This Lora was trained on 20 images of the Jane Margolis (actress Kristen Ritter)

Prompt: (masterpiece, best quality, awards winner) (close up portrait Kristen Ritter as Jane Margulis addict) (front view:1.3), (breaking bad) girl, epic character composition, by ilya kuvshinov, alessio albi, nina masic, sharp focus, natural lighting, subsurface scattering, f2, 35mm, film grain <lora:janemargulis:1>

Negative promt: 3d, ((disfigured)), ((bad art)), ((deformed)), ((poorly drawn)), ((extra limbs)), ((b&w)), weird colors, blurry

Model: Realistic Invision

Steps: 20, Sampler: Euler a, CFG scale: 7, Seed: 2893519060, Size: 512x704, Model hash: a8e08b582e, Model: realisticVisionV30_v30VAE, Lora hashes: "janemargulis: 8fb6681bd0e9"

You can use other prompt and other models it gives interesting and unpredictable results