Shivam Dreambooth>LORA of American Taxi and Evening Shade actress Marilu Henner, using 77 ref images and 1400 (real) reg images, for 8,000 steps. The period covered is around 1978-83.

This model was trained on unusually high-quality data, though mainly of posed publicity stills. Therefore it may prove repetitive in a text-to-image context, but is well-suited for high quality image-to-image work.

No nudes were in the training data, so while the model may sometimes produce some racy images, it is not likely to produce truly NSFW output by default.

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.