CyberHarem/arashi_chisato_lovelivesuperstar

---
license: mit
task_categories:
- text-to-image
tags:
- art
- not-for-all-audiences
size_categories:
- n<1K
---

# Dataset of arashi_chisato/嵐千砂都/아라시치사토 (Love Live! Superstar!!)

This is the dataset of arashi_chisato/嵐千砂都/아라시치사토 (Love Live! Superstar!!), containing 500 images and their tags.

The core tags of this character are `bangs, white_hair, hair_bun, double_bun, red_eyes, long_hair, twintails, blunt_bangs, ribbon`, which are pruned in this dataset.

Images are crawled from many sites (e.g. danbooru, pixiv, zerochan ...), the auto-crawling system is powered by [DeepGHS Team](https://github.com/deepghs)([huggingface organization](https://huggingface.co/deepghs)).

## List of Packages

| Name | Images | Size | Download | Type | Description |
|:-----------------|---------:|:-----------|:----------------------------------------------------------------------------------------------------------------------------------|:-----------|:---------------------------------------------------------------------|
| raw | 500 | 673.58 MiB | [Download](https://huggingface.co/datasets/CyberHarem/arashi_chisato_lovelivesuperstar/resolve/main/dataset-raw.zip) | Waifuc-Raw | Raw data with meta information (min edge aligned to 1400 if larger). |
| 800 | 500 | 328.31 MiB | [Download](https://huggingface.co/datasets/CyberHarem/arashi_chisato_lovelivesuperstar/resolve/main/dataset-800.zip) | IMG+TXT | dataset with the shorter side not exceeding 800 pixels. |
| stage3-p480-800 | 1227 | 741.34 MiB | [Download](https://huggingface.co/datasets/CyberHarem/arashi_chisato_lovelivesuperstar/resolve/main/dataset-stage3-p480-800.zip) | IMG+TXT | 3-stage cropped dataset with the area not less than 480x480 pixels. |
| 1200 | 500 | 567.26 MiB | [Download](https://huggingface.co/datasets/CyberHarem/arashi_chisato_lovelivesuperstar/resolve/main/dataset-1200.zip) | IMG+TXT | dataset with the shorter side not exceeding 1200 pixels. |
| stage3-p480-1200 | 1227 | 1.14 GiB | [Download](https://huggingface.co/datasets/CyberHarem/arashi_chisato_lovelivesuperstar/resolve/main/dataset-stage3-p480-1200.zip) | IMG+TXT | 3-stage cropped dataset with the area not less than 480x480 pixels. |

### Load Raw Dataset with Waifuc

We provide raw dataset (including tagged images) for [waifuc](https://deepghs.github.io/waifuc/main/tutorials/installation/index.html) loading. If you need this, just run the following code

```python
import os
import zipfile

from huggingface_hub import hf_hub_download
from waifuc.source import LocalSource

# download raw archive file
zip_file = hf_hub_download(
repo_id='CyberHarem/arashi_chisato_lovelivesuperstar',
repo_type='dataset',
filename='dataset-raw.zip',
)

# extract files to your directory
dataset_dir = 'dataset_dir'
os.makedirs(dataset_dir, exist_ok=True)
with zipfile.ZipFile(zip_file, 'r') as zf:
zf.extractall(dataset_dir)

# load the dataset with waifuc
source = LocalSource(dataset_dir)
for item in source:
print(item.image, item.meta['filename'], item.meta['tags'])
```

## List of Clusters

List of tag clustering result, maybe some outfits can be mined here.

