Skip to content

laphisboy/StyleGAN2-KaoKore-Style-Mixing

 
 

KaoKore Faces

Blending FFHQ faces with KaoKore pre-modern Japanese art faces

KaoKore Dataset

source: https://github.com/rois-codh/kaokore https://arxiv.org/abs/2002.08595

Created blend_and_project.py

from projector.py
referenced:
https://github.com/justinpinkney/stylegan2/blob/master/blend_models.py
https://github.com/XingruiWang/Animefy/blob/master/blend.py

Results

Model blend:

  • model trained for 500,000 iteration on FFHQ
  • model further trained for additional 180,000 iteration on KaoKore

How model is blended

Result for blend_and_project

Result on my face

Future Fixes

Latent space is found by projection on blended model,
But wwould it have been better if projection of FFHQ trained StyleGAN2?

About

YAI 7th - StyleGAN2 Style Mixing with KaoKore Dataset

Resources

License

MIT and 3 other licenses found

Licenses found

MIT
LICENSE
Apache-2.0
LICENSE-FID
BSD-2-Clause
LICENSE-LPIPS
Unknown
LICENSE-NVIDIA

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 90.9%
  • Cuda 7.7%
  • C++ 1.4%