/AwesomeStyleGAN

Awesome StyleGAN models

Primary LanguagePython

AwesomeStyleGAN

Awesome StyleGAN models

GAN image transformation video

Generate video of image transformation using offficial Nvidia StyleGAN2 ADA models:

video.gif

Installation

Use Docker

Or manually install all dependencies and download models:

TensorFlow model

Clone the repository:

git clone https://github.com/NVlabs/stylegan2-ada.git

Download the preptarained model:

wget https://nvlabs-fi-cdn.nvidia.com/stylegan2-ada/pretrained/ffhq.pkl -O models/nvidia-stylegan2-ada-ffhq-tf.pkl

Pytorch model

Clone the repository:

git clone https://github.com/NVlabs/stylegan2-ada-pytorch.git

Download the preptarained model:

wget https://nvlabs-fi-cdn.nvidia.com/stylegan2-ada-pytorch/pretrained/ffhq.pkl -O models/nvidia-stylegan2-ada-ffhq-pt.pkl

Usage

An example script usage is in the scripts folder:

Video with sound

Instead of linear interpolation you can use sine interpolation. There is an example of viddeo with beat detection from Aubio library.

There is an another example of video with beat detection in the wild.