CivArchive
    Chloe クロエ | Kuroinu 黒獣 - v1.0
    NSFW
    Preview 515228
    Preview 515225

    Chloe クロエ | Kuroinu 黒獣

    https://www.pixiv.net/users/86166786

    Discord: Picture Share (Uncensorship) https://discord.gg/YkqSnaXqEQ

    Version 2 : Images : 200 From Anime

    prompt:

    (Night:1.7), Castle, Brick wall,

    Standing at attention,dynamic pose, crossed arms,

    blue outfit,blue Jacket, long black coat,thighhighs,blue armor, cleavage cutout,

    <lora:Chloe_Kuroinu-KK77-V1:0.7>,
    <lora:Mariana_Luciano_NON_VIRGIN-KK77-V1:0.2>,<lora:more_details:0.1>,
    long pointy ears, dark elf, dark skin,

    blonde hair,long hair,Side ponytail, red eyes,

    1 girl, 20yo,Young female,Beautiful Finger,Beautiful long legs,Beautiful body,Beautiful Nose,Beautiful character design, perfect eyes, perfect face,expressive eyes,

    looking at viewer,(Upper_body),(Focus on her face),

    official art,extremely detailed CG unity 8k wallpaper, perfect lighting,Colorful, Bright_Front_face_Lighting,shiny skin,
    (masterpiece:1.0),(best_quality:1.0), ultra high res,4K,ultra-detailed,
    photography, 8K, HDR, highres, absurdres:1.2, Kodak portra 400, film grain, blurry background, bokeh:1.2, lens flare, (vibrant_color:1.2)

    (Beautiful,large_Breasts:1.4), (beautiful_face:1.5),(narrow_waist),

    Negative prompt:

    EasyNegative, FastNegativeV2, bad-artist-anime, bad-hands-5, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry, out of focus, censorship, Missing vagina, Blurry faces, Blank faces, bad face, Ugly, extra ear, amputee, missing hands, missing arms, missing legs, Extra fingers, 6 fingers, Extra feet, Missing nipples, ghost, futanari, Extra legs, Extra hands, panties,pants, (painting by bad-artist-anime:0.9), (painting by bad-artist:0.9), text, error, blurry, jpeg artifacts, cropped, normal quality, artist name, (worst quality, low quality:1.4),twisted_hands,fused_fingers,Face Shadow,NSFW,


    Steps: 48, Sampler: Euler a, CFG scale: 7, Seed: -1, Size: 512x768,

    Model hash: 3e9211917c, Model: yesmix_v16Original, Denoising strength: 0.5,

    Hires upscale: 2, Hires steps: 18, Hires upscaler: R-ESRGAN 4x+ Anime6B,

    Lora hashes: "Chloe_Kuroinu-KK77-V1: 0e5d8ce817f7,

    Mariana_Luciano_NON_VIRGIN-KK77-V1: 55dda9129501,

    more_details: 3b8aa1d351ef",

    TI hashes: "easynegative: c74b4e810b03, FastNegativeV2: a7465e7cc2a2,

    bad-artist-anime: 5f7bea88750c, bad-hands-5: aa7651be154c", Version: v1.5.0

    Description

    FAQ

    Comments (7)

    ShenroApr 17, 2023· 7 reactions
    CivitAI

    my fav choco elf

    oppaimakerApr 17, 2023· 4 reactions
    CivitAI

    fantastic,Looking forward to other characters in this series

    ZelinezApr 20, 2023· 5 reactions
    CivitAI

    Anyone struggling to get good results with this, I have found that using the tag "solo" in positive prompt (which is very common) completely ruins the model. make sure to not use that.
    Also bad prompt v2 seems to also have a negative effect here for some reason, seems like some of the tags this model uses are just a bit inconsistent with most models, but if you do these things you should be fine.

    Kisaku_KK77
    Author
    Apr 20, 2023

    some bad prompt is a "embeddings"

    youtu.be / W3BFU4oytb0

    Kisaku_KK77
    Author
    Apr 20, 2023

    Thank you

    ZelinezApr 20, 2023· 1 reaction

    @Kisaku_KK77 I know :) I do usually use this, but with this Lora it does not seem to have a positive effect

    ZelinezApr 20, 2023· 1 reaction

    @Kisaku_KK77 Also here's a tip in case you want to go back and improve this Lora substantially.

    Right now it very clearly prefers it when chloe is at a medium distance to the viewers (like in the leg spread pic i posted). If she is closer or further the lora struggles a bit to really hit the face details. I would bet that you didn't have many pictures of her from far away and full sized portraits in the training set. To make a well blananced lora that can do all distances, and poses, I have found you want a split of ~ 2/10 portraits, 3/10 upper body, 5/10 full body pictures. hope this helps, and thanks for sharing ;)

    LORA
    SD 1.5

    Details

    Downloads
    1,955
    Platform
    CivitAI
    Platform Status
    Available
    Created
    4/17/2023
    Updated
    5/13/2026
    Deleted
    -

    Available On (1 platform)

    Same model published on other platforms. May have additional downloads or version variants.