CyberHarem/hazawa_tsugumi_bangdream

--- license: mit task_categories: - text-to-image tags: - art - not-for-all-audiences size_categories: - n<1K --- # Dataset of hazawa_tsugumi/羽沢つぐみ (BanG Dream!) This is the dataset of hazawa_tsugumi/羽沢つぐみ (BanG Dream!), containing 297 images and their tags. The core tags of this character are `brown_hair, short_hair, brown_eyes, bangs`, 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 | 297 | 319.55 MiB | [Download](https://huggingface.co/datasets/CyberHarem/hazawa_tsugumi_bangdream/resolve/main/dataset-raw.zip) | Waifuc-Raw | Raw data with meta information (min edge aligned to 1400 if larger). | | 800 | 297 | 204.10 MiB | [Download](https://huggingface.co/datasets/CyberHarem/hazawa_tsugumi_bangdream/resolve/main/dataset-800.zip) | IMG+TXT | dataset with the shorter side not exceeding 800 pixels. | | stage3-p480-800 | 659 | 405.88 MiB | [Download](https://huggingface.co/datasets/CyberHarem/hazawa_tsugumi_bangdream/resolve/main/dataset-stage3-p480-800.zip) | IMG+TXT | 3-stage cropped dataset with the area not less than 480x480 pixels. | | 1200 | 297 | 287.55 MiB | [Download](https://huggingface.co/datasets/CyberHarem/hazawa_tsugumi_bangdream/resolve/main/dataset-1200.zip) | IMG+TXT | dataset with the shorter side not exceeding 1200 pixels. | | stage3-p480-1200 | 659 | 550.27 MiB | [Download](https://huggingface.co/datasets/CyberHarem/hazawa_tsugumi_bangdream/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/hazawa_tsugumi_bangdream', 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 | 5 |  |  |  |  |  | blush, upper_body, white_shirt, 1girl, :d, looking_at_viewer, open_mouth, simple_background, solo, collared_shirt, white_background, apron, clenched_hands, long_sleeves | | 1 | 11 |  |  |  |  |  | 1girl, blush, solo, holding_tray, looking_at_viewer, open_mouth, white_shirt, long_sleeves, collared_shirt, :d, waitress, brown_apron, upper_body, food, standing | | 2 | 7 |  |  |  |  |  | 1girl, black_jacket, blush, long_sleeves, solo, black_choker, collarbone, hairband, looking_at_viewer, open_mouth, yellow_dress, hood_down, necklace, simple_background, white_background, :d, hooded_jacket, hair_ribbon, open_jacket, standing, upper_body | | 3 | 11 |  |  |  |  |  | blazer, school_uniform, grey_jacket, long_sleeves, 1girl, blush, collared_shirt, white_shirt, open_mouth, solo, striped_necktie, blue_necktie, looking_at_viewer, plaid_skirt, pleated_skirt, smile, simple_background, upper_body, white_background, blue_skirt, miniskirt, wing_collar | | 4 | 8 |  |  |  |  |  | 1girl, blush, collarbone, solo, bare_shoulders, white_background, simple_background, bikini, medium_breasts, navel, open_mouth, bare_arms, cleavage, looking_at_viewer, black_hair, cowboy_shot, flying_sweatdrops, upper_body | | 5 | 5 |  |  |  |  |  | 1girl, solo, choker, collarbone, looking_at_viewer, petals, blush, earrings, hair_bow, shiny_hair, short_sleeves, wedding_dress, white_bow, yellow_rose, bridal_veil, closed_mouth, grin, hair_flower, off-shoulder_dress, stained_glass, standing, upper_body, white_dress, white_gloves, yellow_bow, yellow_dress | | 6 | 5 |  |  |  |  |  | knee_boots, :d, black_choker, black_footwear, black_gloves, blush, necklace, open_mouth, solo_focus, earrings, fishnets, jacket, lace-up_boots, looking_at_viewer, red_shirt, short_sleeves, standing, thighhighs, 2girls, 3girls, black_skirt, electric_guitar, long_sleeves, plaid_shirt, simple_background, thigh_strap, white_background | | 7 | 7 |  |  |  |  |  | 1girl, blush, solo, looking_at_viewer, red_headwear, santa_hat, fur_trim, upper_body, black_gloves, bow, earrings, fingerless_gloves, fur-trimmed_headwear, open_mouth, ribbon, white_background, :d, gift_box, holding_gift, holding_sack, merry_christmas, santa_costume, simple_background | | 8 | 16 |  |  |  |  |  | 1girl, 1boy, blush, hetero, nipples, penis, solo_focus, sex, open_mouth, vaginal, mosaic_censoring, navel, completely_nude, small_breasts, sweat, medium_breasts, cum_in_pussy, girl_on_top, smile, straddling | ### Table Version | # | Samples | Img-1 | Img-2 | Img-3 | Img-4 | Img-5 | blush | upper_body | white_shirt | 1girl | :d | looking_at_viewer | open_mouth | simple_background | solo | collared_shirt | white_background | apron | clenched_hands | long_sleeves | holding_tray | waitress | brown_apron | food | standing | black_jacket | black_choker | collarbone | hairband | yellow_dress | hood_down | necklace | hooded_jacket | hair_ribbon | open_jacket | blazer | school_uniform | grey_jacket | striped_necktie | blue_necktie | plaid_skirt | pleated_skirt | smile | blue_skirt | miniskirt | wing_collar | bare_shoulders | bikini | medium_breasts | navel | bare_arms | cleavage | black_hair | cowboy_shot | flying_sweatdrops | choker | petals | earrings | hair_bow | shiny_hair | short_sleeves | wedding_dress | white_bow | yellow_rose | bridal_veil | closed_mouth | grin | hair_flower | off-shoulder_dress | stained_glass | white_dress | white_gloves | yellow_bow | knee_boots | black_footwear | black_gloves | solo_focus | fishnets | jacket | lace-up_boots | red_shirt | thighhighs | 2girls | 3girls | black_skirt | electric_guitar | plaid_shirt | thigh_strap | red_headwear | santa_hat | fur_trim | bow | fingerless_gloves | fur-trimmed_headwear | ribbon | gift_box | holding_gift | holding_sack | merry_christmas | santa_costume | 1boy | hetero | nipples | penis | sex | vaginal | mosaic_censoring | completely_nude | small_breasts | sweat | cum_in_pussy | girl_on_top | straddling | |----:|----------:|:--------------------------------|:--------------------------------|:--------------------------------|:--------------------------------|:--------------------------------|:--------|:-------------|:--------------|:--------|:-----|:--------------------|:-------------|:--------------------|:-------|:-----------------|:-------------------|:--------|:-----------------|:---------------|:---------------|:-----------|:--------------|:-------|:-----------|:---------------|:---------------|:-------------|:-----------|:---------------|:------------|:-----------|:----------------|:--------------|:--------------|:---------|:-----------------|:--------------|:------------------|:---------------|:--------------|:----------------|:--------|:-------------|:------------|:--------------|:-----------------|:---------|:-----------------|:--------|:------------|:-----------|:-------------|:--------------|:--------------------|:---------|:---------|:-----------|:-----------|:-------------|:----------------|:----------------|:------------|:--------------|:--------------|:---------------|:-------|:--------------|:---------------------|:----------------|:--------------|:---------------|:-------------|:-------------|:-----------------|:---------------|:-------------|:-----------|:---------|:----------------|:------------|:-------------|:---------|:---------|:--------------|:------------------|:--------------|:--------------|:---------------|:------------|:-----------|:------|:--------------------|:-----------------------|:---------|:-----------|:---------------|:---------------|:------------------|:----------------|:-------|:---------|:----------|:--------|:------|:----------|:-------------------|:------------------|:----------------|:--------|:---------------|:--------------|:-------------| | 0 | 5 |  |  |  |  |  | X | X | X | X | X | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 1 | 11 |  |  |  |  |  | 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 | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 3 | 11 |  |  |  |  |  | X | X | X | X | | X | X | X | X | X | X | | | X | | | | | | | | | | | | | | | | X | X | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 4 | 8 |  |  |  |  |  | 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 | 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 | X | X | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | | | | | | | | | | | | | 7 | 7 |  |  |  |  |  | X | X | | X | X | X | X | X | X | | X | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | X | | | | | | | | | | | | | | | | | | X | | | | | | | | | | | | | X | X | X | X | X | X | X | X | X | X | X | X | | | | | | | | | | | | | | | 8 | 16 |  |  |  |  |  | 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

