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

Shivam Dreambooth>LORA conversion of the British glamor model and actress Donna Ewin, as she appeared in the early part of her career, using 362 ref images and 1400 (real) reg images, for 20,000 steps.

Due to the varied and HQ nature of the data, the huge amount of it, and the extensive training, this is an unusually versatile model, in terms of posing, and is capable of producing excellent skin and face detail, among other things. Does best with ControlNet and other guideline methods, rather than straight Text-to-Image.

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.