Tutu’s sexy uniform (Dimension Radio x Latex Clothing PU Nun Uniform)/图图的情趣制服（次元电台X乳胶衣PU修女服）

zhaotutuzhaotutu
274
1.4K
性感femaleclothes女人服装girls
v2.0
model-image-0
model-image-1
model-image-2
model-image-3
model-image-4
model-image-5
model-image-6
model-image-7
model-image-8
model-image-9
model-image-10
model-image-11
model-image-12
model-image-13
model-image-14
model-image-15
model-image-16
model-image-17

详情

下载文件 (1)

模型描述

Created with Tutu AI Workflow

Trained with Tutu Trainer. Tagged with Tutu Annotator.

This LoRA is part of my Tutu AI workflow. Tutu Trainer is used for LoRA training, model resource management, parameter presets, and training checks. Tutu Annotator is used for dataset annotation, prompt reverse engineering, English-friendly tags, and cleaner searchable captions.

For a latex / PU cosplay clothing LoRA, the model needs to learn the outfit structure, glossy material, cross necklace, habit, bodysuit, gloves, and thigh boots without dragging the whole image away. Clean training and tagging make the outfit easier to restore and easier to search.

Tutu AI Workflow - Tutu Trainer and Tutu Annotator

Tutu's Adult Costume LoRA: Latex / PU Nun-Inspired Uniform

This is a clothing LoRA for a Dimension Radio x Latex Clothing PU nun-inspired cosplay uniform. It focuses on a glossy black latex / PU bodysuit look, cross necklace, habit, latex gloves, and thigh boots.

A friend sent me this outfit and asked whether I wanted to try it because it looked good. I originally planned to buy it and shoot a video, but then I got lazy and did not make the video, so I made a LoRA instead. Sometimes the production path is very serious, and the reason it starts is very ordinary.

  • Type: latex / PU nun-inspired adult cosplay uniform
  • Base model: SD 1.5
  • Current version: v2.0
  • Main trigger group: tutututu, nun, cross necklace, latex bodysuit, shiny clothes, skin tight, habit, latex gloves, black bodysuit, thigh boots
  • Recommended weight: 0.4 to 0.9, start around 0.6
  • Recommended CLIP skip: 2
  • CFG Scale: start around 7

What this model is good at

  • Restoring the glossy black latex / PU clothing material.
  • Keeping the nun-inspired outfit structure: habit, cross necklace, bodysuit, gloves, and thigh boots.
  • Working well with other LoRAs when the weight is not too high.
  • Using a relatively low weight; around 0.6 is often enough.
  • Adapting well to many base models, especially 2.5D and anime-style models.

Production notes

I keep insisting on high-quality LoRA production. This model was also made with real-shot material and a differential extraction workflow. Recently I made many optimizations to the overall algorithm and production method, and this model benefits from that.

In simple terms, the difference extraction workflow tries to remove unrelated contamination from the source material and keep the useful target elements: outfit structure, material, shine, and accessories. That is why this LoRA can work well together with other LoRAs and does not need an extreme weight.

The more technical side includes automated model exploration and difference analysis between LoRA weights. I do not want to turn the page into a math note, but the practical result is what matters: better restoration, cleaner target extraction, and lower pollution.

Recommended settings

  • Make sure the LoRA is loaded correctly.
  • Recommended CLIP skip / CLIP stop layers: 2.
  • Recommended weight: 0.4 to 0.9. Start around 0.6.
  • Start CFG Scale around 7.
  • Do not add too many negative prompts, or the LoRA effect may be weakened.
  • The model is friendly to many base models, especially 2.5D and anime-style models. Adjust parameters for different bases.

Prompt keywords

Main trigger group:

tutututu, nun, cross necklace, latex bodysuit, shiny clothes, skin tight, habit, latex gloves, black bodysuit, thigh boots

Compact variants that may also help:

latexgloves, blackbodysuit, thighboots

Useful prompt phrases:

  • latex bodysuit
  • shiny clothes
  • black bodysuit
  • skin tight
  • latex gloves
  • thigh boots
  • cross necklace
  • habit
  • adult cosplay outfit
  • fashion portrait

If the outfit is incomplete, use the full trigger group first. If the latex shine is weak, strengthen latex bodysuit, shiny clothes, and black bodysuit. If the outfit starts affecting the whole image, lower the LoRA weight.

Why I made this LoRA

There are many similar clothing LoRAs, but many of them are not close enough to real clothing. Some popular costume directions are missing, and many LoRAs affect the character and the whole image too much, making them inconvenient to use.

So I continue making a series of clothing LoRAs with a more practical workflow. For convenience, I keep the trigger style unified: tutututu plus the target outfit elements.

FAQ

Why is 0.6 often enough?

This model is already focused on the target outfit. If the prompt is complete, around 0.6 can give a good effect without overpowering the image.

Why is the outfit incomplete?

Use the full trigger group. The model needs several elements at the same time: nun, cross necklace, latex bodysuit, habit, latex gloves, and thigh boots.

Why can I not get exactly the same image as the examples?

Different base models, LoRAs, plugins, samplers, and settings will produce different results. Please use the examples as a direction and create your own best version.

Responsible use

  • Use this LoRA only for appropriate adult cosplay / fashion contexts.
  • Do not use this model for underage, school-age, or ambiguous-age sexualized content.
  • You are fully responsible for any creative work made with this model.
  • Do not use this model to create or share illegal, harmful, malicious, defamatory, fraudulent, or political content.
  • If you use this model commercially, please inform me. Thank you.

