CyberHarem/kakania_reverse1999

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

# Dataset of Kakania/卡卡尼亚 (Reverse:1999)

This is the dataset of Kakania/卡卡尼亚 (Reverse:1999), containing 18 images and their tags.

The core tags of this character are `long_hair, black_hair, hat, very_long_hair, brown_hair, white_headwear, earrings`, 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 | Images-head | Images-others |
|:-----------------|---------:|:----------|:---------------------------------------------------------------------------------------------------------------------|:-----------|:---------------------------------------------------------------------|:--------------|:----------------|
| raw | 18 | 56.89 MiB | [Download](https://huggingface.co/datasets/CyberHarem/kakania_reverse1999/resolve/main/dataset-raw.zip) | Waifuc-Raw | Raw data with meta information (min edge aligned to 1400 if larger). | -- | -- |
| stage3-p480-1200 | 45 | 79.01 MiB | [Download](https://huggingface.co/datasets/CyberHarem/kakania_reverse1999/resolve/main/dataset-stage3-p480-1200.zip) | IMG+TXT | 3-stage cropped dataset with the area not less than 480x480 pixels. | 13 | 32 |

### 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/kakania_reverse1999',
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 | 9 |  |  |  |  |  | 1girl, gloves, long_sleeves, puffy_sleeves, solo, flower, purple_dress, breasts, closed_mouth, necklace, purple_eyes, white_dress |
| 1 | 7 |  |  |  |  |  | jewelry, white_dress, 1girl, looking_at_viewer, solo, white_gloves, juliet_sleeves, parted_lips, upper_body, blue_eyes, butterfly, closed_mouth, elbow_gloves, hat_bow, ribbon, smile |

### Table Version

| # | Samples | Img-1 | Img-2 | Img-3 | Img-4 | Img-5 | 1girl | gloves | long_sleeves | puffy_sleeves | solo | flower | purple_dress | breasts | closed_mouth | necklace | purple_eyes | white_dress | jewelry | looking_at_viewer | white_gloves | juliet_sleeves | parted_lips | upper_body | blue_eyes | butterfly | elbow_gloves | hat_bow | ribbon | smile |
|----:|----------:|:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:--------|:---------|:---------------|:----------------|:-------|:---------|:---------------|:----------|:---------------|:-----------|:--------------|:--------------|:----------|:--------------------|:---------------|:-----------------|:--------------|:-------------|:------------|:------------|:---------------|:----------|:---------|:--------|
| 0 | 9 |  |  |  |  |  | X | X | X | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | |
| 1 | 7 |  |  |  |  |  | X | | | | X | | | | X | | | X | X | X | X | X | X | X | X | X | X | X | X | X |

---
许可证：MIT协议
任务类别：
- 文本到图像生成
标签：
- 艺术创作
- 不适合全年龄段观众
样本规模：
- 少于1000条
---

# 《重返未来：1999》卡卡尼亚（Kakania）数据集

本数据集取材于游戏《重返未来：1999》中的角色卡卡尼亚（Kakania），共包含18张图像及其对应标注标签。

该角色的核心标注标签为`长发（long_hair）、黑发（black_hair）、帽子（hat）、超长长发（very_long_hair）、棕发（brown_hair）、白色头饰（white_headwear）、耳环（earrings）`，本数据集已对上述核心标签进行了剪枝处理。

本数据集的图像采集自多个平台（如danbooru、pixiv、zerochan等），自动爬虫系统由DeepGHS团队开发维护，其相关仓库与机构主页分别为 [GitHub仓库](https://github.com/deepghs) 与 [Hugging Face机构主页](https://huggingface.co/deepghs)。

## 数据包列表

| 数据包名称 | 图像数量 | 占用大小 | 下载链接 | 数据类型 | 描述 | 头部图像数 | 其他图像数 |
|:-----------------|---------:|:----------|:---------------------------------------------------------------------------------------------------------------------|:-----------|:---------------------------------------------------------------------|:--------------|:----------------|
| 原始数据 | 18 | 56.89 MiB | [下载](https://huggingface.co/datasets/CyberHarem/kakania_reverse1999/resolve/main/dataset-raw.zip) | Waifuc-Raw | 包含元数据的原始图像数据（若图像短边大于1400像素，则将其对齐至1400像素） | -- | -- |
| stage3-p480-1200 | 45 | 79.01 MiB | [下载](https://huggingface.co/datasets/CyberHarem/kakania_reverse1999/resolve/main/dataset-stage3-p480-1200.zip) | IMG+TXT | 经过3阶段裁剪处理的数据集，裁剪后图像区域不小于480×480像素 | 13 | 32 |

### 使用Waifuc加载原始数据集

我们提供了可通过Waifuc加载的原始数据集（包含带标签的图像），相关使用教程可参考 [Waifuc官方文档](https://deepghs.github.io/waifuc/main/tutorials/installation/index.html)，加载代码如下：

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/kakania_reverse1999',
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'])

## 聚类标签列表

以下为标签聚类结果，可从中挖掘该角色的不同穿搭风格。

### 原始文本格式

| 序号 | 样本数 | 示例图1 | 示例图2 | 示例图3 | 示例图4 | 示例图5 | 标签 |
|----:|----------:|:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 0 | 9 |  |  |  |  |  | 1位女性、手套、长袖、泡泡袖、单人、花朵、紫色连衣裙、胸部、闭口、项链、紫色眼眸、白色连衣裙 |
| 1 | 7 |  |  |  |  |  | 珠宝、白色连衣裙、1位女性、看向镜头、单人、白色手套、朱丽叶袖、微张嘴唇、上半身、蓝色眼眸、蝴蝶、闭口、肘部手套、帽饰蝴蝶结、丝带、微笑 |

### 表格格式

| 序号 | 样本数 | 示例图1 | 示例图2 | 示例图3 | 示例图4 | 示例图5 | 1位女性 | 手套 | 长袖 | 泡泡袖 | 单人 | 花朵 | 紫色连衣裙 | 胸部 | 闭口 | 项链 | 紫色眼眸 | 白色连衣裙 | 珠宝 | 看向镜头 | 白色手套 | 朱丽叶袖 | 微张嘴唇 | 上半身 | 蓝色眼眸 | 蝴蝶 | 肘部手套 | 帽饰蝴蝶结 | 丝带 | 微笑 |
|----:|----------:|:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------|:--------|:---------|:---------------|:----------------|:-------|:---------|:---------------|:----------|:---------------|:-----------|:--------------|:--------------|:----------|:--------------------|:---------------|:-----------------|:--------------|:-------------|:------------|:------------|:---------------|:----------|:---------|:--------|
| 0 | 9 |  |  |  |  |  | X | X | X | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | |
| 1 | 7 |  |  |  |  |  | X | | | | X | | | | X | | | X | X | X | X | X | X | X | X | X | X | X | X |