User LoRA

XL

Condom Suit (Bodysuit Condom Filling) Pony & NoobAI

#Condom

#Bodysuit

Bìa bị gỡ: Vi phạm quy tắc nội dung

Tải lại ảnh bìa. Bạn vẫn có thể tìm kiếm và sử dụng mô hình này.

Đã tải lên vào
18:04 5 thg 1, 2025
Lượt sử dụng
652
Đánh giá
Chưa có đánh giá
Từ khóa

bodysuit, bulge

Quyền
  • Allow image generation & sharing
  • Cho phép người dùng tải xuống mô hình của bạn
  • Sử dụng thương mại

Mô tả

Futanari girls sporting erections under a bodysuit they're wearing, and, sometimes, filling them with semen. Now updated for Pony Diffusion and NoobAI. NoobAI ver 0.5 has a base level of understanding of condom suit; this Lora makes it more consistent.It should work for regular anime girls as well as anthro girls. Non-femboy guys may or may not work since they were very underrepresented in training data.Pony Diffusion & NoobAI:The trigger word is: bodysuit, bulge. You can change the color of the suit like this: pink bodysuit, red bodysuit, ... and for ejaculation inside the suit: ejaculation, (cum:1.3), condom filling although condom filling occasionally will cause random floating orbs of condom-cum that are completely detached from the penis.Recommend weight 0.8 to reduce how much the style is affected. Bump it up to 1.0 if it's being stubborn.Seems to work better with more common bodysuit colors such as black, blue, and red. Weird colors like orange didn't always come out right. Honestly, this was a pretty lazy LoRA, so maybe not enough or varied training data.SD 1.5 version (old):The trigger word is: condom suit, bodysuit. You can change the color of the suit like this: pink bodysuit, red bodysuit, ... and for ejaculation inside the suit: ejaculation, cum in clothes, condom fillingThis was trained against the Futanari Factor model. This means that it wants a CLIP skip of 2 but I don't think it matters much (sometimes I wonder if CLIP skip is just a meme, desu). AOM2 is completely unable to work (as typical for futa), EasyFluff kinda wants to work but not really.This first version significantly changes the artstyle and simplifies it for some scenarios. I also suspect it is a bit overfit to the input images. To counteract these weaknesses, try dropping the weight, using a style LoRA, the Add Detail LoRA, or CFG Rescale. I recommend weight 0.6 and upping it if it's not working. You'll need a few rerolls to get a good picture.

Bình luận