Many preview images on this site are currently broken due to their original hosts being indefinitely offline. Work is underway to recover the affected images and rehost them somewhere reliable.

Model output example
100%
Scroll to zoom · Drag to pan
Thumbnail
1 / 5

4xArtFaces_realplksr_dysample

4xRealPLKSR_dysampleby Helaman

Good for

Faces

Link to Github Release

4xArtFaces_realplksr_dysample

Scale: 4
Architecture: RealPLKSR with Dysample
Architecture Option: realplksr

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

Dataset: ArtFaces
Dataset Size: 5'630
OTF (on the fly augmentations): No
Pretrained Model: 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 which is a curated version of the metfaces dataset for the purpose of training single image super resolution models.

Training details (7)
Date
2024-08-08
Dataset
ArtFaces
Dataset size
5630
Training iterations
139000
Training batch size
6
Training HR size
256
Training OTF
No
How to upscale →Understanding licenses →
Download (28.3 MB)
PyTorch .pth file / Hosted by GitHub

Model

Architecture
RealPLKSR_dysample
Scale
4x
Color Mode

Rights

CC-BY-4.0
Private use
Commercial use
Distribution
Modifications
Credit required
State Changes
No Liability & Warranty
Disclaimer

Similar models