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.

Normal RG0

4xESRGANby RunDevelopment

A 4x upscaler for uncompressed normal maps with a zeroed-out B channel. The input is required to have no alpha and constant-zero blue channel. The model can handle some light compression artifacts but has trouble with quantization artifacts. The output normals will also have a constant-zero B channel. Use external software or image editing plugins to properly normalize the generated normals and generate the Z component (if necessary). E.g. chaiNNer can do this with Normalize Normal Map node. Do not rely on this network producing unit vectors.

More information: https://github.com/RunDevelopment/ESRGAN-models/blob/main/normals/README.md

Training details (8)
Date
2022-04-02
Dataset
Custom. See description
Dataset size
577
Training iterations
100000
Training epochs
89
Training batch size
8
Training HR size
128
Training OTF
No

Model

Architecture
ESRGAN
Scale
4x
Size
64nf23nb
Color Mode

Rights

CC0-1.0
Private use
Commercial use
Distribution
Modifications
No Liability & Warranty
Disclaimer

Collections that include this model

Similar models