CyberHarem/hoshizora_rin_lovelive

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

# Dataset of hoshizora_rin/星空凛/호시조라린 (Love Live!)

This is the dataset of hoshizora_rin/星空凛/호시조라린 (Love Live!), containing 500 images and their tags.

The core tags of this character are `short_hair, orange_hair, yellow_eyes, hair_ornament, green_eyes`, 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 | 573.09 MiB | [Download](https://huggingface.co/datasets/CyberHarem/hoshizora_rin_lovelive/resolve/main/dataset-raw.zip) | Waifuc-Raw | Raw data with meta information (min edge aligned to 1400 if larger). |
| 800 | 500 | 344.64 MiB | [Download](https://huggingface.co/datasets/CyberHarem/hoshizora_rin_lovelive/resolve/main/dataset-800.zip) | IMG+TXT | dataset with the shorter side not exceeding 800 pixels. |
| stage3-p480-800 | 1181 | 717.85 MiB | [Download](https://huggingface.co/datasets/CyberHarem/hoshizora_rin_lovelive/resolve/main/dataset-stage3-p480-800.zip) | IMG+TXT | 3-stage cropped dataset with the area not less than 480x480 pixels. |
| 1200 | 500 | 506.59 MiB | [Download](https://huggingface.co/datasets/CyberHarem/hoshizora_rin_lovelive/resolve/main/dataset-1200.zip) | IMG+TXT | dataset with the shorter side not exceeding 1200 pixels. |
| stage3-p480-1200 | 1181 | 984.15 MiB | [Download](https://huggingface.co/datasets/CyberHarem/hoshizora_rin_lovelive/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/hoshizora_rin_lovelive',
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 | 57 |  |  |  |  |  | 1girl, solo, smile, looking_at_viewer, blush, veil, white_dress, bare_shoulders, earrings, choker, hair_flower, open_mouth, wedding_dress, white_gloves, white_background |
| 1 | 6 |  |  |  |  |  | 1girl, cape, constellation, earrings, looking_at_viewer, solo, star_(symbol), starry_sky_print, hat, open_mouth, blush, :d, character_name, dated, happy_birthday |
| 2 | 9 |  |  |  |  |  | 1girl, hair_bobbles, looking_at_viewer, skirt, solo, blush, white_thighhighs, one_side_up, :d, open_mouth, side_ponytail |
| 3 | 9 |  |  |  |  |  | 1girl, skirt, smile, solo, blush, looking_at_viewer, blazer, open_mouth, otonokizaka_school_uniform, winter_uniform, bow |
| 4 | 25 |  |  |  |  |  | 1girl, otonokizaka_school_uniform, solo, looking_at_viewer, blush, plaid_skirt, white_shirt, blue_bowtie, blue_skirt, open_mouth, long_sleeves, pleated_skirt, striped_bowtie, short_sleeves, summer_uniform, white_background, winter_uniform, bangs, blazer, simple_background, :d |
| 5 | 7 |  |  |  |  |  | 1girl, cat_ears, cat_tail, looking_at_viewer, smile, solo, earrings, bow, white_gloves, open_mouth, dated, fake_animal_ears, paw_pose |
| 6 | 5 |  |  |  |  |  | 1girl, cat_ears, cat_tail, looking_at_viewer, paw_pose, solo, blush, fingerless_gloves, one_eye_closed, smile, vertical-striped_thighhighs, ;3, bow, shorts, hairband, yellow_gloves |
| 7 | 13 |  |  |  |  |  | 1girl, looking_at_viewer, solo, blush, open_mouth, top_hat, white_shirt, :d, bangs_pinned_back, black_headwear, black_pantyhose, black_skirt, center_frills, hoop_earrings, long_sleeves, paw_pose, bow, high_heels, star_(symbol), suspender_skirt |
| 8 | 11 |  |  |  |  |  | 1girl, smile, solo, fingerless_gloves, necktie, open_mouth, skirt, earrings, looking_at_viewer, hat, one_eye_closed, white_gloves, ;d, blush, scarf |
| 9 | 9 |  |  |  |  |  | 1girl, blush, china_dress, hair_flower, looking_at_viewer, solo, smile, blue_dress, side_slit, sleeveless_dress, tray, bare_arms, bare_shoulders, bowl, breasts, holding, open_mouth, ramen, ribbon, tassel |
| 10 | 5 |  |  |  |  |  | 1girl, cat_cutout, cat_ear_panties, cat_lingerie, choker, cleavage_cutout, jingle_bell, looking_at_viewer, neck_bell, paw_pose, side-tie_panties, solo, underwear_only, blush, cat_ears, navel, small_breasts, white_background, cat_tail, smile, white_panties, :3, ass_visible_through_thighs, black_bra, black_panties, collarbone, fake_animal_ears, fang, frilled_bra, groin, heart, simple_background, stomach, white_bra |

