If you're using a system like Google Photos, artificial intelligence is already in your life, growing smarter as you feed it more images captured by your phone. A smartphone can now magically erase elements in a photo. The demonstration is far less important than what it represents. Below you'll see a demonstration of this new text input element in an interface that's essentially an extension of NVIDIA Canvas. NVIDIA points to text, semantic segmentation, sketch, and style. One single GAN framework in GauGAN2 includes several modalities. This model uses a wide variety of sketches (approximately 10 million high-quality landscape images), as its bank of visual knowledge, and draws upon said bank in order to decide what your words could mean in a work of art. With GauGAN2, NVIDIA researchers expanded what's possible with simple input and artificial intelligence interpretation of said input.
