CivArchive
    Arcane Style and Characters | All-in-One LoRA | Jinx Vi Mel Caitlyn - v1.0
    NSFW
    Preview 10178078Preview 10178085Preview 10178086Preview 10178104Preview 10178102Preview 10178101Preview 10178117Preview 10178115Preview 10178127Preview 10178120Preview 10178203Preview 10178209Preview 10178225Preview 10178325Preview 10178326Preview 10178327Preview 10178351Preview 10178369Preview 10178339

    This LoRA is trained on screenshots from Arcane. It features many League of Legends characters, namely Jinx, Vi, Caitlyn, Ekko, Jayce, Mel, Sevika, Silco, Vander, and Victor. This model can recreate both the style and characters from the Arcane series. Trained on Pony Diffusion V6 XL, it possesses Pony's ability.

    Update:

    add Flux version which support 4 characters which are Jinx Vi Mel Caitlyn.

    Usage Tips:

    • Use with Pony Diffusion or a Pony-based model.

    • Use with a pony prompt.

    • Trigger words for characters (some characters are tagged but not enough data):

      • main female: jinx, vi, caitlyn, mel, sevika,

      • main male:silco, jayce, viktor, ekko, vander

      • orphan: powder, yung vi, yung ekko, mylo, claggor

      • KDA: ahri kda, akali kda, evelynn kda, kaisa kda

      • imagine dragons (not good): ben mckee, dan reynolds, daniel platzman, wayne sermon, jid

      • undergound people (not good): deckard, dustin, mek, ran, thieram, finn

      • others: ambessa medarda,elora,grayson, heimerdinger, hoskel, cassandra kiramman, howl,marcus, skyyoung

    • You can also add LoRA for mimicking the Arcane style.

    Description

    This version is trained directly with arcane screenshot on Pony Diffusion V6 XL

    LORA
    Pony

    Details

    Downloads
    3,249
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/18/2024
    Updated
    10/1/2025
    Deleted
    -
    Trigger Words:
    jinx
    vi
    caitlyn
    ekko
    jayce
    mel
    silco

    Files

    arcane_pony_v1-0.safetensors

    Mirrors

    CivitAI (1 mirrors)
    Other Platforms (TensorArt, SeaArt, etc.) (1 mirrors)

    training data.zip

    Mirrors

    CivitAI (1 mirrors)