数据集信息

• 名称: Dataset of hazawa_tsugumi/羽沢つぐみ (BanG Dream!)
• 描述: 包含297张图片及其标签的数据集。
• 核心标签: brown_hair, short_hair, brown_eyes, bangs
• 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	297	319.55 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	297	204.10 MiB	IMG+TXT	短边不超过800像素的数据集。
stage3-p480-800	659	405.88 MiB	IMG+TXT	3阶段裁剪数据集，区域不小于480x480像素。
1200	297	287.55 MiB	IMG+TXT	短边不超过1200像素的数据集。
stage3-p480-1200	659	550.27 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	图片示例	标签
0	5		blush, upper_body, white_shirt, 1girl, :d, looking_at_viewer, open_mouth, simple_background, solo, collared_shirt, white_background, apron, clenched_hands, long_sleeves
1	11		1girl, blush, solo, holding_tray, looking_at_viewer, open_mouth, white_shirt, long_sleeves, collared_shirt, :d, waitress, brown_apron, upper_body, food, standing
2	7		1girl, black_jacket, blush, long_sleeves, solo, black_choker, collarbone, hairband, looking_at_viewer, open_mouth, yellow_dress, hood_down, necklace, simple_background, white_background, :d, hooded_jacket, hair_ribbon, open_jacket, standing, upper_body
3	11		blazer, school_uniform, grey_jacket, long_sleeves, 1girl, blush, collared_shirt, white_shirt, open_mouth, solo, striped_necktie, blue_necktie, looking_at_viewer, plaid_skirt, pleated_skirt, smile, simple_background, upper_body, white_background, blue_skirt, miniskirt, wing_collar
4	8		1girl, blush, collarbone, solo, bare_shoulders, white_background, simple_background, bikini, medium_breasts, navel, open_mouth, bare_arms, cleavage, looking_at_viewer, black_hair, cowboy_shot, flying_sweatdrops, upper_body
5	5		1girl, solo, choker, collarbone, looking_at_viewer, petals, blush, earrings, hair_bow, shiny_hair, short_sleeves, wedding_dress, white_bow, yellow_rose, bridal_veil, closed_mouth, grin, hair_flower, off-shoulder_dress, stained_glass, standing, upper_body, white_dress, white_gloves, yellow_bow, yellow_dress
6	5		knee_boots, :d, black_choker, black_footwear, black_gloves, blush, necklace, open_mouth, solo_focus, earrings, fishnets, jacket, lace-up_boots, looking_at_viewer, red_shirt, short_sleeves, standing, thighhighs, 2girls, 3girls, black_skirt, electric_guitar, long_sleeves, plaid_shirt, simple_background, thigh_strap, white_background
7	7		1girl, blush, solo, looking_at_viewer, red_headwear, santa_hat, fur_trim, upper_body, black_gloves, bow, earrings, fingerless_gloves, fur-trimmed_headwear, open_mouth, ribbon, white_background, :d, gift_box, holding_gift, holding_sack, merry_christmas, santa_costume, simple_background
8	16		1girl, 1boy, blush, hetero, nipples, penis, solo_focus, sex, open_mouth, vaginal, mosaic_censoring, navel, completely_nude, small_breasts, sweat, medium_breasts, cum_in_pussy, girl_on_top, smile, straddling

表格版本

#	样本数量	图片示例	标签
0	5		X, X, X, X, X, X, X, X, X, X, X, X, X, X
1	11		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
3	11		X, X, X, X, X, X, X, X, X, X, X, X, X, X
4	8		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
6	5		X, X, X, X, X, X, X, X, X, X, X, X, X, X
7	7		X, X, X, X, X, X, X, X, X, X, X, X, X, X
8	16		X, X, X, X, X, X, X, X, X, X, X, X, X, X

