CyberHarem/windsong_reverse1999
收藏Hugging Face2024-08-05 更新2025-04-12 收录
下载链接:
https://hf-mirror.com/datasets/CyberHarem/windsong_reverse1999
下载链接
链接失效反馈官方服务:
资源简介:
---
license: mit
task_categories:
- text-to-image
tags:
- art
- not-for-all-audiences
size_categories:
- n<1K
---
# Dataset of Windsong/北方哨歌 (Reverse:1999)
This is the dataset of Windsong/北方哨歌 (Reverse:1999), containing 27 images and their tags.
The core tags of this character are `long_hair, grey_hair, white_hair, hair_over_one_eye, purple_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 | Images-head | Images-others |
|:-----------------|---------:|:----------|:----------------------------------------------------------------------------------------------------------------------|:-----------|:---------------------------------------------------------------------|:--------------|:----------------|
| raw | 27 | 64.22 MiB | [Download](https://huggingface.co/datasets/CyberHarem/windsong_reverse1999/resolve/main/dataset-raw.zip) | Waifuc-Raw | Raw data with meta information (min edge aligned to 1400 if larger). | -- | -- |
| stage3-p480-1200 | 60 | 95.43 MiB | [Download](https://huggingface.co/datasets/CyberHarem/windsong_reverse1999/resolve/main/dataset-stage3-p480-1200.zip) | IMG+TXT | 3-stage cropped dataset with the area not less than 480x480 pixels. | 23 | 37 |
### 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/windsong_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 | 16 |  |  |  |  |  | white_shirt, 1girl, solo, coat, collared_shirt, fur_trim, jacket, long_sleeves, looking_at_viewer, pants, black_gloves, green_necktie, belt, smile, closed_mouth, mole_under_mouth |
| 1 | 5 |  |  |  |  |  | black_gloves, boots, collared_shirt, long_sleeves, solo, white_shirt, 1boy, male_focus, belt, black_footwear, closed_mouth, fur-trimmed_coat, green_pants, necktie, 1girl, brown_pants, crossed_arms, full_body, green_ribbon, jacket, neck_ribbon, shadow, sitting, smile, standing, tiles |
### Table Version
| # | Samples | Img-1 | Img-2 | Img-3 | Img-4 | Img-5 | white_shirt | 1girl | solo | coat | collared_shirt | fur_trim | jacket | long_sleeves | looking_at_viewer | pants | black_gloves | green_necktie | belt | smile | closed_mouth | mole_under_mouth | boots | 1boy | male_focus | black_footwear | fur-trimmed_coat | green_pants | necktie | brown_pants | crossed_arms | full_body | green_ribbon | neck_ribbon | shadow | sitting | standing | tiles |
|----:|----------:|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:--------------|:--------|:-------|:-------|:-----------------|:-----------|:---------|:---------------|:--------------------|:--------|:---------------|:----------------|:-------|:--------|:---------------|:-------------------|:--------|:-------|:-------------|:-----------------|:-------------------|:--------------|:----------|:--------------|:---------------|:------------|:---------------|:--------------|:---------|:----------|:-----------|:--------|
| 0 | 16 |  |  |  |  |  | X | X | X | X | X | X | X | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | |
| 1 | 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 |
license: MIT协议
task_categories:
- 文本到图像(text-to-image)
tags:
- 艺术(art)
