---
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/4xNomosWebPhoto_RealPLKSR)

# 4xNomosWebPhoto_RealPLKSR  

Scale: 4  
Architecture: [RealPLKSR](https://github.com/muslll/neosr/blob/c8720232448eb059567ae820e3d461d66a4aef1c/neosr/archs/realplksr_arch.py)  
Architecture Option: realplksr  

Author: Philip Hofmann  
License: CC-BY-0.4  
Purpose: Restoration  
Subject: Photography  
Input Type: Images  
Release Date: 28.05.2024  

Dataset: [Nomos-v2](https://github.com/muslll/neosr?tab=readme-ov-file#-datasets)  
Dataset Size: 6000  
OTF (on the fly augmentations): No  
Pretrained Model: 4x_realplksr_gan_pretrain  
Iterations: 404'000, 445'000  
Batch Size: 12, 4  
GT Size: 128, 256, 512  

Description:  

short: 4x RealPLKSR model for photography, trained with realistic noise, lens blur, jpg and webp re-compression.  

full: My newest version of my RealWebPhoto series, this time I used the newly released [Nomos-v2](https://github.com/muslll/neosr?tab=readme-ov-file#-datasets) dataset by musl.   
I then made 12 different low resolution degraded folders, using [kim's datasetdestroyer](https://github.com/Kim2091/helpful-scripts/tree/main/Dataset%20Destroyer) for scaling and compression, my [ludvae200 model](https://github.com/Phhofm/models/releases/tag/Ludvae200) for realistic noise, and [umzi's wtp_dataset_destroyer](https://github.com/umzi2/wtp_dataset_destroyer/tree/master?tab=readme-ov-file) with its floating point lens blur implementation for better control (since i needed to control the lens blur strength more precisely).   
I then mixed them together in a single lr folder and trained for 460'000 iters, checked the results, and upon kims suggestion of using interpolation, I tested and am releasing this interpolation between the checkpoints 404'000 and 445'000.  

This model has been trained on [neosr](https://github.com/muslll/neosr) using mixup, cutmix, resizemix, cutblur, nadam, unet, multisteplr, mssim, perceptual, gan, dists, ldl, ff, color and lumaloss, and interpolated using the current [chaiNNer](https://github.com/chaiNNer-org/chaiNNer) nightly version.  

This model took multiple retrainings and reworks of the dataset, until I am now satisfied enough with the quality to release this version.   

For more details on the whole process see the [pdf file](https://huggingface.co/Phips/4xNomosWebPhoto_RealPLKSR/blob/main/4xNomosWebPhoto-4.pdf) in the attachement.  

I am also attaching the 404'000, 445'000 and 460'000 checkpoints for completeness.  

PS in general degradation strengths have been reduced/adjusted in comparison to my previous RealWebPhoto models  

Showcase:  
[Slow Pics 10 Examples](https://slow.pics/s/euvEv4hL)  

![Example1](https://github.com/Phhofm/models/assets/14755670/ebbb01d3-c0c7-427d-ba8b-a77797255f59)
![Example2](https://github.com/Phhofm/models/assets/14755670/763be319-fd46-4ca8-a4c2-e71e66b7cbc7)
![Example3](https://github.com/Phhofm/models/assets/14755670/e713fde1-d5d2-4355-905f-9756482b5e6c)
![Example4](https://github.com/Phhofm/models/assets/14755670/624e054a-913a-431c-97a5-8406c5602151)
![Example5](https://github.com/Phhofm/models/assets/14755670/42196634-c486-4b2b-adce-340f36af87fe)
![Example6](https://github.com/Phhofm/models/assets/14755670/f260014a-2276-4c09-a7af-b18b4142d7ae)
![Example7](https://github.com/Phhofm/models/assets/14755670/d7d94828-7cdd-4e9d-9de3-497820899372)
![Example8](https://github.com/Phhofm/models/assets/14755670/fc18229d-54c0-49d6-83e2-3558c8e4236b)
![Example9](https://github.com/Phhofm/models/assets/14755670/ccc880c7-8923-4995-b8df-41de6556ce35)
![Example10](https://github.com/Phhofm/models/assets/14755670/d395936d-0c30-4166-9566-f014e5a2fda8)