CivArchive
    Avatar Wan Style (from The Legend of Korra) LoRA - offset
    Preview 1065590Preview 1065584Preview 1065591Preview 1065589Preview 1065581Preview 1065586Preview 1065583Preview 1065587Preview 1065582Preview 1065592Preview 1065585Preview 1065594

    Avatar Wan style (from The Legend of Korra) LoRA

    Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee


    I always liked this part of season 2. This is made with screenshots from episode 7 and 8, which tell the Avatar Wan story. I wasn't sure about this because there are no female characters in that flashback for some reason, and it's 90% Avatar Wan interacting with odd creatures and minor characters. However it seems it turned out good.

    Should be used at around 1 weight with AnyLoRA ckpt and with the trigger avatar wan.

    Keep in mind this is not a character LoRA, so it can't really reproduce characters from the show, but it can get pretty close with accurate prompting. This is very much intended for you to create your own characters. It should work on basically every model, but it's accurate only on AnyLoRA as far as I've seen, as that one tends to be more "style neutral".


    How to use LoRA's in auto1111:

    • Update webui (use git pull like here or redownload it)

    • Copy the file to stable-diffusion-webui/models/lora

    • Select your LoRA like in this video

    • Make sure to change the weight (by default it's :1 which is usually too high)

    Description

    LORA
    SD 1.5

    Details

    Downloads
    664
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/7/2023
    Updated
    11/12/2025
    Deleted
    -
    Trigger Words:
    avatar wan

    Files

    avatar_wan_offset.safetensors

    Mirrors