CivArchive
    H0rr0r - v1.0
    NSFW
    Preview 117607519
    Preview 117607515
    Preview 117607520
    Preview 117607514
    Preview 117607511
    Preview 117607521
    Preview 117607523
    Preview 117607513
    Preview 117607522
    Preview 117607510
    Preview 117607517
    Preview 117607518

    This lora was trained on some horror movies. I don't really know how good it is, I think 3000 samples may not have been enough, or it might have slight overfit.

    For best results use h0rr0r, and then date of the movie, like 1982, 2020 or 2005, etc... then directed by James Cameron, or whoever you want, and then the prompt. You don't have to use year and director, it's just a trend I saw in the tagging and seems to give some extra flavor.

    Like I said, there may be overfit, so if your prompt is not very long I suggest a lower power than 1. Longer prompts seem to yield better results.

    Description

    FAQ

    Comments (1)

    adondlin255Jan 17, 2026
    CivitAI

    I don't know how to use the one style, yet I will pick this one up in case. The look is rafter nifty looking. I wonder if an Illustrious version will be made one day.

    I wonder if 3,000 pictures is normal for making such loras. Most loras I make tend to be between 15 to 150 pictures.

    LORA
    ZImageTurbo

    Details

    Downloads
    214
    Platform
    CivitAI
    Platform Status
    Available
    Created
    1/15/2026
    Updated
    7/6/2026
    Deleted
    -
    Trigger Words:
    h0rr0r

    Files

    z_Image_H0rr0r.safetensors

    Mirrors

    CivitAI (1 mirrors)