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.

LADDIER1

4xESRGANby Alexander Syring

Remove noise, grain, box blur, lens blur and gaussian blur and increase overall image quality.

Training details (5)
Date
2019-11-13
Dataset
Mostly images of Nirvana some of other images
Training iterations
282500
Training batch size
8
Training HR size
128

Model

Architecture
ESRGAN
Scale
4x
Size
64nf23nb
Color Mode

Rights

None

Similar models