BeforeAfter
100%
Scroll to zoom · Drag to pan
SheeepIt!
Good for
Restoring frames from the show "Sheeep"
This model was trained to restore "Sheeep" while retaining and enhancing the noise present in the show. The model amazingly finished training in only 8.8k iterations with no pretrain, with a dataset of only 4 image pairs. This model should work well for animes and cartoons with a lot of grain present. There are some slight haloing issues in dark colors unfortunately, but I was unable to fix it.
Training details (5)
- Date
- 2022-07-21
- Dataset
- Sheeep release frames and production frames from tenpence in Animation Upscale
- Dataset size
- 4
- Training epochs
- 47
- Training HR size
- 96
Model
Rights
CC-BY-NC-SA-4.0Disclaimer
Private use
Distribution
Modifications
Credit required
Same License
State Changes
No Liability & Warranty