See the information about the two models below:
Author: Philip Hofmann
License: CC BY 4.0
Release Date: 11.01.2024 (dd/mm/yy)
Trained with musl's [neosr](https://github.com/muslll/neosr), kim's [Datasetdestroyer](https://github.com/Kim2091/helpful-scripts/tree/main/Dataset%20Destroyer), and the Real-ESRGAN pipeline.

---

Name: 2xNomosUni_compact_multijpg_ldl
Author: Philip Hofmann
Release Date: 11.01.2024 (dd/mm/yy)
License: CC BY 4.0
Network: SRVGGNetCompact
Scale: 2
Purpose: 2x fast universal DoF preserving upscaler
Iterations: 218'000
epoch: 168
batch_size: 12
HR_size: 128
Dataset: nomosuni
Number of train images: 2989
OTF Training: No
Pretrained_Model_G: 2x-Compact-Pretrain

Description:
2x compact fast universal DoF preserving upscaler, pair trained with jpg degradation (down to 40) and multiscale (down_up, bicubic, bilinear, box, nearest, lanczos).

Examples:
[ani](https://slow.pics/c/Zd7UCmLP)  
[face](https://slow.pics/c/wKiu7Orf) 
[dofwheat](https://imgsli.com/MjMyNTU4)

---

Name: 2xNomosUni_compact_otf_medium
Author: Philip Hofmann
Release Date: 11.01.2024 (dd/mm/yy)
License: CC BY 4.0
Network: SRVGGNetCompact
Scale: 2
Purpose: 2x fast universal upscaler with medium degradation handling (jpg compression, noise, blur)
Iterations: 276'000
epoch: 218
batch_size: 12
HR_size: 128
Dataset: nomosuni
Number of train images: 2989
OTF Training: Yes
Pretrained_Model_G: 2xNomosUni_compact_otf_strong

Description:
2x compact fast universal upscaler with medium degradation handling using the Real-ESRGAN training pipeline, based off 2xNomosUni_compact_otf_strong. Handles jpg compression, some noise, and some blur (so dejpgs, denoises and deblurs).

Examples:
[RealPhoto](https://imgsli.com/MjMyNTUy)
[Noisy](https://imgsli.com/MjMyNTUz)