That SD 1.5 picture doesn't look like base SD 1.5. It's way too good, perhaps it was some kind of finetune like RealisticVision?

Could be they are specifically training against it. There was some controversy about "studio ghibli style". Similarly how in the early days of Stable Diffusion "Greg Rutkowski style" was a very popular prompt to get a specific look. These days modern Stable Diffusion based models like SD 3 or FLUX mostly removed references to specific artists from their datasets.

If you think Grey Goo for just Starcraft with a new skin, check out Stormgate. They went so far to replicate almost all UI elements and put them in similar spots. With even things like the top ability bar which resembles Spear of Adun/coop commander interfaces in SC2.

I like to use these AI models for generating mockup screenshots of game. I can drop a "create a mockup screenshot of a steampunk 2D platformer in which you play as a robot" and it will give me some interesting screenshot. Then I can ask it to iterate on the style. Of course it's going to be broken in some ways and it's not even real pixel art, but it gives a good reference to quickly brainstorm some ideas.

Unfortunately I have to use ChatGPT for this, for some reason local models don't do well with such tasks. I don't know if it's just the extra prompting sauce that ChatGPT does or just diffusion models aren't well designed for these kind of tasks.

trebuchet is the solution