Interesting. I took a stab at your prompt and SD really struggles. It just completely ignores part of the prompt. Even craiyon puts in an effort to at least complete the entire prompt.
The bison is very realistic at least. So maybe the future is different models that have different specialties.
You can take an image and feed it into SD along with the prompt (look for img2img in the readme), I think you can use that to create the idea in craiyon and then move to SD for a quality finish.
The bison is very realistic at least. So maybe the future is different models that have different specialties.
Edit: managed to get this one after a few more tries https://imgur.com/a/3061n5d