Some of the “passable” generations from when I started using LoRAs, I was still basically guessing how to prompt properly and eventually got better. I also started to generate more realistic images shortly after this.
The prompts used a lost to history (but they are bad enough to not be much use).
Civatai seems awesome, I’ve gotta check it out, thanks!
Using action figures with stable diffusion sounds really difficult lol. I’m bad at posing stuff IRL, I once spent multiple hours trying to take a single nude photo to post on discord lol