laverne01
laverne01
> 见我PR I’m also facing an issue with excessive UMAT codes; there are too many of them in the enabled module. How can I resolve this problem? I would appreciate...
@RobbWatershed Thank you, this helps me a lot!
Calling the function directly makes the code look better. I will try it out and will message back if I have a solution. Thank you.
Thank you! I was able to directly call the function with JNI without using the CLI. The next thing I’m working on is using GFPGAN or Codeformer for face enhancement...
Thank you so much! Where can I check for any new updates if they become available?
I've implemented RealESGAN on Android, and it works quite well. You can try implementing it similarly with the waifu2x model from here: https://github.com/ArchieMeng/ncnn-android-waifu2x-demo. As for CodeFormer, things seem to be...
> RealESGAN RealESGAN is used for image upscaling. If you want to restore faces, use CodeFormer or GFPGAN.