Thanks. Mostly I was just curious about the process.
So, to produce something like this:
you'd have told it "Start with something similar to M.C. Escher's "Relativity" but don't create impossible triangles. Place a man, facing away from the viewer, in the center of the image. He's standing on the landing below two sets of steps that progress upward and away from him and from one another, gazing at the apex of a balcony that projects toward him and that is centered between the stairs."
Add more details as they occur to you and keep iterating, until you get what you're after? Presumably you can go back to previous versions as you like, because the AI will have remembered everything it's done each time?
By the way, I particularly liked the last image of the face with cut-paper leaves for hair.
It actually can be as simple as this, and the tool takes from there: stairs, Escher style.
and it can produce that, just from that short sentence. However, you can be as creative as you want with description. A.I. produces amazing results with broad narrative. From what I’m aware, you cannot go back to previous results, but in case of the tool I use, you can change things in certain spots in the image. Not sure how to explain this further.
Also, fur the fun of it, I took the narrative you ‘translated’ that image, and let the tool create a new image based on that. See below:
Let me know if you have any other questions. I’ll be glad to help.
I appreciate you liked the cut-paper face. Also, feel free to give me ideas to create some images. I’ll post on my Facebook and Instagram.
Doron