Real-ESRGAN VS arXiv2021-RIFE

It's not exactly what you're after, as it's anime specific and you need to process the video yourself (eg disassemble to frames, run the upscaler, then assemble back to a movie file), but Real-ESRGAN is really good:

https://github.com/xinntao/Real-ESRGAN/

It's pretty brilliant for cleaning up very old, low resolution anime.

Just a note you can run upscaling on your home desktop with Real-ESRGAN:

https://github.com/xinntao/Real-ESRGAN

Maybe Real-ESRGAN is a good fit? Even tho it's a couple of years old

I'm glad you noticed! I upscaled the icon from the wiki using Real-ESRGAN's 4xplus anime model, then photoshopped out the text. Worked far better than waifu2x.

A: Try using High-res Fix and R-ESRGAN 4x+ Anime6B as upscaler

Maybe try this one https://github.com/xinntao/Real-ESRGAN it may work even better.

Screenshotted from the official music video, upscaled to 4k using a state of the art ML model.

Do you happen to remember which chapter has that "scene"? You could also try to enhance it yourself, I did it using Real-ESRGAN, which is really easy to use.

RIFE Link - https://github.com/hzwer/arXiv2020-RIFE

Now I see that a new model called RIFE is available: https://github.com/hzwer/arXiv2020-RIFE but I'm not sure of there are any open source frontends for it.

You might be able to clean up your video frames with something like RIFE and/or Real-ESRGAN.

You mean RIFE. Dang swipe/voice dictation!

That is already quickly becoming a thing. There is an AI called RIFE, which is publicly accessible for free (github repo), if you know how to use the terminal/command line, and some python you can get it working fairly easily, and it interpolates video with really good quality and efficiency.

The video was interpolated to 60 fps using RIFE (which explains any artifacts or distortions)