ESRGAN VS realsr-ncnn-vulkan

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.

Compressing the videos has become quite a project that involves the seed_travel script, a little imagemagick, upscaling with realSR, an absolute ton of interpolation with RIFE, and the swiss army knife of video tools, ffmpeg.

I used realsr-ncnn-vulkan if anyone is interested.

Try RealSR, I always get pretty solid results with it and it's very straightforward as long as you're not afraid of programs without a GUI. There are also those "GAN" upscalers but I honestly know basically nothing about them, but I'm sure there is some program with GAN on it's name that can get you similar or better results than TopazAI. ESRGAN maybe?

Executables are here(see releases on right side): https://github.com/nihui/realsr-ncnn-vulkan/releases