An artificial intelligence from Nvidia called StyleGAN2 can draw an almost infinite number of pictures in different styles. Users can choose the style, color scheme, and appearance of their brushstrokes.
The company unveiled its latest machine learning experiment for image creation at CVPR 2020.
The video shows how users can work in the program: you can create new portraits in the shortest possible time by controlling the colors, facial expressions, and poses.
“Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality,” StyleGAN statement says.