CivArchive
    Kojima Ayami - Castlevania (video game) style - lolol - V1
    NSFW
    Preview 7691707
    Preview 7691704
    Preview 7691710
    Preview 7691730
    Preview 7691709
    Preview 7691739
    Preview 7691708
    Preview 7691728
    Preview 7691745
    Preview 7691740

    This LORA attempts to create images in the style of the Castlevania video games art by Kojima Ayami (Slightly NSFW).

    The games were awesome as a kid, the art even more.

    Eerie.

    Recommended weight: 0.8 ~ 1.0

    VAE: Anything / Orangemix

    ↓ !! CLICK "Show More" FOR RECOMMENDED USAGE !!

    (TAGS UPDATED FOR RECENT VERSION)

    Suggested tags:

    1girl, solo, male focus,
    *OR*
    1boy, solo, male focus,
    
    looking at viewer,
    {close-up | portrait | upper body},
    
    wavy hair,
    hair flower,
    
    #BACKGROUND tags
    flower, 
    {white flower | red flower | yellow flower | black flower | blue flower | lily \(flower\)},
    rose, {white rose | yellow rose | red rose},
    
    plants, vine, thorns, leaf, petals, branches,
    candles, castle,
    moon, night,

    Optional tags:

    eyelashes,
    pale skin,
    
    pointy ears, vampire, 
    demon girl, monster girl, horns,
    
    wings, 
    bat wings, demon wings,
    angel, feathered wings, angel wings, head wings,
    black wings,
    
    {bat \(animal\) | dragon | snake | butterfly, bug},
    
    blood,

    Negative prompt:

    (EasyNegative:0.8), (worst quality, low quality:1.2), 
    (blurry, bokeh, depth of field, watermark, username, artist name, signature, text, monochrome, greyscale)

    Notes:

    Some models have a strong bias for girls and can't generate men properly.

    Adding "male focus" with the girl tags is to make it easier for the other background tags to pop up as most of the dataset consist of men. Use a "breast size" tag like "medium breasts" if you wish.

    "painting (medium)" is the exact tag in the training, but "painting \(medium\)" is how it's typed with the Autocomplete extension with Danbooru tag. I think this doesn't work because of the model I used for training. It might generate "physical paintings" in the background.

    Click on the 🔔 or Follow me if you want to receive a notification when I update or release new models.

    Check out my profile.

    I have other models that might also pique your interest :)

    I would love to see what you've generated with my LORAs.

    Don't be shy to post below in the gallery or leave a Like.

    Every little contributions motivate me to create more content.

    Enjoy! :>

    If the original artist does not approve of this model and wish it be removed, I will take it down.

    Description

    FAQ

    LORA
    SD 1.5

    Details

    Downloads
    144
    Platform
    CivitAI
    Platform Status
    Deleted
    Created
    4/24/2025
    Updated
    5/3/2026
    Deleted
    4/24/2025

    Files

    ayamiKojimaV1LOL.safetensors

    Mirrors

    CivitAI (1 mirrors)
    TensorFiles (1 mirrors)