Zenkai No? Love Live!
Conditional Variational Autoencoder  based School Idol image generation, implemented in PyTorch.
Used 1,466 face images of members of main school idol teams on the animation "Love Live!", extracted from the game "Love Live! School Idol Festival".
Note that this repo's implementation is also a fine implementation of the CVAE.
Clone the repo and type following:
python preprocess.py python train.py python sample.py
Using a nice GPU is heavily recommended.
Autoencoding images in a train set
Autoencoding images in a test set
Generating images from a randomly sampled latent vector
Hanayo to Rin:
Maki to Nico:
Maki to Yoshiko:
Ruby to Dia:
Yoshiko to Riko:
 Kingma, Diederik P., et al. "Semi-supervised learning with deep generative models." Advances in Neural Information Processing Systems. 2014.