CivArchive
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined
    Preview undefined

    If you want to use more my checkpoint online generation, please visit here.

    https://tensor.art/u/762555264535746522


    V15

    关于例图, 我使用了1024x1360的大小,都是直接输出没有经过AD跟高修.

    For the example images

    V15, I used 1024x1360,

    generated directly without AD or hires fix.

    调整了数据,不在需要正负面质量词.

    The data has been adjusted, and positive/negative quality tags are no needed.

    • Steps: 30

    • CFG scale: 7

    • Sampler: Euler a


    V14

    关于例图, 我使用了1024x1360的大小,都是直接输出没有经过AD跟高修.

    For the example images

    V14, I used 1024x1360,

    generated directly without AD or hires fix.

    重新调整了整体色彩,构图,背景.

    The overall color, composition, and background have been re-adjusted.

    • Steps: 30

    • CFG scale: 7

    • Sampler: Euler a

    Positive Prompt

    score_9, score_8_up, score_7_up,

    Negative Prompt

    score_6,score_5,score_4,, worst quality, low quality, bad anatomy, bad hands, missing fingers, fewer digits, source_furry, sourcwe_pony, source_cartoon,3d, blurry,


    V13

    v13主要是进行了色调跟数据调整,对脸部基本没有太大调整.

    Version 13 mainly focuses on color tone and data adjustments, with minimal changes to the face.

    把cfg稳定在了7,方便后面版本的调整.

    The CFG has been stabilized at 7 to facilitate adjustments in future versions.

    • Steps: 30

    • CFG scale: 7

    • Sampler: Euler a

    Positive Prompt

    score_9, score_8_up, score_7_up,source_real,real skin,
    BREAK

    Negative Prompt

    worst quality,low quality,
    source_furry, source_pony, source_cartoon,2d,
    ,bad anatomy, bad hands,blurry,3d,

    __________________________________________________________________________________________________

    • Steps: 30

    • CFG scale: 5~7

    • Sampler: Euler a

    • Steps: 12

    • CFG scale: 1

    • Sampler: Euler a

    two versions same Prompt

    Positive Prompt

    score_9, score_8_up, score_7_up,source_real,real skin,
    BREAK

    Negative Prompt

    worst quality,low quality,
    worst detail,low detail,
    source_furry, source_pony, source_cartoon,2d,
    ,bad anatomy, bad hands, text, error, missing fingers, (extra digit:1.4), fewer digits, cropped, bad artist, outlines,jpeg artifacts, signature, watermark, username, blurry,3d,

    _______________________________________________________________________

    V11

    • Steps: 30

    • CFG scale: 5~7

    • Sampler: Euler a

    • ADetailer face_yolov8s.pt use (ADetailer sampler: DPM++ 2M, ADetailer scheduler: Karras )

    Positive Prompt

    score_9, score_8_up, score_7_up,source_real,real skin,
    BREAK

    Negative Prompt

    worst quality,low quality,
    worst detail,low detail,
    source_furry, source_pony, source_cartoon,2d,
    ,bad anatomy, bad hands, text, error, missing fingers, (extra digit:1.4), fewer digits, cropped, bad artist, outlines,jpeg artifacts, signature, watermark, username, blurry,3d,

    __________________________________________________________________________________________________

    V10

    • Steps: 30

    • CFG scale: 3.5~7

    • Sampler: Euler a

    • ADetailer face_yolov8n/s.pt use (ADetailer sampler: DPM++ 2M, ADetailer scheduler: Karras )

    Positive Prompt

    score_9, score_8_up, score_7_up,source_real,realistic,photorealistic, 
    BREAK

    Negative Prompt

    worst quality,low quality,
    worst detail,low detail,
    source_furry, source_pony, source_cartoon,2d,
    ,bad anatomy, bad hands, text, error, missing fingers, (extra digit:1.4), fewer digits, cropped, bad artist, outlines,jpeg artifacts, signature, watermark, username, blurry,3d,

    __________________________________________________________________________________________________

    V2toV9

    Recommended Setting

    • Steps: 30-50

    • CFG scale: 7

    • Sampler: Euler a

    • Sampler: Euler a ADetailer face_yolov8n/s.pt use more better

    Positive Prompt

    score_9, score_8_up, score_7_up,

    Negative Prompt

    score_6,score_5,score_4, worst quality, low quality, bad anatomy, bad hands, missing fingers, fewer digits, source_furry, source_pony, source_cartoon,3d, blurry,

    ________________________________________________________________________________________________

    v1

    Recommended Setting

    • Steps: 30

    • CFG scale: 3.5-7

    • Sampler: Euler a or DPM++ 2M Karras

    • ADetailer face_yolov8n/s.pt use more better

    Positive Prompt

    score_9, score_8_up, score_7_up,

    Negative Prompt

    score_6,score_5,score_4,bad anatomy, bad hands, missing fingers, fewer digits, source_furry, source_pony, source_cartoon,3d, blurry, 

