I just tried. It’s basically github.com/xinntao/Real-ESRGAN expect OP’s program upscales video, frame by frame, and combines those frames into a new video.
Video looks like it’s made by AI. Tried on old video - not sure if old or new video looking better. Contours in new video are difderent with each frame lol.
OP did a great job, but overall technology is not there yet. Videos aren’t looking good tbh.