Please read the version details for updates, thank you.
"I like girls that are like little parade floats" - Anonymous
Produces girls with a body that looks like a hyper bastardization of the venus bodytype, enlarging it and thickening it to the extreme, while taking care of keeping the overall hourglass shape. While the girls it creates are beyond a doubt overweight, it attempts to avoid excessive fat rolls, giving the impression that the midsection is larger as the foundation for the much larger top and bottom halves of the body, rather than being conventionally obese.
The head is smaller as a shorthand for making the generated girls look truly massive. Because of this, the faces can look shoddy unless the angle allows a closer view of it (such as with high angular shots, cowboy shots), in which case it is recommended to lower the weight when upscaling.
In general, this model can also help you if you enjoy gigantic breasts, asses AND bellies, but you struggle generating all three in a single picture.
This model was created using Prodigy, a dataset built on roughly 95% AI pictures generated with earlier versions, and most notably, no tagging whatsoever, as an experiment. Therefore no specific keyword is needed, only guiding it towards the desired shape through thickness tags. I listed a handful of those as the trigger words, even though the model hasn't been trained on them, for your convenience.
Muscular girls with this body shape (strongfats) can also be made, my go-to method for those besides adding muscle tags is to also include "abs" in negatives. Be advised that muscle and tone is correlated with slimness so they might compromise upper size.
Also mind that backgrounds fight for space with the character so you might find it easier to create a bigger character in an (unprompted for) simple background than on an specific location.
Description
Aimed to improve the finish of the lora. I attempted to reduce face scuffing and remove artifacts like stray or strange fat folds, double navels, misplaced legs, etc, by fixing the dataset.
FAQ
Comments (4)
100 percent will try the 3-wt version, 2-wt was already really good, can't wait to see how good 3-WT is.
I'm finding more success with 2-wt still, any tips you're finding useful for this new version?
3-WT is a little cleaner so you could raise its weight slightly more than you would use for 2-WT.
I flicked over a few of your prompts and saw that you use extremely high emphasis in your prompts in the 1.9~2.0 range.
I don't do much realism but from my experience with Pony and AutismMix an emphasis of 1.5 is already overkill. In anime models it's impossible to miss because the image gets completely destroyed due to conflicting styles fighting each other - I suspect that realism models can take much more emphasis since real life has one "style", but in turn the image is considerably stricter to the point of negating lora effects.
Other than that I don't know, browse through other people's prompts yourself, see what works.
@downloadmorevram Thanks a ton for the response, I definitely can be guilty of cranking up emphasis instead other changes. I will bring all the emphasis down and try again.