CivArchive
    Mai Kannazuki (Hentai: G-Taste) NSFW - v1.0
    NSFW
    Preview 6723733
    Preview 6723740
    Preview 6723742
    Preview 6723743
    Preview 6723744

    And finally dominatrix (or sub?) from G-taste - Mai Kannazuki!

    0.9 - 1 strength of Lora is the best radius (For combining with other LoRAs, I recommend reducing weight).

    Some necessary tags for better experience:

    Main tags:

    MaiKannazuki, 1girl, mature female, brown hair, (single sidelock:1.2), brown eyes, earrings, red lips, glasses,
    red blazer, bowtie, puffy long sleeves, red miniskirt, grey pantyhose, red high heels

    Also you can use other tokens for her body and clothes and see what I used in preview!

    Main advices for all LoRAs:

    I recommend you next prompt order for NAI-based mixes (you can see it in my preview arts):

    1. (high quality:1.2) ("masterpiece" and "8K" kill some concepts. Be careful if you try some complex clothes or concepts.)

      Also put lighting / shadows, intricate details if you need some extra effects. Sometimes it doesn't work if style of anime or game was baked in LoRA or anime checkpoint mixes lost some concepts which exists in vanilla SD 1.5.

    2. Activation word (from lora civitai page, usually character name). Describe with danbooru tags character activity, expressions, camera position.

    3. Hair details, face details, jewelry, crowns, hats, etc.

    4. Clothes and shoes; Or nude.

    5. Body details (large breasts, cleavage). Genitals if you want to generate it.

    6. Background.

    Advices for upscaling / fixing:

    • use highres.fix (If you are sure that your prompt is easy for SD); I prefer x4_Fatal_anime_500000_G, foolhardy_remacri with 2x upscale. 0.36 denoising and 15-20 Hires fix is enough.

    • Do not use "latent" upscaler because it works worse with denoisning < 0.6 but you don't want so high denoising stength because it changes your image instead of adding details.

    • use extention after detailer for better faces or img2img inpaint (only mask) for faces or eyes with 0.25 denoising.

    • use SD Upscale / Ultimate SD Upscale script in img2img after highres fix if you want 4K or more resolution with adding details (don't use Extras for it).

    • Use Photoshop / Photopea extension for fixing hands, textures and other.

    I will be glad to receive feedback from you and a demonstration of your art with my LoRA!

    https://tensor.art/u/604375505701151021

    Description

    FAQ

    Comments (13)

    DennyDan84Feb 17, 2024· 1 reaction
    CivitAI

    Great lora- thanks!!

    Enigmata
    Author
    Feb 17, 2024

    I'm glad you liked it and would look at your generated pictures :3

    MILF__hunterApr 10, 2024· 1 reaction
    CivitAI

    can you please make Touka Fubuki from G Taste?

    Enigmata
    Author
    Apr 10, 2024

    Maybe in future. For now I have other plans :3

    MILF__hunterApr 11, 2024· 1 reaction

    @Enigmata here is the link for training data, hope you will make it, https://www.mediafire.com/file/brmdk2gq29e3c47/Touka_Fubuki.zip/file

    Enigmata
    Author
    Apr 11, 2024

    @MILF__hunter not bad

    Hal171Apr 20, 2025· 1 reaction
    CivitAI

    Please any update for Mai on Noobai epsilon?

    Enigmata
    Author
    Apr 20, 2025· 1 reaction

    I can make her for NoobAI and maids too.
    I didn't make these girls on Pony because I thought they are not popular.

    Hal171Apr 22, 2025· 1 reaction

    @Enigmata The NoobAI version will be amazing. Sadly G-Taste is not well known but it retain amazing vibe, like the Golden Boys, those retro anime are the Golden age.

    Enigmata
    Author
    Apr 23, 2025· 1 reaction

    @Hal171 I'll try to find time. Actually I am planning to accelerate transferring loras on NoobAI what means less arts but more loras which I did for previous models.

    Hal171Sep 6, 2025

    @Enigmata Still waiting patiently for Mai G-taste update 😆

    Enigmata
    Author
    Sep 6, 2025· 1 reaction

    @Hal171 oh I am making Shion girls right now :/ I try to find time for this girl too. Sadly I need to make her from zero because it's SD1.5 lora and I have 512x512 dataset only. So I need to crop and resize everything again and tag it again.

    Hal171Sep 8, 2025· 1 reaction

    @Enigmata  your Lora is the best 👍

    LORA
    SD 1.5

    Details

    Downloads
    742
    Platform
    CivitAI
    Platform Status
    Available
    Created
    2/16/2024
    Updated
    5/13/2026
    Deleted
    -
    Trigger Words:
    MaiKannazuki
    1girl, mature female, brown hair, (single sidelock:1.2), brown eyes, earrings, red lips, glasses
    red blazer, bowtie, puffy long sleeves, red miniskirt, grey pantyhose, red high heels
    panties under pantyhose

    Files

    MaiKannazuki.safetensors

    Mirrors

    TensorFiles (1 mirrors)