waifu2x-ncnn-vulkan VS ESRGAN

Hi OP, try going in ubuntu then install there. Mine works fine after doing these steps: sudo apt update && upgrade sudo apt install apt-utils sudo apt install python-is-python3 git clone https://github.com/nihui/waifu2x-ncnn-vulkan.git cd waifu2x-ncnn-vulkan git submodule update --init --recursive mkdir build cd build apt install cmake apt install build-essential cmake ../src cmake --build . -j 4 ./waifu2x-ncnn-vulkan Note: i thought its stucked at 100% after cmake --build but just wait maybe 5mins and completed installing to build, all good, and... im no IT/Dev but it worked for me by following the installation guide. Now i can see these ``` Usage: waifu2x-ncnn-vulkan -i infile -o outfile [options]...

why not https://github.com/nihui/waifu2x-ncnn-vulkan ?

The other is using AI upscaling, which will allow you to upscale it while keeping a high quality look. You could try Waifu2x for that.

https://github.com/nihui/waifu2x-ncnn-vulkanis that a legist question? look it for yourself.

This seems to be based on ESRGAN which is supposed to be higher quality than waifu2x.

I downloaded https://github.com/xinntao/ESRGAN , I run it using command line, no gui.

Nerd info: Uses 3 different algorithms together: https://github.com/CompVis/stable-diffusion For generating source https://github.com/TencentARC/GFPGAN For repairing faces, mouths, eyes https://github.com/xinntao/ESRGAN For upscaling Paint.Net for manual retouching, cleanup and adjustments.

Code for https://arxiv.org/abs/1809.00219 found: https://github.com/xinntao/ESRGAN

Even if it's not a simple black and white image, you can get damn impressive results when upscaling images with GAN-based algorithms, like ESRGAN, together with a suitable pretrained model. Both are free of charge. The software can be tricky to use compared to Photoshop, though.

I use ESRGAN: https://github.com/xinntao/ESRGAN

There are two Generator architectures that are in the code, however these are actually just sitting there unused, likely from work that did not pan out because if you look at their inference code it's not used at all. Instead they directly import the plain old vanilla RRDB architecture from BasicSR yet again another Xinntao repository. Seeing the theme here.