the arrow that appears at the end of the field and choose Edit…
• In the dialog that appears enter “opengl32.lib”

$ ./waifu2x_glsl -h
Usage: ./waifu2x_glsl [options] file

Options:
-h                 Print this message
-m <model name>    waifu2x model name [noise2_model.json...]
-s <scale>         Magnification [1.0, 1.6, 2.0...]
-o <output name>   output file name [*.png, *.jpg]

$ ./waifu2x_glsl -s 1.0 nyanko.jpg
$ ./waifu2x_glsl -m vgg_7/art_y/noise3_model.json nyanko.jpg

• ./waifu2x_glsl -s 2.0 -m noise2_model.json waifu_s.jpg -o waifu_d.png

• https://github.com/yui0/catseye
• Image Super-Resolution Using Deep Convolutional Networks
• EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
• Waifu2x
  • Waifu2x webgl version / GLSL code
  • Original implementation
  • https://github.com/ueshita/waifu2x-converter-glsl
  • https://stanko.github.io/super-resolution-image-resizer
  • https://www.slideshare.net/KosukeNakago/seranet
• GLSL
  • https://github.com/transcranial/keras-js/tree/master/src/webgl
  • https://github.com/scienceai/neocortex/blob/master/src/lib/webgl/matmul_fragment_shader.glsl
  • https://tenso.rs/demos/fast-neural-style/
• Picture
  • Nyanko: https://www.illust-box.jp/member/view/7263/
  • Nyanko: http://www.poipoi.com/yakko/cgi-bin/sb/log/eid5173.html#more-5173
• OpenGL on Mac