### Table Version

| # | Samples | Img-1 | Img-2 | Img-3 | Img-4 | Img-5 | 1girl | solo | smile | looking_at_viewer | blush | veil | white_dress | bare_shoulders | earrings | choker | hair_flower | open_mouth | wedding_dress | white_gloves | white_background | cape | constellation | star_(symbol) | starry_sky_print | hat | :d | character_name | dated | happy_birthday | hair_bobbles | skirt | white_thighhighs | one_side_up | side_ponytail | blazer | otonokizaka_school_uniform | winter_uniform | bow | plaid_skirt | white_shirt | blue_bowtie | blue_skirt | long_sleeves | pleated_skirt | striped_bowtie | short_sleeves | summer_uniform | bangs | simple_background | cat_ears | cat_tail | fake_animal_ears | paw_pose | fingerless_gloves | one_eye_closed | vertical-striped_thighhighs | ;3 | shorts | hairband | yellow_gloves | top_hat | bangs_pinned_back | black_headwear | black_pantyhose | black_skirt | center_frills | hoop_earrings | high_heels | suspender_skirt | necktie | ;d | scarf | china_dress | blue_dress | side_slit | sleeveless_dress | tray | bare_arms | bowl | breasts | holding | ramen | ribbon | tassel | cat_cutout | cat_ear_panties | cat_lingerie | cleavage_cutout | jingle_bell | neck_bell | side-tie_panties | underwear_only | navel | small_breasts | white_panties | :3 | ass_visible_through_thighs | black_bra | black_panties | collarbone | fang | frilled_bra | groin | heart | stomach | white_bra |
|----:|----------:|:----------------------------------|:----------------------------------|:----------------------------------|:----------------------------------|:----------------------------------|:--------|:-------|:--------|:--------------------|:--------|:-------|:--------------|:-----------------|:-----------|:---------|:--------------|:-------------|:----------------|:---------------|:-------------------|:-------|:----------------|:----------------|:-------------------|:------|:-----|:-----------------|:--------|:-----------------|:---------------|:--------|:-------------------|:--------------|:----------------|:---------|:-----------------------------|:-----------------|:------|:--------------|:--------------|:--------------|:-------------|:---------------|:----------------|:-----------------|:----------------|:-----------------|:--------|:--------------------|:-----------|:-----------|:-------------------|:-----------|:--------------------|:-----------------|:------------------------------|:-----|:---------|:-----------|:----------------|:----------|:--------------------|:-----------------|:------------------|:--------------|:----------------|:----------------|:-------------|:------------------|:----------|:-----|:--------|:--------------|:-------------|:------------|:-------------------|:-------|:------------|:-------|:----------|:----------|:--------|:---------|:---------|:-------------|:------------------|:---------------|:------------------|:--------------|:------------|:-------------------|:-----------------|:--------|:----------------|:----------------|:-----|:-----------------------------|:------------|:----------------|:-------------|:-------|:--------------|:--------|:--------|:----------|:------------|
| 0 | 57 |  |  |  |  |  | X | X | X | X | X | X | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| 1 | 6 |  |  |  |  |  | X | X | | X | X | | | | X | | | X | | | | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| 2 | 9 |  |  |  |  |  | X | X | | X | X | | | | | | | X | | | | | | | | | X | | | | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| 3 | 9 |  |  |  |  |  | X | X | X | X | X | | | | | | | X | | | | | | | | | | | | | | X | | | | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| 4 | 25 |  |  |  |  |  | X | X | | X | X | | | | | | | X | | | X | | | | | | X | | | | | | | | | X | X | X | | X | X | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| 5 | 7 |  |  |  |  |  | X | X | X | X | | | | | X | | | X | | X | | | | | | | | | X | | | | | | | | | | X | | | | | | | | | | | | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| 6 | 5 |  |  |  |  |  | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | X | | | | | | | | | | | | X | X | | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| 7 | 13 |  |  |  |  |  | X | X | | X | X | | | | | | | X | | | | | | X | | | X | | | | | | | | | | | | X | | X | | | X | | | | | | | | | | X | | | | | | | | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| 8 | 11 |  |  |  |  |  | X | X | X | X | X | | | | X | | | X | | X | | | | | | X | | | | | | X | | | | | | | | | | | | | | | | | | | | | | | X | X | | | | | | | | | | | | | | | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
| 9 | 9 |  |  |  |  |  | X | X | X | X | X | | | X | | | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | X | X | X | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | |
| 10 | 5 |  |  |  |  |  | X | X | X | X | X | | | | | X | | | | | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | X | X | X | X | 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

数据集名称

Dataset of hoshizora_rin/星空凛/호시조라린 (Love Live!)

