Out of curiosity, how do you tell the agent what you want - just describing it in words? Or draw something and scan it in?
I can't tell you how the parent commentor does it, but I saw an excellent reproduction of some historical building done by Astra in headless blender, using photographs, blueprints, and contemporary descriptions. Frontier models are smart enough to incorporate just about any kind of evidence you can give them about what you want, so give them everything.
loading story #50425850