THERE IS A LORA VERSION OF THIS MODEL AVAILABLE. IT IS EXACTLY THE SAME MODEL AS THIS ONE, EXCEPT IN A DIFFERENT AND LIGHTER FORMAT.

Shivam Dreambooth of the 1980s Italian singer, model and actress, using 48 ref images and 1980 (real) reg images, for 8,000 steps

Keep the sampling steps for the initial images no higher than about 60-70, ideally on the good Karras interpreters, and keep working the picture until it assembles. You can move the steps up as you go in for detail later with inpainting, etc..

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 may produce subject-accurate NSFW output unless countered by negative prompts.