How to use an anime-optimized super-resolution model
The anime that I casually watch may actually have artifacts.
Refreshing with Real-CUGAN
It removes noise and can super-resolution up to 4 times.
Method
Clone the repository and download the pre-trained weight.
Import and run the model from upcunet_v3.py.
If you zoom in and compare, you can see that it is beautiful.
Also in the video
The repository also has scripts that can be applied to videos.
🐣
I’m a freelance engineer.
Work consultation
Please feel free to contact us with a brief development description.
rockyshikoku@gmail.com
I am making an app that uses Core ML and ARKit.
We send machine learning / AR related information.
