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
Weighed trained version with token revision of the dataset. Should improve the finish and clean up artifacts slightly.
FAQ
Comments (7)
Hi, I've got the same issue that I had on a previous of your lora but fixed since : "Error while deserializing header: InvalidHeaderDeserialization"
The v1 is great, hope the v2 will be better :)
thx for this
Same error here as well when I was trying to render a character using this LoRA just now with SwamUI that I thought at first was Swam's Comfy backend it uses derping out again. Might as well go back to the older version or it's Pony version until this gets fixed.
Hello, thanks for letting me know. I have replaced the faulty file with the original unedited weight trained file. Sorry for the inconvenience. The issue was with the metadata. Of course, Forge again did not tell me there was any issue until I rebooted.
My weighed loras involve lora merging. When you merge two loras, the result is left with a stub json that essentially says "this was merged from X and Y" and nothing else - this means training keywords are lost and you can't see them on most UIs, which I find is a nice feature.
When I release a weight trained lora, I typically copy the metadata from the original non-weight trained lora and paste it over the WT lora, update the hash and lora name in the json and send it. I don't know exactly when but some update to the safetensors library must've tightened the check on the metadata integrity and it seems none of the metadata editors I've tried is up to the task yet.
It sucks as I can't give new WT loras any metadata but fortunately this specific one doesn't exactly need it.
Again, thank you very much and sorry for any inconvenience this might've caused.
@downloadmorevram Thanks! No problem, very good lora to add that so beloved thickness.
@downloadmorevram Thank you. This is some nice news to wake up to! Can't wait to try again! 👍
AWESOME!
Excellent