4xNomos2_realplksr_dysample
Good for
4xNomos2_realplksr_dysample
Scale: 4
Architecture: RealPLKSR with Dysample
Architecture Option: realplksr
Github Release
Author: Philip Hofmann
License: CC-BY-0.4
Purpose: Pretrained
Subject: Photography
Input Type: Images
Release Date: 30.06.2024
Dataset: nomosv2
Dataset Size: 6000
OTF (on the fly augmentations): No
Pretrained Model: 4xmssim_realplksr_dysample_pretrain
Iterations: 185'000
Batch Size: 8
GT Size: 256, 512
Description:
A Dysample RealPLKSR 4x upscaling model that was trained with / handles jpg compression down to 70 on the Nomosv2 dataset, preserves DoF.
Based on the 4xmssim_realplksr_dysample_pretrain I released 3 days ago.
This model affects / saturate colors, which can be counteracted a bit by using wavelet color fix, as used in these examples.
Showcase: Slowpics
Training details (7)
- Date
- 2024-06-30
- Dataset
- Nomos-v2
- Dataset size
- 6000
- Training iterations
- 185000
- Training batch size
- 8
- Training HR size
- 512
- Training OTF
- No