Medium-quality Shivam Dreambooth LORA conversion of Italian actress and sex symbol Sophia Loren, using 188 ref images and 1400 (real) reg images, for 12,000 steps.

Why it's larger than usual. It can be very rewarding to use, but this is a tricky model, and I therefore didn't FP16 the Kohya conversion - I didn't want to over-slim the weights in this case. It's not the most resilient model I did.

To get a generation of the younger version, put the word young in front of the key prompt, and use brackets to control the degree of youth.

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 well produce subject-accurate NSFW output unless countered in negative prompts.