### Raw Text Version

| # | Samples | Img-1 | Img-2 | Img-3 | Img-4 | Img-5 | Tags |
|----:|----------:|:--------------------------------|:--------------------------------|:--------------------------------|:--------------------------------|:--------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 0 | 6 |  |  |  |  |  | 1girl, collared_shirt, looking_at_viewer, neck_ribbon, pinafore_dress, red_ribbon, short_sleeves, solo, upper_body, white_shirt, yuigaoka_school_uniform, blush, single_sidelock, smile, birthday, ok_sign, pink_background |
| 1 | 10 |  |  |  |  |  | 1girl, blue_jacket, collared_shirt, grey_dress, long_sleeves, looking_at_viewer, neck_ribbon, open_jacket, pinafore_dress, red_ribbon, solo, white_shirt, yuigaoka_school_uniform, open_mouth, white_background, :d, blush, simple_background, upper_body, teeth |
| 2 | 7 |  |  |  |  |  | 1girl, looking_at_viewer, neck_ribbon, red_ribbon, solo, upper_body, yuigaoka_school_uniform, blue_jacket, collared_shirt, portrait, smile, white_shirt, birthday, blush, long_sleeves, shiny_hair, open_mouth |
| 3 | 8 |  |  |  |  |  | 1girl, happy_birthday, looking_at_viewer, solo, character_name, dated, english_text, upper_body, grin, blush, jacket, short_sleeves, signature, single_sidelock |
| 4 | 11 |  |  |  |  |  | 1girl, looking_at_viewer, midriff, navel, solo, collarbone, smile, blush, open_jacket, pink_jacket, open_mouth, crop_top, long_sleeves, small_breasts, black_shorts, off_shoulder, one_eye_closed, pink_background, upper_body, white_tank_top |
| 5 | 5 |  |  |  |  |  | 1girl, looking_at_viewer, solo, tiara, upper_body, white_gloves, blush, earrings, necklace, smile, collarbone, crown, open_mouth, elbow_gloves, pink_dress, puffy_short_sleeves, purple_dress |
| 6 | 5 |  |  |  |  |  | 2girls, looking_at_viewer, smile, solo_focus, holding_hands, orange_hair, boots, mini_hat, pink_dress |
| 7 | 17 |  |  |  |  |  | 1girl, blush, nipples, completely_nude, navel, collarbone, pussy, small_breasts, 1boy, hetero, censored, open_mouth, solo_focus, penis, sex, sweat, closed_eyes, looking_at_viewer |

### Table Version

| # | Samples | Img-1 | Img-2 | Img-3 | Img-4 | Img-5 | 1girl | collared_shirt | looking_at_viewer | neck_ribbon | pinafore_dress | red_ribbon | short_sleeves | solo | upper_body | white_shirt | yuigaoka_school_uniform | blush | single_sidelock | smile | birthday | ok_sign | pink_background | blue_jacket | grey_dress | long_sleeves | open_jacket | open_mouth | white_background | :d | simple_background | teeth | portrait | shiny_hair | happy_birthday | character_name | dated | english_text | grin | jacket | signature | midriff | navel | collarbone | pink_jacket | crop_top | small_breasts | black_shorts | off_shoulder | one_eye_closed | white_tank_top | tiara | white_gloves | earrings | necklace | crown | elbow_gloves | pink_dress | puffy_short_sleeves | purple_dress | 2girls | solo_focus | holding_hands | orange_hair | boots | mini_hat | nipples | completely_nude | pussy | 1boy | hetero | censored | penis | sex | sweat | closed_eyes |
|----:|----------:|:--------------------------------|:--------------------------------|:--------------------------------|:--------------------------------|:--------------------------------|:--------|:-----------------|:--------------------|:--------------|:-----------------|:-------------|:----------------|:-------|:-------------|:--------------|:--------------------------|:--------|:------------------|:--------|:-----------|:----------|:------------------|:--------------|:-------------|:---------------|:--------------|:-------------|:-------------------|:-----|:--------------------|:--------|:-----------|:-------------|:-----------------|:-----------------|:--------|:---------------|:-------|:---------|:------------|:----------|:--------|:-------------|:--------------|:-----------|:----------------|:---------------|:---------------|:-----------------|:-----------------|:--------|:---------------|:-----------|:-----------|:--------|:---------------|:-------------|:----------------------|:---------------|:---------|:-------------|:----------------|:--------------|:--------|:-----------|:----------|:------------------|:--------|:-------|:---------|:-----------|:--------|:------|:--------|:--------------|
| 0 | 6 |  |  |  |  |  | X | X | X | X | X | X | X | X | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| 1 | 10 |  |  |  |  |  | X | X | X | X | X | X | | X | X | X | X | X | | | | | | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| 2 | 7 |  |  |  |  |  | X | X | X | X | | X | | X | X | X | X | X | | X | X | | | X | | X | | X | | | | | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| 3 | 8 |  |  |  |  |  | X | | X | | | | X | X | X | | | X | X | | | | | | | | | | | | | | | | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| 4 | 11 |  |  |  |  |  | X | | X | | | | | X | X | | | X | | X | | | X | | | X | X | X | | | | | | | | | | | | | | X | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | |
| 5 | 5 |  |  |  |  |  | X | | X | | | | | X | X | | | X | | X | | | | | | | | X | | | | | | | | | | | | | | | | X | | | | | | | | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | |
| 6 | 5 |  |  |  |  |  | | | X | | | | | | | | | | | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | X | | | X | X | X | X | X | X | | | | | | | | | | |
| 7 | 17 |  |  |  |  |  | X | | X | | | | | | | | | X | | | | | | | | | | X | | | | | | | | | | | | | | | X | X | | | X | | | | | | | | | | | | | | | X | | | | | X | X | X | X | X | X | X | X | X | X |

