No example images yet
This model doesn't have a before/after example. Adding one helps people judge whether it fits their material.
Add an example →Lollypop
Good for
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
Rights
CC-BY-NC-SA-4.0Disclaimer
Private use
Distribution
Modifications
Credit required
Same License
State Changes
No Liability & Warranty