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

This model was trained at 512px x ??0px. Consequently it rarely 'doubles up' when using the popular 512px x 768px format.

A LoRA of 1970s/80s British m odel, presenter and actress Linda Lusardi, using 124 ref images and 1980 (real) reg images, for 24,000 steps over two hours on a 3090 GPU. Trained from scratch in Kohya, not extracted from a DreamBooth.

This LoRA performs well in the mid-range of CFG and steps, but bear in mind that it is trained on scans from traditional media, and this is going to show up in the output.

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.