CivArchive
    Artist: ATDAN - v1.0
    NSFW
    Preview 1141634
    Preview 1141635
    Preview 1141637
    Preview 1141696
    Preview 1141778
    Preview 1141860
    Preview 1141861
    Preview 1141818
    Preview 1141901

    ATDAN Style LoRA

    中文 | English 使用前阅读 | Read before use

    --

    仿ATDAN的作画风格的LoRA模型。

    权重建议值:0.7~1.1

    基于模型:Anything-5RE

    训练信息:共计263张原画(含裁剪图),最后一次训练迭代1038步。

    其他的一些建议:EasyNegative, badhandv4。

    LoRA model with a painting style imitating ATDAN.

    Recommended weight value: 0.7~1.1

    Based on the model: Anything-5RE

    Training information: A total of 263 paintings (including cropped images) were used for training, with the final training iteration completed at 1,038 steps.

    Other suggestions: EasyNegative, badhandv4.

    --

    任何问题,欢迎反馈,问题不提出就不会得到解决。如果你创作出了好作品,欢迎分享它。如果它无法满足你的需求,我是说,我的朋友,请不要给出一星好评。

    Any questions are welcome for feedback, as problems will not be solved without being raised. If you have created a great work, please feel free to share it. If it cannot meet your needs, my friend, please do not give a one-star rating.

    Description

    首个版本,待改进。

    FAQ

    Comments (3)

    panoramatJul 14, 2023
    CivitAI

    能问一下fitting ratio是如何评估的吗?

    Chanter
    Author
    Jul 21, 2023· 1 reaction

    不好意思最近才上线,这个的评估到头来还是具有主观性的,主要用于给使用者们一个大概的参考,希望能让大家了解到我的每个模型有哪些不足和长处,判定这个模型能不能满足自己的需求。我举其中一个例子,拿肢体拟合来说,同一套参数和种子,从训练集中抽自己看得顺眼的一张图,打开它的标签文本,用这个标签使用lora和不使用lora各出一次图,看用lora跑出来的图跟训练的原图的肢体拟合得多些还是和Checkpoint当前种子的肢体拟合得多些。不断重复上述过程,计算比率得出结论。希望能够解答你的困惑。

    panoramatJul 21, 2023

    @Chanter 感谢,我以为有自动化工具

    LORA
    SD 1.5

    Details

    Downloads
    1,178
    Platform
    CivitAI
    Platform Status
    Available
    Created
    6/14/2023
    Updated
    5/13/2026
    Deleted
    -
    Trigger Words:
    1girl

    Files

    style_ATDAN.safetensors

    Mirrors

    Available On (1 platform)

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