---
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/2xLexicaRRDBNet)  

# 2xLexicaRRDBNet_Sharp

Name: 2xLexicaRRDBNet_Sharp  
Author: Philip Hofmann  
Release Date: 01.06.2023  
License: CC BY 4.0  
Network: RRDBNet  
Scale: 2  
Purpose: Upscaling AI generated images - a bit sharper then above model  
Iterations: 220'000  
batch_size: 4  
HR_size: 128  
Epoch: 18 (require iter number per epoch: 10964)  
Dataset: lexica-aperture-v3-small  
Number of train images: 43856  
OTF Training: No  
Pretrained_Model_G: None  

Description: Its like the above model, but trained for some more with l1_gt_usm and percep_gt_usm set to true, resulting in sharper outputs. I provide both so they can be chosen based on preferrence of the user.

![Example1](https://github.com/Phhofm/models/assets/14755670/3812501e-ef5a-4d8d-b286-3ac73c1c14ec)
![Example2](https://github.com/Phhofm/models/assets/14755670/c69c7b9a-b31f-4246-8133-d6559f1ab378)
![Example3](https://github.com/Phhofm/models/assets/14755670/5eaafd0d-8829-4cd0-8bc1-0973306f5b95)
![Example4](https://github.com/Phhofm/models/assets/14755670/b128687b-35e5-4505-9a7c-1430de309bf0)
![Example5](https://github.com/Phhofm/models/assets/14755670/47109b66-3a24-47c8-be16-ffd294126d06)
![Example6](https://github.com/Phhofm/models/assets/14755670/d533bb3b-20a4-4b72-8c2a-e3e5dbfbc138)
![Example7](https://github.com/Phhofm/models/assets/14755670/7e9d9384-297b-4b30-9638-91235a1b8a14)
![Example8](https://github.com/Phhofm/models/assets/14755670/58228d65-6222-49ec-8672-59a81110d600)
![Example9](https://github.com/Phhofm/models/assets/14755670/2c18374e-b8e6-4807-a1c7-38db257de189)
![Example10](https://github.com/Phhofm/models/assets/14755670/e7d1be71-404f-4982-babc-c6028d2f54b8)
![Example11](https://github.com/Phhofm/models/assets/14755670/1451bd2f-164c-4e50-83ed-6c06711f82f8)
![Example12](https://github.com/Phhofm/models/assets/14755670/9b49469a-8a5a-4d8d-abd7-92ff3c5e132e)
![Example13](https://github.com/Phhofm/models/assets/14755670/a3651ddb-58be-427a-ad62-5f4523e3eebb)
![Example14](https://github.com/Phhofm/models/assets/14755670/5639e063-1b22-46a8-a2f0-dd502e5285f0)
![Example15](https://github.com/Phhofm/models/assets/14755670/5eabc77c-ec3a-4e0b-9422-6472fb229863)
![Example16](https://github.com/Phhofm/models/assets/14755670/616ce870-48c4-4bb8-9d18-16ba8e25bdb8)