Shivam Dreambooth of American actress Jennifer Connelly, using 125 ref images and 1400 (real) reg images, for 8,000 steps.

The period covered is around 1994-2010. 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.

Nonetheless, for the benefit of purists, all of the showcase images uploaded here are raw output, complete with readable prompts and generation details (though some have no details, because 'restore faces' was used in the generation). More will come later.

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

Please don't complain or post negative comments about the format I produce these models in. No-one is forcing you to look at this page or download anything. I don't do LORAs, Lycoris, TIs, or anything else but DreamBooths. Feel free to convert this to a more lightweight format and upload it, if you like.