This LoRA recreates the likeness of Ai Shinozaki (篠崎 愛), the renowned Japanese gravure model and actress. It is designed to capture her distinctive features across a wide variety of styles and settings.

The trigger word is optional, but using `Ai Shinozaki` will generally produce the strongest and most accurate resemblance.

A LoRA strength between 0.7 and 1.0 is recommended for the best results.

As this LoRA is trained on a single individual, some facial features may bleed onto other people in multi-character images. To reduce this effect, describe the appearance of every other person in your prompt as specifically as possible. While some identity leakage is inevitable, detailed prompting helps keep it to a minimum.

You should use Ai Shinozaki to trigger the image generation.

Download them in the Files & versions tab.