/ArcaneGAN

ArcaneGAN

MIT LicenseMIT

ArcaneGAN by Alex Spirin

Photos Colab

Videos Colab for videos

visitors

If you like what I'm doing you can:

Thank you for being awesome!

Changelog

ArcaneGAN v0.4

The main differences are:

  • lighter styling (closer to original input)
  • sharper result
  • happier faces
  • reduced childish eyes effect
  • reduced stubble on feminine faces
  • increased temporal stability on videos
  • reduced mouth\teeth artifacts

Image samples

v0.3 vs v0.4

v3-4

Video samples

ryan.mp4
obama.mp4

ArcaneGAN v0.3

Videos processed by the huggingface video inference colab.

obama2.mp4
ryan2.mp4

Image samples

arcaneganv03

Faces were enhanced via GPEN before applying the ArcaneGAN v0.3 filter.

ArcaneGAN v0.2

The release is here image photo_2021-12-04_08-05-34 photo_2021-12-04_07-23-17 weewq

Implementation Details

The model is a pytroch *.jit of a fastai v1 flavored u-net trained on a paired dataset, generated via a blended stylegan2.