中文说明

这是图图情趣制服系列里的 次元电台 X 乳胶衣 PU 修女服 LoRA，主要用于成人 cosplay / 时装风格创作。它重点还原黑色乳胶 / PU 亮面紧身服、十字项链、头巾、乳胶手套、黑色连体衣和长靴。

这个模型的来源还挺日常：朋友发来说这个挺好看的，要不要试一下。我本来是打算买来拍视频的，结果临时犯懒没拍成，就做了个 LoRA。训练过程是认真的，但起因确实很生活。

  • 类型：乳胶 / PU 修女风成人 cosplay 制服
  • 基础模型：SD 1.5
  • 当前版本：v2.0
  • 主触发词组：tutututu, nun, cross necklace, latex bodysuit, shiny clothes, skin tight, habit, latex gloves, black bodysuit, thigh boots
  • 推荐权重：0.4 到 0.9，建议从 0.6 开始
  • CLIP 终止层：2
  • CFG Scale：从 7 左右开始

这个模型适合什么

  • 还原黑色乳胶 / PU 亮面材质。
  • 保留修女风服装结构：头巾、十字项链、连体衣、手套、长靴。
  • 和其他 LoRA 一起使用时也比较友好。
  • 权重不需要太大，0.6 左右通常就有不错效果。
  • 对各种大模型比较友好，尤其擅长 2.5D 和二次元。

制作说明

我一直坚持高质量 LoRA 制作。这个 LoRA 也是用实拍素材 + 差异提取流程制作，最近我对整个算法和制作方式做了很多优化，这个模型也吃到了这些优化。

简单说，差异提取的目标是尽量去掉素材里不相关的污染，只保留有用的目标元素：服装结构、材质、光泽和配饰。所以这个 LoRA 和其他 LoRA 一起用时效果也很好，而且不需要把权重开得特别大。

更技术一些的部分包括自动化模型探索、LoRA 权重差异分析等。这里不把页面写成数学笔记，实际结果更重要：还原更好、提取更干净、污染更少。

推荐参数

  • 确保正确加载 LoRA。
  • CLIP 终止层数建议设置为 2。
  • 推荐权重：0.4 到 0.9，建议从 0.6 开始。
  • CFG Scale 可以从 7 开始尝试。
  • 负面提示词不要堆太多，否则会影响 LoRA 效果。
  • 对多种大模型都比较友好，尤其适合 2.5D 和二次元；不同底模需要适当调参。

出图关键词

主触发词组：

tutututu, nun, cross necklace, latex bodysuit, shiny clothes, skin tight, habit, latex gloves, black bodysuit, thigh boots

也可以尝试的紧凑写法：

latexgloves, blackbodysuit, thighboots

  • latex bodysuit
  • shiny clothes
  • black bodysuit
  • skin tight
  • latex gloves
  • thigh boots
  • cross necklace
  • habit
  • adult cosplay outfit
  • fashion portrait

如果服装不完整，先写完整触发词组。如果乳胶光泽不够，加强 latex bodysuit、shiny clothes、black bodysuit。如果影响整张图，先降低 LoRA 权重。

为什么要做这个 LoRA

类似服装 LoRA 很多，但很多不够贴近真实服装，或者当下流行的一些服装方向没有。还有一些 LoRA 对人物和画面影响太大，用起来不够方便。

所以我会继续做一系列服装 LoRA。为了方便使用，我后续制作的 LoRA 会尽量统一触发词风格：tutututu 加目标服装元素。

常见问题

为什么 0.6 就够了？

因为这个模型已经比较聚焦目标服装。如果触发词写完整，0.6 左右通常能有不错效果，不需要把权重拉得太大。

为什么服装不完整？

请写完整触发词。这个模型需要多个元素同时出现：nun、cross necklace、latex bodysuit、habit、latex gloves、thigh boots。

为什么我出不了和例图一样的图片？

每个人使用的底模、LoRA、插件、采样器和参数都不一样，请把例图当作方向，不要强求完全一致。

负责任使用

  • 请只用于合适的成年 cosplay / 时装语境。
  • 不要用于未成年人、校园年龄、年龄模糊的性化内容。
  • 你需要对使用本模型生成的任何作品承担全部责任。
  • 不要使用本模型制作或传播非法、有害、恶意、诽谤、诈骗或政治用途内容。
  • 如果将本模型用于商业用途或定制合作，请提前联系我，谢谢。

日本語説明

これは latex / PU nun-inspired adult cosplay uniform LoRA です。黒いラテックス / PU の光沢、ボディスーツ、十字架ネックレス、habit、ラテックス手袋、サイブーツを表現するためのモデルです。

  • Trigger: tutututu, nun, cross necklace, latex bodysuit, shiny clothes, skin tight, habit, latex gloves, black bodysuit, thigh boots
  • Weight: 0.4 to 0.9, start around 0.6
  • CLIP skip: 2
  • CFG Scale: start around 7

服装が不完全な場合は、トリガー語を全部入れてください。ラテックスの光沢が弱い場合は、latex bodysuit, shiny clothes, black bodysuit を強めてください。強すぎる場合は LoRA ウェイトを下げてください。

此模型生成的图像