I've been experimenting with GauGAN2, released
[https://blogs.nvidia.com/blog/2021/11/22/gaugan2-ai-art-demo/] in Nov 2021 as a
follow-on to GauGAN
[https://www.aiweirdness.com/this-neural-net-makes-my-sketches-19-06-15/]. One
new thing Nvidia added in GauGAN2 is the ability to generate a picture to match
a phrase.
"A
