What sort of prompts do you guys use?
I have 2 photos of a locomotive:
https://photos.app.goo.gl/wgd2NGBBCERSo3Ay6
https://photos.app.goo.gl/zvGmeW29HiKGXgQZ9
I know it was built on 4/1886. Is a Porter 0-4-2T. Is 30" gauge. Has 6x10 cylinders. Has 24" drivers. Has 16" trailing wheel. Has a 48" driver wheelbase. Has a 102" total wheelbase. And is 14' overall length.
Edit: I think it is able to Google that info because it gave me this.
https://photos.app.goo.gl/uQw5jL8fT9j62mm9A
And when I scale it so the wheels are 24" the wheelbase turns out correct. But notice it insists on adding a cow catcher.
You have to learn to talk it's lingo.. if you're using Gemini, read through it's "step by step" methodology to see how it thinks. A lot of it is thinking in images or even in pixels; I don't know if it understands a reference to "wheelbase" or even to look at a specific locomotive from it's database. It's weird though--I found it applying standard railing height to my sand-tower design (3' 6"), and calling it a Sand Tower, even though I didn't specify this. My techinqe is to stop and add/re-write the original instructions to get better results. And sometimes even then it would ignore parts of the instruction. I have also stopped, download the image so far, deleted the thread, and restarted with the image to get better results. So.. keep trying?
An example of something I wrote or close to it for the backdrop:
"Improve detail of the buildings and trees, retaining the architectural style. Lower perspective to the level of the first floor. Make the sky solid gray."
Or for the foobie B&O GE "Change the color of the locomotives to RGB 4f5e73. Delete graphics. Keep yellow sill stripe"
