The result of my experiment with trying to generate Among Us characters using AI. I used dreamboth and SD 1.4 to create the model.

To use the model, use:

"amongus man" in positive prompt and:

"lowres, bad ???????, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name, game, screenshot "

in negative prompt (game, screenshot + lowres are the most important)

You can edit, improve and publish your version of the model as much as you want, but it would be nice if you could link me in the description when you're done :)