Trained exclusively using anime screenshots with multiple characters and scenery. Many different outfits and full body shots are trained just to get the body proportion right.Note: Since the characters have very unique proportions and head shape, I don't recommand using it to create any sex scenes.Recommended Settings:The LoRA is trained on NoobAI Vpred 1.0. It may or may not work on the Epsilon model.Sampler: Euler / Euler aScheduler: Normal / SimpleSteps: 36-40CFG: ~5 (Euler) / ~4 (Euler a)(Based on NoobAI-XL User Manual)LoRA Strength: 0.9-1.0Negative Prompt: None, v-prediction model seems to be very sensitive to negative prompt, having it will impact the style a lot, same applies to any artist tags. Use positive prompt if you don't want anything (eg. no headwear, no hair ornament, uncensored).~Trigger words:koi to usoSome lighting and effects being trained:light source from back, creates a bright outlines of the characterbacklightinglight source from side, usually half of the face is litsidelightingsunset outdoors / candle light indoorsorange lightcreate a bloom effect with yellow tonewarm coloredchromatic aberrationchromatic aberration
