CivArchive
    Jinx [Arcane] (Z-Image Turbo LoRA) - v1.0
    Preview 112807632Preview 112807631Preview 112807629Preview 112807634Preview 112807630Preview 112807635Preview 112807633

    Character LoRA of Jinx 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: "Jinx_Arcane, a young woman with long blue hair in a loose braid and bright blue eyes, wearing a cropped halter top, gloves, striped pants with belts, and visible tattoos, full-body shot, walking forward with a wary expression along a sunlit street."

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

    Description

    Trained on about 35 images
    Trained for 2000 steps

    LORA
    ZImageTurbo

    Details

    Downloads
    519
    Platform
    CivitAI
    Platform Status
    Available
    Created
    12/7/2025
    Updated
    12/27/2025
    Deleted
    -
    Trigger Words:
    Jinx_Arcane

    Files

    Jinx_Arcane_v1.safetensors

    Mirrors

    CivitAI (1 mirrors)