LORA trained on 65 publicly available images of Kristen Stewart.

Trained on base SD 1.5, should work with most realistic models (works best with serenity v2).

Use ADetailer if details are lost and strength of 1 should work on most prompts.
Consider leaving a review if you like the model. All feedback is appreciated.
v1 - The likeness isn't as close as I wanted it to be, will revisit this model soon.
v2 is way better. Leaving both up - to show how big a difference can be made by changing repeats.