🚀Please support my work by donating!! It ensures I have more time to work on models and future releases
This model has been in the works for a very very very long time. I spent years creating my own private dataset just to train this model. It can handle realistic images, anime, cartoons, and quite a bit more without much hassle. It also works amazingly on illustrations and artwork. This is easily the best model I've ever trained.
I hope you all like it. And please consider donating! I'm going through a rough time right now & any support helps a LOT
Description
FAQ
Comments (6)
no pth version or light version ?
Yeah it's not letting me upload more than 1 file to this page for some reason. I had no problems doing this for my other models
You can get the other versions of the model here though:
https://ko-fi.com/s/4b3245cfe5
Or here:
I was finally able to change the upload type and upload a zip with the 2 model types and .pth versions
Hi! What's the difference between these? :)
4x-UltraSharpV2.safetensors 140 MB
4x-UltraSharpV2_Lite.safetensors 29.6 MB
4x-AnimeSharp.safetensors 33.5 MB
@Salciano Hi!
UltraSharpV2 (not Lite) is based on the DAT2 architecture. It's on the heavier side and takes more time and resources to run, but has the best results
The Lite model is based on RealPLKSR. It's faster and lighter to run, but the results are worse than the full model.
AnimeSharp is an unrelated model that focuses on restoring anime. AnimeSharpV4 is a lot better than V1, so if you want to try it then use that one instead.
Thanks! I'll give it a go :)