Before we had the GPT-3 rules-text and location description thread. There's a new toy out there which generates images based on a text prompt, and the method has been refined by a number of artists and is starting to look very, very good. I've just started playing with this notebook (https://colab.research.google.com/dr...dK-N9h_y65b8fj), which lets you run the thing in browser on a cloud GPU.

A couple of example outputs...

"a photo-realistic and beautiful painting of a pirate ship sailing the cloud-ways into a storm."

"a photo-realistic and beautiful painting of the soul-forge churning out yet another weapon for the damned to fight their eternal war"

"a photo-realistic and beautiful painting of a jungle filled with purple, glowing moths"

So, obviously not perfect. It does a 'jungle filled with purple' + 'moths' rather than purple, glowing moths for example. But still, if you tweaked the prompts to get what you wanted, I think you could probably illustrate a campaign in real-time with this.