This LoRA generates bubble butts for a number of SDXL/ZIT models. Its nearly the same dataset as my SD1x bubble butt but with a handful of larger sizes added, and better tagging.
Use the tag "bubble butt", with (optionally) one of the following size tags "medium ass", "big ass", "huge ass", "gigantic ass", "hyper butt" along with similar Hyperfusion tags.
If you want front facing images try "from front", or "ass visible from front" and negative "from behind, looking back, ass focus" at varying weights.
v4 ZIT Changelog:
Couldn't resist training a lora on Z-Image-turbo. Went pretty well, so ill probably be training more when the base model drops.
This one is just a quicky, probably not fully trained, but good enough as you can see.
Dataset is fully anime/furry, so you need to include realism related tags and words if you want that.
v4 WAI_IL Changelog:
No changes, just re-trained on WAI_IL-v14 because I was in a tinkering mood.
v4 noobai_vpred Changelog:
Not much changed. Added a few more images/captions/tags, and trained on noobAI_vpred_1.0 with somewhat similar settings to v3
Same tags as v3, you already know what to expect
"hyper butt" has a greater effect on this noob_vpred version as well if you want it really large.
Description
Just a quick bubble butt lora on the new Z-image architecture. Ill do a full lora when the base model comes out, but I couldn't resist trying it out before then.
Pretty happy with results. Didn't require any tinkering. But I did need to use the ai-toolkit lora adapter to get stable results.
Same dataset as the last.
Training Details:
train_text_encoder: false
type: "lora"
linear: 16
linear_alpha: 16
conv: 8
conv_alpha: 8
caption_dropout_rate: 0.1
resolution: [ 768, 1024 ]
flip_x: true
batch_size: 1
gradient_accumulation: 8
optimizer: "adamw8bit"
lr: 4e-4
dtype: "bf16"
FAQ
Comments (4)
PSA: don't be scared of this lora. The preview images are extreme, but this lora at a low strength produces beautiful, large but well-proportioned asses. Z image likes flat butts and this helps to fix it, it's just a 'donk' slider!
For z-image and LORA LOADER STACK + Lora character ,put on 0.40-0.50 strenght + trigger words
thanks for the pin, bro. Big fan!
Big fan of this model, love the shape and I love how much control you can have over the size. It also allows you to generate from multiple angles (not just behind), which places it way ahead of other similar models!