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.

ditn_w16_pretrain

4xDITNby musl

Good for

Meant to quick start new DITN models trained on neosr. Trained only on downscale degradation (bicubic, bilinear, nearest, lanczos and mitchell). Note: Flash Attention breaks inference compatibility with official code.

Training details (2)
Date
2023-09-14
Training iterations
215000

Model

Architecture
DITN
Scale
4x
Color Mode

Rights

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

Similar models