LORA trained on 55(30,25 split) publicly available images of Maisie Williams.

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

Use ADetailer if details are lost and strength of 1 should work on most prompts.
If there's noise in the image, can lower upto 0.7.
Consider leaving a review if you like the model. All feedback is appreciated.