4xNomosUni Rgt Multijpg
Name: 4xNomosUnirgtmultijpg License: CC BY 4.0 Author: Philip Hofmann Network: RGT Scale: 4 Release Date: 20.02.2024 Purpose: 4x universal DoF preserving upscaler Iterations: 100'000 epoch: 79 batchsize: 12 HRsize:...
Modellquelle
- Art
- Other
- Dateigröße
- 172 MB
- Version
- v4x Nomos Uni rgt multijpg
- Aktualisiert
- 26. Okt. 2026
- Quelle
- Hugging Face
Quellenbeschreibung
4xNomosUni_rgt_multijpg
Name: 4xNomosUni_rgt_multijpg
License: CC BY 4.0
Author: Philip Hofmann
Network: RGT
Scale: 4
Release Date: 20.02.2024
Purpose: 4x universal DoF preserving upscaler
Iterations: 100'000
epoch: 79
batch_size: 12
HR_size: 128
Dataset: nomosuni
Number of train images: 2989
OTF Training: No
Pretrained_Model_G: RGT_x4
Description:
4x universal DoF preserving upscaler, pair trained with jpg degradation (down to 40) and multiscale (down_up, bicubic, bilinear, box, nearest, lanczos) in neosr with adamw, unet and pixel, perceptual, gan and color losses.
Similiar to the 4xNomosUni_rgt_s_multijpg model I released, with same dataset, this is a full RGT model in comparison.
6 Examples (To check JPG compression handling see Example Nr.4, to check Depth of Field handlin see Example Nr.1 & Nr.6): Slowpics
4xNomosUni_rgt_multijpg
Quellen
1 Quelle
Quellen
1 QuelleVerifiziert 26. Okt.
Modellartefakte
1 Artefakt
Modellartefakte
1 Artefakt4xNomosUni_rgt_multijpg.safetensors
safetensors · 172 MB · SHA-256 10d216adcdea…876c · Hugging Face
Download fileQuellenauszüge
2 Auszüge
Quellenauszüge
2 Auszüge--- license: cc-by-4.0 pipeline_tag: image-to-image tags: - pytorch - super-resolution --- [Link to Github Release](https://github.com/Phhofm/models/releases/tag/4xNomosUni_rgt_multijpg) # 4xNomosUni_rgt_multijpg Name: 4xNomosUni_rgt_multijpg License: CC BY 4.0 Author: Philip Hofmann Network: RGT Scale: 4 Release Date: 20.02.2024 Purpose: 4x universal DoF preserving upscaler Iterations: 100'000 epoch: 79 batch_size: 12 HR_size: 128 Dataset: nomosuni Number of train images: 2989 OTF Training: No Pretrained_Model_G: RGT_x4 Description: 4x universal DoF preserving upscaler, pair trained with jpg degradation (down to 40) and multiscale (down_up, bicubic, bilinear, box, nearest, lanczos) in neosr with adamw, unet and pixel, perceptual, gan and color losses. Similiar to the 4xNomosUni_rgt_s_multijpg model I released, with same dataset, this is a full RGT model in comparison. 6 Examples (To check JPG compression handling see Example Nr.4, to check Depth of Field handlin see Example Nr.1 & Nr.6): [Slowpics](https://slow.pics/s/iMuE3vE5) 
Source context: 0 downloads · 0 likes · Pipeline image-to-image · Repo Phips/4xNomosUni_rgt_multijpg
