This project highlights Streamlit's new hash_func feature with an app that calls on TensorFlow to generate photorealistic faces, using Nvidia's Progressive Growing of GANs and Shaobo Guan's Transparent Latent-space GAN method for tuning the output face's characteristics. For more information, check out the tutorial on Towards Data Science.

The Streamlit app is implemented in only 150 lines of Python and demonstrates the wide new range of objects that can be used safely and efficiently in Streamlit apps with hash_func.

The demo requires a CUDA-compatible GPU and Python 3.6 (TensorFlow is not yet compatible with later versions). We suggest creating a new virtual Python 3.6 environment, then running:

git clone https://github.com/streamlit/demo-face-gan.git
cd demo-face-gan
pip install -r requirements.txt
streamlit run app.py

Please ask in the Streamlit community.