PLEASE NOTE - ALL MY CELEBRITY LORAS WILL BE DELETED (BY MYSELF) BY THE END OF JUNE 2024.

Shivam Dreambooth>LORA of American actress Pam Grier, using 92 ref images and 1400 (real) reg images, for 9,000 steps. Will default to stock-style poses, and frankly needs retraining soon (watch this space)>

NOTE: This particular model is a little overcooked, so keep the CFG level low. For T2I generation, try clip skip 2 if general results unsatisfactory in terms of diversity.

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 ????? renderings unless counter-prompted.