Ah, cool. You seem to have much better success with that then I have. Then again I mostly just try to break with overlapping human forms 😂… AI does not seem to understand human flesh or individuality😬😳 …works better w objects
?cid=2154d3d7m0rvj7it5alix9c7dy8b0k3rsw18q0wacssy6nag&rid=giphy.gif&ct=g
Takes some practice to know what works. Different models do different things. Prompts can return wildly different results depending on what you enter. I’ve generated probably over 5000 images now so I have a decent grasp of what works.
Human shape and faces are actually well understood by AI. It’s the hands it has the most difficult time with. Midjourney specifically does poorly with more than one subject.
🤙 Will have to try that some then. I’ve generally noticed the same, faces are usually alright, but if two people dare hug… ooooh boy they must need be a flesh monster with interconnected limbs 😳🤣🤣😅😰
?cid=2154d3d7o2ialxz6k1q289cg6ei7k08heb5mpg6a1s6x4uac&rid=giphy.gif&ct=g