Yes, I am also very positively surprised by the AI img generator. And i too would like to know, what kind of program is behind all this and what models are used, and these style choices are they regular LoRA’s or what ? I too have used comfy and it has been so troublesome to get it consistent in style, and the style i want is realistic western cartoons, which isnt what the checkpoints usually come up with, but when i find something good, comfy may change to photo just because i add a word to the prompts. Such problems are not here. I am so happy. Cannot remember last time i turned off the ad block for anything. But its off here.

I too tried to write a romantic story but ended up bloody and with broken ribs. I think we have to realize this AI is a villain camouflaging itself behind verbose language and quirky details. However, shouldn’t we be able to direct the style? Like - speak like a farmer, descriptive language without latin. Or speak like a street gang member, with jargon. ? It would be natural to write such instructions in the first input - like Style= No violence , behave , good temper, & use common language.