CivArchive
    VtuberMaker LoRA - v1.0
    NSFW
    Preview 543845
    Preview 543843
    Preview 543839
    Preview 543840

    ATTENTION THIS IS IMPORTANT!!!! DUE TO HOW THE FILES WERE STRUCTURED MAKE SURE YOU PUT "FULL BODY" IN THE PROMPT FOR THE BEST RESULTS!


    THIS MODEL WAS TRAINED ON MEINAMIX V9!

    Example prompt: vtubermodel of 1girl , dark brown hair ,orange eyes , fulffy weasel ears , high quality , extra detailed , rendered, (green hoodie:1.3), white background, full body, smiling, semi realism <lora:VtuberMaker:0.7>

    Neg prompt : (worst quality, low quality:1.4), border, frame, (large breasts:1.4), watermark, signature bad eyes , bad hands, asymmetrical, complex background , black background, extra fingers


    this model was trained with the meinamix v9 model

    Description

    Sorry everyone for all the trouble i may have caused with the model being a ckpt rather than a lora!! im new at this ... this time its a LoRA

    FAQ

    Comments (13)

    ThePotatoApr 20, 2023
    CivitAI

    Love the preview pics, would love to see more example pics too. I noticed it's tagged as LoRA, should this be tagged as a checkpoint?

    HorridWitch
    Author
    Apr 20, 2023· 1 reaction

    hey i updated the model im new at this and yeah it was a checkpoint accidentally oops .... well now its a lora!

    aGolemApr 20, 2023

    @HorridWeasel are you sure, the file size is way more in line with a LoRA?

    HorridWitch
    Author
    Apr 20, 2023· 1 reaction

    @Cjb what youre seeing now is the revamp! i had ckpt files in there by accident but everything is now fixed i personally recommend v2.0 as it has more stylization flexibility ! enjoy :)

    126275Apr 20, 2023· 1 reaction

    @HorridWeasel friendly reminder that generally you'd only want to train on the nai model/ anime-full-pruned. You want a good database that is pruned towards anime, got a lot of concepts, scenery data and styles, while not overfitting your lora. Training on sd 1.5 is just..

    notice how your first pic has lora strength 0.3 meaning it's barely activated, while your second is already overcooked at 0.7. You can aim towards 0.8-1 strength, cfg 7, Karras++ sampler

    HorridWitch
    Author
    Apr 20, 2023

    @cyan8 heya thanks for the suggestion! ill make sure to train v3 the way you suggested ^^

    HorridWitch
    Author
    Apr 20, 2023· 1 reaction

    @cyan8 i tried your suggestions and they didnt work i just personally believe different loras require different offsets to work , have a nice day ^^

    HorridWitch
    Author
    Apr 20, 2023· 1 reaction

    @cyan8 if u have anymore suggestions im open to hearing them im using kohaya gui!

    ThePotatoApr 22, 2023

    @HorridWeasel Thanks for sharing, can't wait to try your LoRA out!

    HorridWitch
    Author
    Apr 22, 2023

    @ThePotato one tip if youre noticing an overbake try not using the keyword!

    iBurnApr 20, 2023
    CivitAI

    Hey! Was it trained only on female avatars? Is it possible to generate male avatar with that lora?

    HorridWitch
    Author
    Apr 20, 2023· 1 reaction

    heya yes male models were trained too

    BerdnikovMaxJul 1, 2023
    CivitAI

    Looks interesting, but can it somehow be used to create a working model?

    LORA
    Other

    Details

    Downloads
    272
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/20/2023
    Updated
    8/22/2026
    Deleted
    -
    Trigger Words:
    vtubermodel

    Files

    VtuberMaker.safetensors

    Mirrors

    CivitAI (1 mirrors)