CyberHarem/vritra_fgo
收藏资源简介:
--- license: mit task_categories: - text-to-image tags: - art - not-for-all-audiences size_categories: - n<1K --- # Dataset of vritra/ヴリトラ/弗栗多 (Fate/Grand Order) This is the dataset of vritra/ヴリトラ/弗栗多 (Fate/Grand Order), containing 96 images and their tags. The core tags of this character are `blonde_hair, long_hair, dragon_horns, breasts, horns, dark_skin, dragon_girl, facial_mark, dark-skinned_female, yellow_eyes, large_breasts, swept_bangs, tail, dragon_tail`, 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 | 96 | 155.24 MiB | [Download](https://huggingface.co/datasets/CyberHarem/vritra_fgo/resolve/main/dataset-raw.zip) | Waifuc-Raw | Raw data with meta information (min edge aligned to 1400 if larger). | | 1200 | 96 | 137.05 MiB | [Download](https://huggingface.co/datasets/CyberHarem/vritra_fgo/resolve/main/dataset-1200.zip) | IMG+TXT | dataset with the shorter side not exceeding 1200 pixels. | | stage3-p480-1200 | 238 | 261.44 MiB | [Download](https://huggingface.co/datasets/CyberHarem/vritra_fgo/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/vritra_fgo', 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 | 36 |  |  |  |  |  | looking_at_viewer, 1girl, black_dress, solo, bracelet, fur_trim, neck_ring, cleavage_cutout, sharp_teeth, white_background, grin | | 1 | 6 |  |  |  |  |  | 1girl, black_dress, looking_at_viewer, mouth_veil, solo, long_sleeves, green_ribbon | ### Table Version | # | Samples | Img-1 | Img-2 | Img-3 | Img-4 | Img-5 | looking_at_viewer | 1girl | black_dress | solo | bracelet | fur_trim | neck_ring | cleavage_cutout | sharp_teeth | white_background | grin | mouth_veil | long_sleeves | green_ribbon | |----:|----------:|:--------------------------------|:--------------------------------|:--------------------------------|:--------------------------------|:--------------------------------|:--------------------|:--------|:--------------|:-------|:-----------|:-----------|:------------|:------------------|:--------------|:-------------------|:-------|:-------------|:---------------|:---------------| | 0 | 36 |  |  |  |  |  | X | X | X | X | X | X | X | X | X | X | X | | | | | 1 | 6 |  |  |  |  |  | X | X | X | X | | | | | | | | X | X | X |
许可证: MIT 任务类别: - 文本到图像 标签: - 艺术 - 不适宜全年龄段 样本量范围: - n<1K # 《Fate/Grand Order》角色弗栗多(vritra/ヴリトラ)数据集 本数据集收录了《Fate/Grand Order》中角色弗栗多(vritra/ヴリトラ)的96张图像及其对应的标注标签。 该角色的核心标注标签为`金发(blonde_hair)、长发(long_hair)、龙角(dragon_horns)、胸部(breasts)、角(horns)、深色皮肤(dark_skin)、龙娘(dragon_girl)、面部印记(facial_mark)、深色皮肤女性(dark-skinned_female)、黄瞳(yellow_eyes)、巨乳(large_breasts)、偏分刘海(swept_bangs)、尾巴(tail)、龙尾(dragon_tail)`,本数据集已对上述标签进行了剪枝处理。 图像从多个平台爬取而来(例如danbooru、pixiv、zerochan等),自动爬取系统由[DeepGHS Team](https://github.com/deepghs)(其Hugging Face组织主页:https://huggingface.co/deepghs)开发维护。 ## 数据集包列表 | 包名 | 图像数量 | 大小 | 下载链接 | 类型 | 描述 | |:-----------------|---------:|:-----------|:------------------------------------------------------------------------------------------------------------|:-----------|:-------------------------------------------------------------| | raw | 96 | 155.24 MiB | [下载](https://huggingface.co/datasets/CyberHarem/vritra_fgo/resolve/main/dataset-raw.zip) | Waifuc-Raw | 包含元信息的原始数据,若图像短边大于1400像素则将其对齐至1400像素。 | | 1200 | 96 | 137.05 MiB | [下载](https://huggingface.co/datasets/CyberHarem/vritra_fgo/resolve/main/dataset-1200.zip) | IMG+TXT | 短边不超过1200像素的数据集。 | | stage3-p480-1200 | 238 | 261.44 MiB | [下载](https://huggingface.co/datasets/CyberHarem/vritra_fgo/resolve/main/dataset-stage3-p480-1200.zip) | IMG+TXT | 经过3阶段裁剪的数据集,裁剪区域不小于480×480像素。 | ### 使用Waifuc加载原始数据集 我们提供了支持waifuc加载的原始数据集(包含带标注的图像)。如需使用,请执行以下代码: python import os import zipfile from huggingface_hub import hf_hub_download from waifuc.source import LocalSource # 下载原始压缩包文件 zip_file = hf_hub_download( repo_id='CyberHarem/vritra_fgo', repo_type='dataset', filename='dataset-raw.zip', ) # 将文件解压至指定目录 dataset_dir = 'dataset_dir' os.makedirs(dataset_dir, exist_ok=True) with zipfile.ZipFile(zip_file, 'r') as zf: zf.extractall(dataset_dir) # 使用waifuc加载数据集 source = LocalSource(dataset_dir) for item in source: print(item.image, item.meta['filename'], item.meta['tags']) ## 聚类结果列表 本部分为标签聚类结果,可从中挖掘角色穿搭相关信息。 ### 原始文本版本 | # | 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 | 36 |  |  |  |  |  | 看向镜头、单女性角色、黑色连衣裙、单人、手链、毛边装饰、颈环、领口镂空、尖牙、白色背景、露齿笑 | | 1 | 6 |  |  |  |  |  | 单女性角色、黑色连衣裙、看向镜头、口纱、单人、长袖、绿色丝带 | ### 表格版本 | # | 样本数量 | 示例图1 | 示例图2 | 示例图3 | 示例图4 | 示例图5 | 看向镜头 | 单女性角色 | 黑色连衣裙 | 单人 | 手链 | 毛边装饰 | 颈环 | 领口镂空 | 尖牙 | 白色背景 | 露齿笑 | 口纱 | 长袖 | 绿色丝带 | |----:|----------:|:--------------------------------|:--------------------------------|:--------------------------------|:--------------------------------|:--------------------------------|:--------------------|:--------|:--------------|:-------|:-----------|:-----------|:------------|:------------------|:--------------|:-------------------|:-------|:-------------|:---------------|:---------------| | 0 | 36 |  |  |  |  |  | X | X | X | X | X | X | X | X | X | X | X | | | | | 1 | 6 |  |  |  |  |  | X | X | X | X | | | | | | | | X | X | X |
数据集概述
基本信息
- 名称: vritra/ヴリトラ/弗栗多 (Fate/Grand Order)
- 包含内容: 96张图像及其标签
- 核心标签: blonde_hair, long_hair, dragon_horns, breasts, horns, dark_skin, dragon_girl, facial_mark, dark-skinned_female, yellow_eyes, large_breasts, swept_bangs, tail, dragon_tail
- 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
| 名称 | 图像数量 | 大小 | 类型 | 描述 |
|---|---|---|---|---|
| raw | 96 | 155.24 MiB | Waifuc-Raw | 包含元信息的原始数据,最小边对齐至1400像素(如果更大)。 |
| 1200 | 96 | 137.05 MiB | IMG+TXT | 短边不超过1200像素的数据集。 |
| stage3-p480-1200 | 238 | 261.44 MiB | IMG+TXT | 三阶段裁剪数据集,区域不小于480x480像素。 |
数据集加载示例
-
使用工具: waifuc
-
加载代码示例: python import os import zipfile
from huggingface_hub import hf_hub_download from waifuc.source import LocalSource
下载原始归档文件
zip_file = hf_hub_download( repo_id=CyberHarem/vritra_fgo, repo_type=dataset, filename=dataset-raw.zip, )
提取文件至目录
dataset_dir = dataset_dir os.makedirs(dataset_dir, exist_ok=True) with zipfile.ZipFile(zip_file, r) as zf: zf.extractall(dataset_dir)
使用waifuc加载数据集
source = LocalSource(dataset_dir) for item in source: print(item.image, item.meta[filename], item.meta[tags])
标签聚类结果
| # | 样本数 | 标签 |
|---|---|---|
| 0 | 36 | looking_at_viewer, 1girl, black_dress, solo, bracelet, fur_trim, neck_ring, cleavage_cutout, sharp_teeth, white_background, grin |
| 1 | 6 | 1girl, black_dress, looking_at_viewer, mouth_veil, solo, long_sleeves, green_ribbon |




