American adult model Sydney Moon

Does a fairly good job on reproducing her facial features including her smile. Will sometimes pull a little too heavy on the training images meaning that you will have to prompt strongly for certain outfits and/or backgrounds (or lower the weight).

Recommended weight from my tests: between 0.8 and all the way up to 1 - most of my sample images were using a weight of around 0.9.

My sample images are a mix of different checkpoints and samplers (Euler A or DPM++ 2M SDE Karras for the more illustration leaning ones, plain DPM++ 2M Karras or UniPC for the more photorealistic ones). CFG scale around 5, If the checkpoint was capable (and most current SD1.5 should be) I ran the base images on a resolution of 768x1024 with a HighRes-Fix of 1.5 (and ADetailer on occasion).

Other settings may work better or worse - feel free to share yours!