Shivam Dreambooth>LoRA conversion of British pop singer Jay Aston, who was a member of the popular UK band Bucks Fizz throughout the decade, after the group won the Eurovision Song Content in 1981.

Uses 171 ref images and 1400 (real) reg images, trained for 8,000 steps.

NOTE: This model is a bit overcooked, so use very low (i.e., 3-4) CFG for generations.

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.