数据集描述

该数据集包含500张关于角色hoshizora_rin/星空凛/호시조라린（来自Love Live!）的图像及其标签。

核心标签

• short_hair
• orange_hair
• yellow_eyes
• hair_ornament
• green_eyes

数据集包列表

名称	图像数量	大小	类型	描述
raw	500	573.09 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	344.64 MiB	IMG+TXT	短边不超过800像素的数据集。
stage3-p480-800	1181	717.85 MiB	IMG+TXT	3阶段裁剪数据集，区域不小于480x480像素。
1200	500	506.59 MiB	IMG+TXT	短边不超过1200像素的数据集。
stage3-p480-1200	1181	984.15 MiB	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	图像示例	标签
0	57		1girl, solo, smile, looking_at_viewer, blush, veil, white_dress, bare_shoulders, earrings, choker, hair_flower, open_mouth, wedding_dress, white_gloves, white_background
1	6		1girl, cape, constellation, earrings, looking_at_viewer, solo, star_(symbol), starry_sky_print, hat, open_mouth, blush, :d, character_name, dated, happy_birthday
2	9		1girl, hair_bobbles, looking_at_viewer, skirt, solo, blush, white_thighhighs, one_side_up, :d, open_mouth, side_ponytail
3	9		1girl, skirt, smile, solo, blush, looking_at_viewer, blazer, open_mouth, otonokizaka_school_uniform, winter_uniform, bow
4	25		1girl, otonokizaka_school_uniform, solo, looking_at_viewer, blush, plaid_skirt, white_shirt, blue_bowtie, blue_skirt, open_mouth, long_sleeves, pleated_skirt, striped_bowtie, short_sleeves, summer_uniform, white_background, winter_uniform, bangs, blazer, simple_background, :d
5	7		1girl, cat_ears, cat_tail, looking_at_viewer, smile, solo, earrings, bow, white_gloves, open_mouth, dated, fake_animal_ears, paw_pose
6	5		1girl, cat_ears, cat_tail, looking_at_viewer, paw_pose, solo, blush, fingerless_gloves, one_eye_closed, smile, vertical-striped_thighhighs, ;3, bow, shorts, hairband, yellow_gloves
7	13		1girl, looking_at_viewer, solo, blush, open_mouth, top_hat, white_shirt, :d, bangs_pinned_back, black_headwear, black_pantyhose, black_skirt, center_frills, hoop_earrings, long_sleeves, paw_pose, bow, high_heels, star_(symbol), suspender_skirt
8	11		1girl, smile, solo, fingerless_gloves, necktie, open_mouth, skirt, earrings, looking_at_viewer, hat, one_eye_closed, white_gloves, ;d, blush, scarf
9	9		1girl, blush, china_dress, hair_flower, looking_at_viewer, solo, smile, blue_dress, side_slit, sleeveless_dress, tray, bare_arms, bare_shoulders, bowl, breasts, holding, open_mouth, ramen, ribbon, tassel
10	5		1girl, cat_cutout, cat_ear_panties, cat_lingerie, choker, cleavage_cutout, jingle_bell, looking_at_viewer, neck_bell, paw_pose, side-tie_panties, solo, underwear_only, blush, cat_ears, navel, small_breasts, white_background, cat_tail, smile, white_panties, :3, ass_visible_through_thighs, black_bra, black_panties, collarbone, fake_animal_ears, fang, frilled_bra, groin, heart, simple_background, stomach, white_bra

搜集汇总

数据集介绍

构建方式

该数据集聚焦于《Love Live!》中的角色星空凛，共计收录500张图像及其对应标签。数据采集自Danbooru、Pixiv、Zerochan等多个图像站点，依托DeepGHS团队开发的自动化爬取系统完成。原始数据经过多尺度处理，提供了多种封装形式：原始数据包保留元信息并将短边对齐至1400像素；800与1200版本则限制短边尺寸以适配不同训练需求；此外还提供了基于三级裁剪策略的数据集，确保裁剪区域不小于480×480像素，有效提升了图像质量与可用性。