原始信息汇总

数据集概述

数据集信息

• 名称: arashi_chisato/嵐千砂都/아라시치사토 (Love Live! Superstar!!)
• 描述: 包含500张图片及其标签的数据集。
• 核心标签: bangs, white_hair, hair_bun, double_bun, red_eyes, long_hair, twintails, blunt_bangs, ribbon
• 来源: 从多个网站（如danbooru, pixiv, zerochan等）爬取。
• 许可证: MIT
• 任务类别: text-to-image
• 标签: art, not-for-all-audiences
• 大小类别: n<1K

数据集包列表

名称	图片数量	大小	类型	描述
raw	500	673.58 MiB	Waifuc-Raw	包含元信息的原始数据（最小边对齐到1400像素，如果更大）。
800	500	328.31 MiB	IMG+TXT	短边不超过800像素的数据集。
stage3-p480-800	1227	741.34 MiB	IMG+TXT	3阶段裁剪数据集，区域不小于480x480像素。
1200	500	567.26 MiB	IMG+TXT	短边不超过1200像素的数据集。
stage3-p480-1200	1227	1.14 GiB	IMG+TXT	3阶段裁剪数据集，区域不小于480x480像素。

标签聚类结果

原始文本版本

#	样本数量	图片示例	标签
0	6		1girl, collared_shirt, looking_at_viewer, neck_ribbon, pinafore_dress, red_ribbon, short_sleeves, solo, upper_body, white_shirt, yuigaoka_school_uniform, blush, single_sidelock, smile, birthday, ok_sign, pink_background
1	10		1girl, blue_jacket, collared_shirt, grey_dress, long_sleeves, looking_at_viewer, neck_ribbon, open_jacket, pinafore_dress, red_ribbon, solo, white_shirt, yuigaoka_school_uniform, open_mouth, white_background, :d, blush, simple_background, upper_body, teeth
2	7		1girl, looking_at_viewer, neck_ribbon, red_ribbon, solo, upper_body, yuigaoka_school_uniform, blue_jacket, collared_shirt, portrait, smile, white_shirt, birthday, blush, long_sleeves, shiny_hair, open_mouth
3	8		1girl, happy_birthday, looking_at_viewer, solo, character_name, dated, english_text, upper_body, grin, blush, jacket, short_sleeves, signature, single_sidelock
4	11		1girl, looking_at_viewer, midriff, navel, solo, collarbone, smile, blush, open_jacket, pink_jacket, open_mouth, crop_top, long_sleeves, small_breasts, black_shorts, off_shoulder, one_eye_closed, pink_background, upper_body, white_tank_top
5	5		1girl, looking_at_viewer, solo, tiara, upper_body, white_gloves, blush, earrings, necklace, smile, collarbone, crown, open_mouth, elbow_gloves, pink_dress, puffy_short_sleeves, purple_dress
6	5		2girls, looking_at_viewer, smile, solo_focus, holding_hands, orange_hair, boots, mini_hat, pink_dress
7	17		1girl, blush, nipples, completely_nude, navel, collarbone, pussy, small_breasts, 1boy, hetero, censored, open_mouth, solo_focus, penis, sex, sweat, closed_eyes, looking_at_viewer

搜集汇总

数据集介绍

构建方式

该数据集聚焦于《Love Live! Superstar!!》中的角色嵐千砂都，收录了500幅图像及其对应标签。数据源自Danbooru、Pixiv、Zerochan等多个平台，依托DeepGHS团队开发的自动化爬取系统完成采集。在预处理阶段，系统对图像进行了核心标签（如刘海、白发、双丸子头、红瞳、长发、双马尾、缎带等）的筛选与修剪，确保数据特征的集中性。数据集提供了多种规格的打包版本，包括原始数据（含元信息，最小边对齐至1400像素）、短边不超过800或1200像素的缩放版，以及基于三阶段裁剪策略、面积不低于480×480像素的增强版，以适应不同训练需求。

