---
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/4xArtFaces_realplksr_dysample)  

# 4xArtFaces_realplksr_dysample  
Scale: 4  
Architecture: [RealPLKSR with Dysample](https://github.com/muslll/neosr/?tab=readme-ov-file#supported-archs)  
Architecture Option: [realplksr](https://github.com/muslll/neosr/blob/master/neosr/archs/realplksr_arch.py)  

Author: Philip Hofmann  
License: CC-BY-0.4  
Purpose: Restoration  
Subject: Art  
Input Type: Images  
Release Date: 08.08.2024  

Dataset: [ArtFaces](https://github.com/Phhofm/models/releases/tag/dataset_artfaces)  
Dataset Size: 5'630  
OTF (on the fly augmentations): No  
Pretrained Model: [4xNomos2_realplksr_dysample](https://github.com/Phhofm/models/releases/tag/4xNomos2_realplksr_dysample)  
Iterations: 139'000  
Batch Size: 6  
Patch Size: 64  

Description:  
A Dysample RealPLKSR 4x upscaling model for art / painted faces.   
Based on my [ArtFaces Dataset](https://github.com/Phhofm/models/releases/tag/dataset_artfaces) which is a curated version of the [metfaces dataset](https://github.com/NVlabs/metfaces-dataset) for the purpose of training single image super resolution models.

Showcase:  
![Example1](https://github.com/user-attachments/assets/5901df2c-d9a3-488e-b270-56b41e7ab1f1)
![Example2](https://github.com/user-attachments/assets/0cc97f6a-af0c-416d-adbf-1d61817ff8fe)
![Example3](https://github.com/user-attachments/assets/b9b3bb46-c139-40e2-8dc7-25873b027716)
![Example4](https://github.com/user-attachments/assets/25c623a6-72d5-42c0-af5b-64d0df011b59)
[![Example5](https://github.com/user-attachments/assets/f1f5f177-b5f0-4c6e-8865-b8d4087e2c68)