特点

数据集的核心特色在于其精细的标签体系与聚类分析。核心角色标签如短髮、橘髮、黃瞳、髮飾、綠瞳已被精简剔除，避免冗余。数据包以IMG+TXT格式存储，便于直接用于文本到图像模型的训练。同时，数据集附带了详尽的聚类结果，将图像按视觉语义分为多个簇，例如婚礼服、星座主题、校园制服、猫耳装扮等，每个簇均提供代表性样本与完整标签列表，为下游任务如风格迁移、概念提取提供了结构化支撑。

使用方法

用户可通过HuggingFace Hub直接下载各类封装数据包。对于原始数据，推荐使用Waifuc库加载，具体流程包括通过huggingface_hub下载dataset-raw.zip压缩包，解压至本地目录后，利用LocalSource接口迭代访问图像及其元信息。此外，数据集的聚类结果以表格和文本两种形式呈现，便于研究者快速筛选特定主题的子集，从而高效地开展模型微调或评估工作。

背景与挑战

背景概述

在动漫与二次元文化蓬勃发展的当下，角色图像数据集成为文本到图像生成模型训练的重要基石。该数据集由DeepGHS团队于近年创建，聚焦于《Love Live!》系列中的角色星空凛（Hoshizora Rin），收录了500张经过精细标注的图像。其核心研究问题在于为特定动漫角色提供高质量、多风格的视觉素材，以支持角色定制化生成任务。数据集通过自动化爬虫系统从Danbooru、Pixiv、Zerochan等多源平台采集，并经过多尺度裁剪与标记聚类处理，为二次元图像生成领域提供了标准化、可复用的数据基础，对推动动漫角色AI创作具有显著影响力。

当前挑战

该数据集所解决的领域问题在于动漫角色图像的细粒度识别与生成，然而构建过程面临多重挑战。其一，跨平台数据采集需应对不同网站的版权限制与反爬机制，确保数据合法合规。其二，图像标注的准确性与一致性难以保障，尤其面对角色多样化的服饰、表情与姿态，需依赖自动化标签系统与人工校验相结合。其三，数据集规模较小（仅500张原始图像），可能限制模型泛化能力，需通过多阶段裁剪（如stage3-p480-800）扩充样本量。此外，内容审核是重要挑战，数据集包含not-for-all-audiences标签，需妥善处理敏感内容以符合伦理规范。

常用场景

经典使用场景

在动漫角色图像生成与风格迁移领域，CyberHarem/hoshizora_rin_lovelive数据集为研究者提供了高质、多态的视觉素材宝库。该数据集汇聚了500张来自Danbooru、Pixiv等平台的《Love Live!》角色星空凛图像，并附带精细标注的标签信息，如发色、瞳色、服饰细节等，尤其适用于条件文本到图像生成任务。通过其提供的多种分辨率与裁剪版本（如stage3-p480-800），研究者可灵活开展基于扩散模型的角色一致性生成研究，探索如何在保持角色核心特征（如橙色短发与黄绿色眼眸）的同时，实现多样化场景与姿态的逼真渲染，从而推动虚拟角色自动生成技术的边界。

解决学术问题

该数据集精准回应了动漫图像生成中角色身份保持与风格泛化的核心学术难题。传统生成模型常因训练数据稀疏或标注粗糙，难以在变换服饰、背景或动作时稳定复现特定角色的关键视觉属性。CyberHarem/hoshizora_rin_lovelive通过提供500张高分辨率图像及其聚类标签（如婚礼服、猫耳装、校服等），使研究者能够系统训练模型学习角色不变性表征，并量化评估不同生成条件下的身份保真度。这一资源显著促进了少样本角色定制生成、可控图像合成以及多模态对齐等前沿课题的进展，为动漫AI创作的理论与实践奠定了数据基石。

衍生相关工作

该数据集衍生了一系列推动动漫AI技术迭代的经典工作。依托其标注质量与多分辨率版本，研究者开发了Waifuc等自动化数据爬取与处理框架，实现了图像采集、筛选与标签补全的流水线化，为后续大规模动漫数据集构建提供了范式参考。在模型层面，基于此数据集的微调实验催生了针对角色一致性生成的高效LoRA（Low-Rank Adaptation）权重方案，有效降低了全参数微调的计算开销。此外，聚类标签的引入启发了多模态对比学习研究，通过联合优化图像-文本匹配损失，显著提升了生成模型对角色服饰、表情等细粒度属性的控制精度，间接推动了如Stable Diffusion等扩散模型在动漫领域的定制化应用。