![Thumbnail](/thumbs/small/e6d8e675b7b958278fecb73b.jpg)
4xNomosUniDAT_bokeh_jpg
by Helaman
4x Multipurpose DAT upscaler
Trained on DAT with Adan, U-Net SN, huber pixel loss, huber perceptial loss, vanilla gan loss, huber ldl loss and huber focal-frequency loss, on paired nomos_uni (universal dataset containing photographs, anime, text, maps, music sheets, paintings ..) with added jpg compression 40-100 and down_up, bicubic, bilinear, box, nearest and lanczos scales. No blur degradation had been introduced in the training dataset to keep the model from trying to sharpen blurry backgrounds.
The three strengths of this model (design purpose):
- Multipurpose
- Handles bokeh effect
- Handles jpg compression
This model will not:
- Denoise
- Deblur
Architecture | DAT |
---|---|
Scale | 4x |
Color Mode | |
License | CC-BY-4.0 Private use Commercial use Distribution Modifications Credit required State Changes No Liability & Warranty |
Date | 2023-09-14 |
Dataset | nomos_uni |
Dataset size | 2989 |
Training iterations | 185000 |
Training epochs | 9 |
Training batch size | 4 |
Training HR size | 128 |