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.

SR
LR
BeforeAfter
100%
Scroll to zoom · Drag to pan
Thumbnail
1 / 3

HFA2k VCISR GRLGAN ep200

4xGRLby Helaman

Good for

AnimeCartoonCompression RemovalRestoration

Purpose: 4x anime upscaler handling video compression artifacts, trained for 200 epochs

4x anime upscaler handling video compression artifacts since trained with otf degradations for "mpeg2video", "libxvid", "libx264", "libx265" with crf 20-32, mpeg bitrate 3800-5800 (together with the standard Real-ESRGAN otf pipeline). A faster arch using this otf degradation pipeline would be great for handling video compression artifacts. Since this one is a GRL model and therefore slow, as noted by the dev maybe more for research purposes (or more for single images/screenshots). Trained using VCISR for 200 epochs.

"This is epoch 200 and the start iteration is 85959 with learning rate 2.5e-05"

Slow Pics examples:
h264_crf28
ludvae1
ludvae2

Training details (8)
Date
2024-01-04
Dataset
hfa2k
Dataset size
2568
Training iterations
85959
Training epochs
200
Training batch size
6
Training HR size
128
Training OTF
Yes
How to upscale →Understanding licenses →
Download (50.7 MB)
PyTorch .pth file / Hosted by Google Drive

Model

Architecture
GRL
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