APRIL 2024 - NEW VERSION!
A new LoRA trained from scratch using triple-training, featuring much synthetic data.
This new model can do much more than the old one.
Requires a LoRA strength of 0.15.
Has a new trigger word: sfxer woman.
Very likely to produce NSFW material.
OLD VERSION:
Shivam Dreambooth>LORA of British 1980s glamor model Samantha Fox, using 77 ref images and 1980 (real) reg images, for 12,000 steps. The period covered is around 1985-1989.
I generally use these models in complex workflows, inpainting faces after initial T2Is, and using ControlNet extensively. So if you're hoping for one-click prompt magic, my models aren't data-curated with this in mind, but rather as tools for traditional workflows that use Photoshop and other older methods.
This model is very likely to produce NSFW and nude renderings unless counter-prompted.
Description
CIVIT DOES NOT ALLOW SMALL FRACTIONS IN THE 'STRENGTH' SECTION, SO THE INFORMATION IT GIVES IS WRONG.
Please use a LoRA strength of 0.15 for this LoRA. Anything else is going to pretty much break it!