BeforeAfter
100%
Scroll to zoom · Drag to pan
VimeoScale
Good for
Category: Pretrained Discriminators Purpose: Upscaling IRL video content
This model is one of the longest I have trained and tuned, includes some noise training but this is not intended for deblocking/decompression. Combined with https://github.com/JoeyBallentine/Video-Inference 's fp16 mode, this should handle most SD and 720p content at or faster than ESRGAN, with a significant bump in quality.
Pretrained model: Self-Trained Base for the Unet finalisation with vgg_fea discrim
Training details (5)
- Date
- 2021-10-08
- Dataset
- 200gb+ Combination of Collected Vimeo scenes (CG, realistic/video, movie trailers, and motion graphics) at original quality and Vimeo90k
- Training iterations
- 200000
- Training batch size
- 13
- Training HR size
- 128
Model
Rights
CC-BY-SA-4.0Disclaimer
Private use
Commercial use
Distribution
Modifications
Credit required
Same License
State Changes
No Liability & Warranty