搜集汇总

数据集介绍

构建方式

该数据集由297张羽沢つぐみ（BanG Dream!中的角色）的图像及其标签组成，图像主要来源于danbooru、pixiv和zerochan等多个网站。数据集中包含了角色的核心特征标签，如棕色头发、短发、棕色眼睛和刘海等。同时，数据集还提供了经过自动爬取系统处理的原始数据，以及经过不同尺寸裁剪的图像数据。

使用方法

数据集的使用方法如下：1. 从Hugging Face网站下载所需的图像数据；2. 使用waifuc库加载原始数据，包括带标签的图像；3. 根据研究需求选择合适的图像尺寸进行裁剪；4. 利用数据集进行文本到图像的生成任务或其他相关研究。

背景与挑战

背景概述

在艺术创作与人工智能技术的交融日益紧密的当下，CyberHarem团队推出了名为"hazawa_tsugumi_bangdream"的数据集，致力于推动文本到图像生成领域的进步。该数据集聚焦于羽沢つぐみ这一角色，收录了297张图像及其标签，为研究者提供了丰富的视觉素材。数据集的核心标签包括棕发、短发、棕眼和刘海，这些特征标签的筛选有助于研究者更好地理解和应用该数据集。数据集的构建过程中，DeepGHS团队贡献了自动爬取系统，该系统从多个网站如danbooru、pixiv、zerochan等收集了图像资源，极大地丰富了数据集的内容。此数据集不仅为文本到图像生成领域的研究提供了宝贵的数据支持，也为艺术创作和人工智能技术的结合提供了新的思路。

当前挑战

尽管"hazawa_tsugumi_bangdream"数据集为文本到图像生成领域的研究提供了大量视觉素材，但仍然面临着一些挑战。首先，该数据集的规模相对较小，仅包含297张图像，这可能限制了其在深度学习模型训练中的应用。其次，数据集的构建依赖于自动爬取系统，这可能会引入数据质量的问题，例如图像的清晰度、标签的准确性等。此外，由于数据集专注于单一角色，其在其他角色或场景上的泛化能力可能有限。因此，如何在保持数据集特色的同时，扩大数据规模和提高数据质量，以及如何提高数据集在更多场景下的适用性，是当前面临的主要挑战。

常用场景

经典使用场景

在动漫与游戏产业中，角色形象是吸引粉丝和玩家的重要因素。本数据集包含了羽沢つぐみ这一角色的297张图片及其标签，核心标签包括棕发、短发、棕眼和刘海。这些图片来源于多个网站，如danbooru、pixiv和zerochan等，并通过DeepGHS Team的自动抓取系统进行收集。数据集主要应用于训练文本到图像的生成模型，帮助模型学习如何根据文本描述生成符合特定角色的图像。

解决学术问题

本数据集解决了动漫角色图像生成中存在的多样性和准确性问题。通过收集大量特定角色的图像，并对其进行标签化处理，数据集为文本到图像生成模型提供了丰富的训练数据，有助于提高模型生成图像的准确性和多样性。此外，数据集还提供了不同尺寸和裁剪阶段的图像，方便研究者进行不同尺度和视角下的图像生成研究。

实际应用

本数据集的实际应用场景包括动漫角色形象设计、游戏角色生成和虚拟偶像制作等。通过对羽沢つぐみ这一角色的图像进行学习，模型可以生成具有相似特征的动漫角色图像，满足动漫和游戏产业的需求。此外，数据集还可以用于虚拟偶像的制作，通过生成具有特定角色特征的图像，帮助虚拟偶像在粉丝中建立形象。

数据集最近研究

最新研究方向

在艺术创作领域，特别是文本到图像的生成，CyberHarem/hazawa_tsugumi_bangdream数据集提供了独特的视角。该数据集专注于特定角色的图像，包含297张图像及其标签，为研究者和开发者提供了深入的个案研究素材。随着深度学习技术在图像生成领域的不断进步，该数据集有望推动基于角色的个性化图像生成研究。此外，该数据集的标签聚类结果揭示了特定场景和服饰的图像分布，这为内容挖掘和推荐系统的研究提供了潜在的应用场景。