Awesome
Steam StyleGAN2-ADA
The goal of this Colab notebook is to capture the distribution of Steam banners with a StyleGAN2-ADA model.
Usage
- Acquire the data, e.g. as a snapshot called
256x256.zip
in my data repository, - Run
StyleGAN2_ADA_training.ipynb
to train a StyleGAN2-ADA model from scratch. - Run
StyleGAN2_ADA_image_sampling.ipynb
to generate images with a trained StyleGAN2-ADA model, - To automatically resume training from the latest checkpoint, you will have to use my fork of StyleGAN2-ADA.
Data
The dataset consists of 14k Steam banners with RGB channels and resized from 300x450 to 256x256 resolution.
Images were downloaded with download_steam_banners.ipynb
.
Images were then filtered (duplicates, outliers, etc.) with remove_duplicates.ipynb
.
References
- DCGAN:
- StyleGAN:
- StyleGAN2:
- StyleGAN2-ADA: