README.md

metadata

license: cc-by-4.0
pipeline_tag: image-to-image
tags:
  - pytorch
  - super-resolution

Link to Github Release

2xLexicaRRDBNet

Name: 2xLexicaRRDBNet
Author: Philip Hofmann
Release Date: 01.06.2023
License: CC BY 4.0
Network: RRDBNet
Scale: 2
Purpose: Upscaling AI generated images
Iterations: 185'000
batch_size: 4
HR_size: 128
Epoch: 17 (require iter number per epoch: 10964)
Dataset: lexica-aperture-v3-small
Number of train images: 43856
OTF Training: No
Pretrained_Model_G: None

Description: 2x upscaler for the AI generated image output. Trained on 43856 images from lexica.art, so its trained specifically on that model but should work in general on ai generated images.

16 Examples with Input, Upscaled (Normal and Sharp) and GT Files, plus example data: https://drive.google.com/drive/folders/1LT20d5u1m8CryCrXOJ7pWJd0mlN7X5yA