    Description

    FAQ

    Comments (22)

    yzj67203859251Oct 20, 2024· 8 reactions
    CivitAI

    细节太低了

    RaininosiOct 27, 2024· 7 reactions
    CivitAI

    I have huge problem generating an outdoor winter landscape. Instead I get a boring background, even though all of this is in negative prompt. I'm forced to use Lora. Even though images are great, it's harder to make this model to follow prompt (problems with ears, eye colors, emotion)

    EoS_StahliOct 28, 2024· 2 reactions

    You can try to switcheroo pose prompts or scenery to force the render to start from 0, try to use ADetailer for fixing stuff like face features/clothes.

    snoopytl2009600Oct 28, 2024· 7 reactions
    CivitAI

    大佬,你的模型都很棒,一直是国内的顶级水平,啥时候出flux的模型啊,期待啊,flux的听话程度,画面的细腻度,以及出来的效果都是当今扛把子的级别,期待大佬的flux模型!!!!

    WAI0731
    Author
    Oct 28, 2024· 1 reaction

    主要是flux的权限问题,暂时没啥想法.等反蒸馏成熟了再看了.

    snoopytl2009600Oct 29, 2024· 1 reaction

    大佬,能不能一上来就整专业名词,啥是反蒸馏啊,不管咋说,支持你!!等待你!!

    WAI0731
    Author
    Oct 29, 2024· 1 reaction

    @snoopytl2009600 说简单点就是,现在的flux官方发布的模型训练效果差,需要等有人修改之后才好大规模训练.

    boysshareNov 3, 2024· 1 reaction

    大佬的手部表现很棒,肢体很好!

    snoopytl2009600Nov 26, 2024· 1 reaction

    大佬我看其他很多人都已经发布了flux的模型了,不知现在是否达到你炼化的要求,我一直翘首期盼大佬你的flux模型,我相信和我一样期待你flux模型的大有人在,其他人都能行,能不能让我们这些人满足一下,说句不好听的,SDXL已是昨日黄花了,就不要再花心思搞了,现在铺天盖地都是flux,快快投入flux的怀抱吧

    WAI0731
    Author
    Nov 26, 2024· 1 reaction

    @snoopytl2009600 因为不好练啊,单纯改个脸型 你用lora就行了,要加瑟瑟不好弄啊,还是那句话蒸馏大模型不好训练本体。成本太高了

    snoopytl2009600Nov 27, 2024· 1 reaction

    @WAI0731 咱不弄色色,就是纯看中你炼的正常模型比较符合亚洲审美,美学分值高,既然大佬暂时没计划,那只能看看别家了

    WAI0731
    Author
    Nov 27, 2024· 1 reaction

    @snoopytl2009600 没办法 我可掏不出几块H100去干那个蒸馏模型 钱包遭不住。

    YSCyscDec 11, 2024· 1 reaction

    @WAI0731 这个参见Pony模型的作者,官方原版的SDXL模型搞涩涩不好搞,那么作者就自己炼,准备大量的数据集(两百万张图片)在非常强大的硬件上训练花了3个月。

    官方原版没有的概念,需要自己训练新概念,或者强化概念。例如pony特有的score_x 是作者自己训练的概念。

    当然,这是个庞大的工程。。。。

    https://civitai.com/articles/4248

    ronaldmikhailp236Nov 11, 2024· 21 reactions
    CivitAI

    Makes everyone look Asian. 🤨

    juliengobetzky316Nov 14, 2024· 9 reactions

    no shit dude it's an asian styled checkpoint

    ryoheiNov 15, 2024· 7 reactions

    well yeah it has CN in the title

    879500Jan 2, 2025

    Ok and? This is good. Way too many western woman models.

    OverassNov 15, 2024· 5 reactions
    CivitAI

    兄弟,你的模型不错,但是我们说画龙点睛,妹妹的眼睛总感觉不对焦,右眼感觉不是很和谐

    460672106622Nov 24, 2024· 5 reactions
    CivitAI

    大佬能做一个网红脸的检查点吗

    zixi_114514Dec 10, 2024· 5 reactions
    CivitAI

    大佬,这模型用啥VAE比较好啊

    WAI0731
    Author
    Dec 10, 2024· 1 reaction

    不用,本身就有

    houzidehuangyanDec 12, 2024· 6 reactions
    CivitAI

    好看

    Checkpoint
    Pony

    Details

    Downloads
    12,690
    Platform
    CivitAI
    Platform Status
    Available
    Created
    10/17/2024
    Updated
    5/14/2026
    Deleted
    -

    Available On (1 platform)

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