- 不适合全年龄段受众(not-for-all-audiences)
size_categories:
- 样本量小于1000(n<1K)
# 《重返未来:1999》角色北方哨歌(Windsong)数据集
本数据集收录了《重返未来:1999》角色北方哨歌(Windsong)的27张图像及其标注标签。
该角色的核心标注标签为`long_hair、grey_hair、white_hair、hair_over_one_eye、purple_eyes`,本数据集已对这些核心标签进行了剪枝处理。
本数据集的图像爬取自多个平台(例如danbooru、pixiv、zerochan等),自动爬取系统由[DeepGHS团队](https://github.com/deepghs)及其Hugging Face组织(https://huggingface.co/deepghs)提供支持。
## 数据集包列表
| 包名称 | 图像数量 | 总大小 | 下载链接 | 数据类型 | 描述 | 图像头数量 | 其他图像数量 |
|:-----------------|---------:|:----------|:----------------------------------------------------------------------------------------------------------------------|:-----------|:---------------------------------------------------------------------|:--------------|:----------------|
| 原始数据集包 | 27 | 64.22 MiB | [下载](https://huggingface.co/datasets/CyberHarem/windsong_reverse1999/resolve/main/dataset-raw.zip) | Waifuc-Raw | 包含元数据的原始数据,若图像短边大于1400像素,则将其对齐至1400像素。 | —— | —— |
| 三阶裁剪数据集包(stage3-p480-1200) | 60 | 95.43 MiB | [下载](https://huggingface.co/datasets/CyberHarem/windsong_reverse1999/resolve/main/dataset-stage3-p480-1200.zip) | 图像+标签文本 | 经过三阶裁剪的数据集,裁剪后图像区域不小于480×480像素。 | 23 | 37 |
### 使用Waifuc加载原始数据集
我们提供适配[Waifuc](https://deepghs.github.io/waifuc/main/tutorials/installation/index.html)的原始数据集(含带标注的图像)加载方案,如需使用,请运行以下代码:
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/windsong_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多种穿搭风格。
### 原始文本版本
| 聚类编号 | 样本数量 | 示例图1 | 示例图2 | 示例图3 | 示例图4 | 示例图5 | 标签列表 |
|----:|----------:|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| 0 | 16 |  |  |  |  |  | 白衬衫(white_shirt)、单少女(1girl)、单人(solo)、外套(coat)、翻领衬衫(collared_shirt)、毛边饰边(fur_trim)、夹克(jacket)、长袖(long_sleeves)、直视镜头(looking_at_viewer)、长裤(pants)、黑色手套(black_gloves)、绿色领带(green_necktie)、腰带(belt)、微笑(smile)、闭口(closed_mouth)、嘴角痣(mole_under_mouth) |
| 1 | 5 |  |  |  |  |  | 黑色手套(black_gloves)、靴子(boots)、翻领衬衫(collared_shirt)、长袖(long_sleeves)、单人(solo)、白衬衫(white_shirt)、单男性(1boy)、男性视角(male_focus)、腰带(belt)、黑色鞋履(black_footwear)、闭口(closed_mouth)、毛边外套(fur-trimmed_coat)、绿色长裤(green_pants)、领带(necktie)、单少女(1girl)、棕色长裤(brown_pants)、交叉手臂(crossed_arms)、全身照(full_body)、绿色丝带(green_ribbon)、夹克(jacket)、颈部丝带(neck_ribbon)、阴影(shadow)、坐姿(sitting)、站姿(standing)、瓷砖地面(tiles) |
### 表格版本
| 聚类编号 | 样本数量 | 示例图1 | 示例图2 | 示例图3 | 示例图4 | 示例图5 | 白衬衫 | 单少女 | 单人 | 外套 | 翻领衬衫 | 毛边饰边 | 夹克 | 长袖 | 直视镜头 | 长裤 | 黑色手套 | 绿色领带 | 腰带 | 微笑 | 闭口 | 嘴角痣 | 靴子 | 单男性 | 男性视角 | 黑色鞋履 | 毛边外套 | 绿色长裤 | 领带 | 棕色长裤 | 交叉手臂 | 全身照 | 绿色丝带 | 颈部丝带 | 阴影 | 坐姿 | 站姿 | 瓷砖地面 |
|----:|----------:|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------------------------|:--------------|:--------|:-------|:-------|:-----------------|:-----------|:---------|:---------------|:--------------------|:--------|:---------------|:----------------|:-------|:--------|:---------------|:-------------------|:--------|:-------|:-------------|:-----------------|:-------------------|:--------------|:----------|:--------------|:---------------|:------------|:---------------|:--------------|:---------|:----------|:-----------|:--------|
| 0 | 16 |  |  |  |  |  | X | X | X | X | X | X | X | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | |
| 1 | 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 |
提供机构:
CyberHarem



