CivArchive
    Sanada Minako 真田美菜子 | イジラレ~復讐催眠~ Bullied ~Revenge Hypnosis~ 復仇催眠 - v1.0
    NSFW
    Preview 2801291
    Preview 739733
    Preview 739828
    Preview 740322
    Preview 740345
    Preview 740347

    Sanada Minako 真田美菜子 | イジラレ~復讐催眠~ Bullied ~Revenge Hypnosis~

    Discord : https://discord.gg/YkqSnaXqEQ

    Version 2.0 : Images : 200 From Anime


    Sponsor : https://ko-fi.com/emaisuraai


    prompt:

    Simple Pink Background,

    (Pink_swearter_jacket),(Black_pleated_skirt:1.1),
    red_bowtie, white_shirt,long_sleeves,

    <lora:Sanada_Minako_Bullied-KK77-V2:0.7>,

    brown_hair,Green_eyes,Long_Hair,Bangs,

    <lora:Oda_Non_Style-KK77-V2:0.3>,<lora:more_details:0.3>,
    1 girl, 20yo,Young female,Beautiful long legs,Beautiful body,
    Beautiful Nose,Beautiful character design, perfect eyes, perfect face,expressive eyes,perfect balance,

    looking at viewer,(Focus on her face),closed mouth, (innocent_big_eyes:1.0),(Light_Smile:0.3),

    official art,extremely detailed CG unity 8k wallpaper, perfect lighting,Colorful, Bright_Front_face_Lighting,White 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),professional photograph,

    (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,(worst quality:2), (low quality:2), (normal quality:2)


    Steps: 48, Sampler: Euler a, CFG scale: 7, Seed: -1, Size: 512x768, Model hash: 3e9211917c, Model: yesmix_v16Original, ControlNet 0: "Module: openpose_full, Model: control_v11p_sd15_openpose [cab727d4], Weight: 1, Resize Mode: Crop and Resize, Low Vram: False, Processor Res: 512, Guidance Start: 0, Guidance End: 1, Pixel Perfect: True, Control Mode: My prompt is more important", Lora hashes: "Sanada_Minako_Bullied-V01: 7fb1ad43e4c1, Oda_Non_Style-KK77-V2: de8a898832ea, more_details: 3b8aa1d351ef", TI hashes: "easynegative: c74b4e810b03, FastNegativeV2: a7465e7cc2a2, bad-artist-anime: 5f7bea88750c, bad-hands-5: aa7651be154c", Version: v1.6.0

    Time taken: 20.3 sec.

    Description

    FAQ

    Comments (8)

    lIIIllIIIlIMay 10, 2023· 1 reaction
    CivitAI

    I'm so happy to see the training image !!

    I don't know how to make LORA right now,

    I'll refer to it When I learn how to make LORA

    Thank you.

    It's interesting

    lIIIllIIIlIMay 10, 2023· 1 reaction
    CivitAI

    If there are not many image materials, is it difficult to make lora for characters of unpopular works?

    If it's an animated work, there's a lot of material to refer to, but if it's only a few images of "artist cg",

    After making a similar character through img 2 img,

    Can I use the created image as training data?

    I've never made a lora.

    I'm Newbie. T_T sorry...

    Kisaku_KK77
    Author
    May 10, 2023· 1 reaction

    First answer on website say:

    There is a specific formula for LoRA training small models.
    Each picture should be trained with at least 100 steps,
    and the total number of steps should not be less than 1500.

    That is to say, it is recommended to train more than 15 pictures.

    If it is smaller,
    use this formula to calculate the number of steps for each picture:
    "1500 /Number of pictures=Number of training steps per picture,
    for example, if I have 10 pictures for training,
    then I can train 150 steps per picture

    Kisaku_KK77
    Author
    May 10, 2023· 1 reaction

    My answer, Picture at lease "15"

    So you can (mirror "7.5" Picture) =

    7.5 X 2 = 15 Picture

    If there is ...
    Less than 7 will be difficult but not impossible

    at lease you have to get a face "right side" "left side"

    even 2 picture maybe that still can make it.

    you just get some other character "body"/"Clothes" put it in

    that also ok.

    =============
    So the most important is the face

    Kisaku_KK77
    Author
    May 10, 2023· 1 reaction

    The Third answer : Just download "Koikatsu" H-Game, That is awesome.

    Kisaku_KK77
    Author
    May 10, 2023· 1 reaction
    lIIIllIIIlIMay 10, 2023· 1 reaction

    @Kisaku_KK77 Thank you so much !!

    I was actually confused because I had no experience making lora, but it really helped me a lot.

    I downloaded the video for reference when I made it.

    It's hopeful to be able to make a lora with 15 images.

    To be honest, I can't try making LORA right now. It's before I bought a graphics card.

    anyway.. the video was really helpful.

    Thank you for your kindness.

    You are the best. \(^ヮ^)/

    I want you to be active for a long time without overwork.

    It's just a selfish mind hahaha ╰(´︶`)╯

    tinkertime612Sep 9, 2023
    CivitAI

    Any chance for the other two girls from this? Thanks!

    LORA
    SD 1.5

    Details

    Downloads
    1,640
    Platform
    CivitAI
    Platform Status
    Available
    Created
    5/9/2023
    Updated
    8/24/2026
    Deleted
    -

    Available On (1 platform)

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