CivArchive
    Mixed ink style-混合水墨风格 - v3.0
    NSFW
    Preview 108734990
    Preview 108734977
    Preview 108734981
    Preview 108734997
    Preview 108734987
    Preview 108734986
    Preview 108734989
    Preview 108734995
    Preview 108736142
    Preview 108734991
    Preview 108734965
    Preview 108735000
    Preview 108734966
    Preview 108734988
    Preview 108734978
    Preview 108734972
    Preview 108734996

    CKRF V1

    基于ChenkinNoob-XL Rectified-Flow 0.3 (https://civarchive.com/models/2363696/chenkinnoob-xl-rectified-flow)版本训练并融合,融合后画风更偏向宣纸水墨效果。

    CKRF V1

    Trained and fused based on the ChenkinNoob-XL Rectified-Flow 0.3 version (https://civarchive.com/models/2363696/chenkinnoob-xl-rectified-flow), the post-fusion style leans more toward a Xuan paper ink painting effect.

    V3.0

    使用新参数训练Lora并融合,调整了融合比例,增强生成稳定性,避免2.0版本中大量出现的肢体错乱和手指乱的问题,缺点是整体光影偏暗,脸部阴影太重,2.0的光影更好些,有对风格特化需求的使用者可以同时继续使用2.0。

    V3.0

    Trained LoRA with new parameters and fused them, adjusting the fusion ratio to enhance generation stability and mitigate the limb disarray and finger distortion issues prevalent in version 2.0. The drawback is the overall darker lighting and heavier facial shadows compared to version 2.0, which offers better lighting. Users with specific style preferences can continue using version 2.0 alongside this one.

    V2.0

    重新用Zero Terminal SNR和alpha1参数训练了Lora并融合,同时调整了融合比例。现在的笔触更细腻,身体比例和对暗场景的适应性更好。缺点是对close-up的响应不好,容易画成全身像和远视角。

    V2.0

    Trained and merged Lora with new parameters like Zero Terminal SNR and alpha 1. Fusion proportions were adjusted too. Now the strokes are now more delicate, and body proportions and adaptability to dark scenes are better, but the disadvantage is that the response to close-up scene prompt is not good enough, making it easy to draw them as long shot scene.

    导言

    这是一个用于生成水墨混合风格图像的Lycoris,经过360张挑选的写意画、工笔画以及中国风数字绘画内容训练,依照个人审美融合而成,训练基底模型是NOOB V-PRED 1.0。

    优点

    • 通过调整chinese ink style、traditional media、color ink \(medium\)、ink \(medium\)等关键词权重,可以产出不同类型的半写意风格。

    缺点

    • 模型在绘画不同元素时表现的风格有差异,总体表现为一种比较精细的写意风格,但不稳定。

    • 肢体扭曲有时会比较严重,手脚偏大。

    使用方法

    推荐权重为1,根据示例内不同关键词,或其他有关于水墨画风的关键词进行调整,获得需要的产出。

    Introduction

    This is a Lycoris used to generate Chinese ink mixed style images. Trained with 360 selected freehand paintings, meticulous brushwork paintings, and Chinese style digital painting content and merged according to personal aesthetics. The training base model is NOOB V-PRED 1.0.

    Advantage

    • By adjusting the weights of keywords such as chinese ink style, traditional media, color ink \ (medium \), ink \ (medium \), etc., you can have various semi-freehand style.

    Shortcoming

    • The style of the model varies when painting different elements, and overall it shows a relatively fine freehand style, but it is unstable.

    • The limbs maybe severely twisted and the hands and feet are slightly larger.

    Usage

    The recommendation weight is 1. Adjust according to different keywords in the example or other keywords related to ink painting style to obtain the desired output.

    Description

    FAQ

    Comments (8)

    BIG_ANov 3, 2025· 2 reactions
    CivitAI

    画古风NSFW非常的非常的棒!极力推荐!

    LizzaSkyNov 3, 2025
    CivitAI

    豪康!

    sotynnkNov 4, 2025
    CivitAI

    大佬能做个ill版本么,vpre不兼容的lora太多了

    kokoDec 6, 2025
    CivitAI

    好看,在我的审美xp上

    zuoqiuyueDec 8, 2025
    CivitAI

    大佬拜托了,有时间的话能否做个ill版本?各种尝试后实在还原不出来例图的风格,实在没招了🙏

    YF30
    Author
    Dec 10, 2025

    我个人建议是直接用NOOB V-PRED 1.0,illu0.1这个原分支作为底模底子太差,之前训了几版都存在严重缺陷,如果你用的是某种风格化特调的illu那这边也不太可能一个一个适配。

    zuoqiuyueDec 11, 2025

    @YF30 好嘞,感谢大佬,我去找找noob的试试

    darkhands1980319Jan 8, 2026
    CivitAI

    简直好到飞起啊,兄弟,不,我的英雄

    LoCon
    NoobAI
    by YF30

    Details

    Downloads
    259
    Platform
    CivitAI
    Platform Status
    Available
    Created
    11/3/2025
    Updated
    5/1/2026
    Deleted
    -

    Files

    Mixed Ink V3.safetensors

    Mirrors

    Huggingface (1 mirrors)
    CivitAI (1 mirrors)
    Other Platforms (TensorArt, SeaArt, etc.) (2 mirrors)

    Available On (2 platforms)

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