NokiMo
otakuhikikomoriart
otakuhikikomoriart

patreon


πŸ˜‘

Of course, it's a matter of taste, but in my opinion, the old model is the cutest (the first picture). It has rich and slightly darker colors.

The second picture is the new model (let's call it that). I think its style is a bit too much 3D, and the colors are somewhat "sweet." However, it handles backgrounds and complex elements really well.

The third picture (the one I've been using for the last two days) is the new model with a style LORA. This LORA was trained on art from Megami Magazine. It's excellent for creating solo characters. But when I try to make two characters, the results aren't as good as I'd like (though, again, that's just my preference). Its colors are the most "natural," and the picture looks more lifelike (in comparison). It's funny that the LORA kind of ruins the backgroundsβ€”which is the model's strong pointβ€”by applying its style. Just compare the city in the last two pictures.

Anyway, this post is for those who make requests (I hope at least someone reads what I write 🀣).

πŸ˜‘ πŸ˜‘ πŸ˜‘

Comments

πŸ€—

Dmitriy

Stable diffusion, UI "reforge" (there are several of them). This is not an app for a phone or a website (let me clarify, because that's what people often think πŸ˜…). You install it locally on your PC.

Dmitriy

I like this picture a lot and what AI did you use to do all these arts? I would like to try it out

Nate

I def prefer the old style and like that you wrote all this explanation out...new guy here and I could see 'something' was different but I don't have an eye for these things. Also have no technical knowledge because my first thought was 'isn't there a button that says replace background?' but now that I see all the different details the style prob would look much too different. Last thing...awesome that you're working on your skills!

Bailout


Related Creators