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

MARCH 2024 - V2

The new VERSION 2 of the Lana Wood model uses the multi-train system, and does most things a little better than the original.

It requires a LoRA strength of 0.15.

It has a new trigger - lwoodex (or lwoodex woman, if you prefer).

It uses a fair bit of synthetic data, more than the older version 1 did.

OLDER INFORMATION FROM ORIGINAL RELEASE

THIS IS THE LORA VERSION OF THE ORIGINAL 2GB CHECKPOINT FILE.

CLICK HERE FOR A MUCH BETTER RANGE OF PREVIEW IMAGES

Shivam Dreambooth>LORA model of American actress and ??? symbol Lana Wood, using 145 ref images and 1400 (real) reg images, for 12,000 steps.

The period covered is around 1970-1979. 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 is very likely to produce ????? renderings unless counter-prompted.