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.<h3 id="v4-zit-changelog:">v4 ZIT Changelog:</h3><ul><li>Couldn't resist training a lora on Z-Image-turbo. Went pretty well, so ill probably be training more when the base model drops.</li><li>This one is just a quicky, probably not fully trained, but good enough as you can see.</li><li>Dataset is fully anime/furry, so you need to include realism related tags and words if you want that.</li></ul><h3 id="v4-wai_il-changelog:">v4 WAI_IL Changelog:</h3><ul><li>No changes, just re-trained on WAI_IL-v14 because I was in a tinkering mood.</li></ul><h3 id="v4-noobai_vpred-changelog:"> v4 noobai_vpred Changelog:</h3><ul><li>Not much changed. Added a few more images/captions/tags, and trained on noobAI_vpred_1.0 with somewhat similar settings to v3</li><li>Same tags as v3, you already know what to expect</li><li>"hyper butt" has a greater effect on this noob_vpred version as well if you want it really large.</li></ul>

bubble_butt SDXL/ZIT

Added 10% more images, and improved a small amount of tags. Otherwise same dataset as v3 but trained on NoobAi_vpred 500 handpicked images extracted from my bubble_butt classifier dataset Training config:<ul><li>Optimizer ADOPT</li><li>--optimizer_args "decouple=True" "weight_decay=0.001" "betas=0.9,0.999" (not sure if this is the best config, still tinkering)<ul><li>Edit: after some testing, don't use weight_decay with DoRA, it hurts the results.</li></ul></li><li>--zero_terminal_snr</li><li>--v_parameterization</li><li>See bubble_butt_v3 for the params I didn't change </li></ul>

Files with SHA256: 3a4c6047d528e6df8185c1a638b37db1a48d6707e272c90a7cd28a2f903e7f44