Category: Pretrained Discriminators
Purpose: Upscaling video content

This model is meant to surpass VEAI 2x while being efficient to run quickly with fp16. The real-esrgan/BSRGAN augmentation and Unet should help with videos where the resolution is not ideal and can reconstruct details without effecting blurs in most cases. This model SHOULD run faster than real-esrgan while matching the resolving and enabling some multiframe feature extraction. No major denoising/compression/blurring effects (or artifacts) should be found.

Pretrained model: Self-Trained Base for the Unet finalisation with vgg_fea discrim

VimeoScale Unet

Category: Pretrained SOFVSR Models
Purpose: RL videos - interpolation
Architecture: CAIN (CAIN 1 Group)

Trained mostly on abba music videos

cainREALTIME

Category: Pretrained Discriminators
Purpose: IRL videos

none

REDSVAL-7f-RRDB Lite

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

Architecture	SOFVSR
Scale	4x
Color Mode	RGB
License	CC-BY-SA-4.0 Private use Commercial use Distribution Modifications Credit required Same License State Changes No Liability & Warranty Disclaimer
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

VimeoScale

Similar Models