Many preview images on this site are currently broken due to their original hosts being indefinitely offline. Work is underway to recover the affected images and rehost them somewhere reliable.

Lollypop

4xESRGANby LyonHrt

A universal model, that is aimed at prerendered images, but handles realistic faces, manga, pixel art and dedithering as well. Trained using the patchgan discriminator, with cx loss, cutmixup and frequency separation, it produces good results with a slight grain due to patchgan, with some sharpening using cutmixup.

Training details (8)
Date
2020-09-11
Dataset
prerendered manga images
Dataset size
109564
Training iterations
235000
Training epochs
16
Training batch size
8
Training HR size
128
Training OTF
Yes

Model

Architecture
ESRGAN
Scale
4x
Size
64nf23nb
Color Mode

Rights

CC-BY-NC-SA-4.0
Private use
Distribution
Modifications
Credit required
Same License
State Changes
No Liability & Warranty
Disclaimer

Similar models