search

chaiNNer-org / spandrel

Spandrel gives your project support for various PyTorch architectures meant for AI Super-Resolution, restoration, and inpainting. Based on the model support implemented in chaiNNer.
MIT License
103 stars 7 forks source link

UpCunet2x_Fast support for ShuffleCugan #182

Closed NevermindNilas closed 4 months ago

NevermindNilas commented 4 months ago

Hi, I was reading through the code and failed to see any mentions of shufflecugan, are there any plans to support sudo's shufflecugan model based on UpCunet2x_Fast?

https://openmodeldb.info/models/2x-sudo-shuffle-cugan-9-584-969

Amazing work so far guys, much appreciated!

RunDevelopment commented 4 months ago

Looks very doable. The architecture itself is very simple and should be easy to detect.

The only issue is that sudo didn't license the code. So we need to ask them for a license before we can add it.

NevermindNilas commented 4 months ago

Awesome, I just asked him to do it. Thank you!

styler00dollar commented 4 months ago

Shuffle Cugan uses UpCunet2x_fast() from bilibili/ailab with pro mode set to false.

RunDevelopment commented 4 months ago

Oh, I didn't even notice that when I added Real-CUGAN. Then it's MIT too. Thanks!