NVIDIA has open-sourced a hyper-realistic face generator called “StyleGAN”, which can use many human photos to generate high quality realistic faces for people doesn’t exist.
StyleGAN is a TensorFLOW implementation for A Style-Based Generator Architecture for Generative Adversarial Networks.
The Flickr-Faces-HQ (FFHQ) dataset used for training in the StyleGAN paper contains 70,000 high-quality PNG images of human faces at 1024×1024 resolution (aligned and cropped).
Users can either train their own model or use the pre-trained model to build their face generators. Linux and Windows are supported, with specific system requirements as follows:
- Both Linux and Windows are supported, but we strongly recommend Linux for performance and compatibility reasons.
- 64-bit Python 3.6 installation. We recommend Anaconda3 with numpy 1.14.3 or newer.
- TensorFlow 1.10.0 or newer with GPU support.
- One or more high-end NVIDIA GPUs with at least 11GB of DRAM. We recommend NVIDIA DGX-1 with 8 Tesla V100 GPUs.
- NVIDIA driver 391.35 or newer, CUDA toolkit 9.0 or newer, cuDNN 7.3.1 or newer.
share your Opinion: How you can use this generator?!