Character LoRA of Vi from Arcane, trained on Z‑Image Turbo using Ostris AI‑Toolkit. Focused on realistic and high quality images from the show itself with variations for realism, trained on 35 captioned images covering multiple outfits, angles, and lighting. Works best for grounded, cinematic shots at 768–1024px.

Best Weight For LoRA: 0.7 - 0.8

Example Prompt including trigger word: "Vi_Arcane, a young woman with short pink hair in an undercut swept to one side and blue eyes, wearing a red jacket over a fitted top, small "VI" tattoo under her eye, nose ring, full-body shot, standing upright and turned to the side."

Recommended Lora Loader Node: Lora Loader (Z-Image) (CRT) by CRTNodes