特点

该数据集的核心特色在于其多维度的结构化设计。除了基础图像外，还提供了基于标签聚类的分组结果，将相似着装或场景的图像归入同一簇（如校服、生日贺图、舞台装、日常便服乃至特定主题组），便于研究者挖掘角色在不同情境下的视觉表现。聚类结果以文本和表格双版本呈现，清晰展示了各簇的样本数量、代表图像及关联标签，支持从宏观到微观的层次化分析。此外，数据集囊括了从纯真风格到限制级内容的广泛标签，既反映了动漫图像社区的多样性，也提示用户在使用时需注意内容筛选。

使用方法

数据集支持通过waifuc框架加载原始压缩包，用户可利用Hugging Face Hub的hf_hub_download函数下载dataset-raw.zip文件，解压后借助LocalSource接口遍历图像、文件名及标签元数据。对于不同分辨率需求，可直接选用800、1200等预处理版本，或应用stage3裁剪版以获取聚焦于主体区域的子图。聚类结果中的标签列表可作为训练条件生成模型时的参考提示词，而多版本打包设计则方便研究者根据计算资源灵活选择数据规模。需要注意的是，部分内容包含成人向标签，使用时需遵守平台规定并实施适当的过滤策略。

背景与挑战

背景概述

在动漫角色图像生成领域，高质量、标注精确的数据集是驱动文本到图像模型性能提升的关键基石。CyberHarem/arashi_chisato_lovelivesuperstar数据集由DeepGHS团队于近年构建，聚焦于《Love Live! Superstar!!》中的角色嵐千砂都。该数据集的核心研究问题在于如何系统性地收集、清洗并标注特定动漫角色的多模态图像数据，以支持后续的文本到图像生成任务。通过从Danbooru、Pixiv、Zerochan等多个平台自动爬取，并辅以核心标签（如白发、红眼、双马尾等）的筛选，该数据集为角色个性化生成提供了标准化素材。其对相关领域的影响力体现在为二次元角色数据集的构建流程树立了范例，推动了动漫风格图像生成模型的精细化发展。

当前挑战

该数据集面临的挑战主要源于两个方面。在领域问题层面，动漫角色图像生成需要模型精准捕捉角色核心特征（如发型、服饰、表情），而数据集中仅包含500张图像，样本量有限，难以覆盖角色在不同场景、姿态和光照条件下的多样性，易导致生成结果的同质化或特征缺失。在构建过程中，跨平台数据爬取面临版权与内容合规性风险，且自动标注的标签可能包含噪声（如部分图像存在多角色、不相关内容或低质量样本），需通过聚类分析（如8个聚类簇）进行人工校验与筛选，但聚类结果中仍混杂了敏感内容（如裸露、性暗示标签），增加了数据安全管理的复杂性。

常用场景

经典使用场景

该数据集作为面向《Love Live! Superstar!!》中角色岚千砂都的精细化图像-文本配对资源，在文本到图像生成领域扮演着关键角色。其核心应用场景聚焦于基于扩散模型的动漫角色定制化生成，研究者可利用其中500张高质量图像及其结构化标签（如发型、服饰、表情等），训练或微调模型以精准捕捉该角色的视觉特征。数据集中提供的多尺度版本（如800像素与1200像素）以及经过三阶段裁剪的版本，为不同分辨率需求的实验提供了灵活选择，显著提升了角色一致性与生成质量。

实际应用

实际应用中，该数据集支撑了多种面向粉丝社群的创作工具开发，例如角色头像自动生成、同人插画辅助绘制以及虚拟偶像内容生产。基于其图像与标签的对应关系，开发者能够构建轻量级模型，实现从文本描述（如“穿着粉色夹克的岚千砂都”）到个性化图像的即时转换。此外，数据集中的聚类结果可直接用于设计交互式角色装扮系统，赋能非专业用户通过简单标签组合快速产出风格统一的视觉素材，从而降低二次创作的技术门槛。

衍生相关工作

该数据集衍生了一系列经典工作，尤其是在动漫领域扩散模型的微调与评估方面。例如，研究者常将其与DreamBooth、LoRA等参数高效微调方法结合，验证少样本学习在角色定制中的有效性。同时，数据集中包含的原始元信息与waifuc加载接口，催生了基于自动爬取与标签清洗的数据管道研究，推动了如DeepGHS团队在图像采集标准化上的技术迭代。此外，服饰聚类的标注形式为后续的语义分割与风格迁移任务提供了参考，激发了针对动漫角色多模态理解的新一轮探索。