Name: 4xNomosUniDAT_bokeh_jpg
Author: Philip Hofmann
Release: 14.09.2023
License: CC BY 4.0
Network: DAT
Scale: 4
Purpose: 4x multipurpose upscaler (bokeh effect with jpg compression)
Iterations: 185000
epoch: 9
batch_size: 4
HR_size: 128
Dataset: nomos_uni
Number of train images: 2989
OTF Training: No
Pretrained_Model_G: DAT_x4
Description:
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
