dreambooth

# Dataset Card for "dreambooth"

## Dataset of the Google paper DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation

The dataset includes 30 subjects of 15 different classes. 9 out of these subjects are live subjects (dogs and cats) and 21 are objects. The dataset contains a variable number of images per subject (4-6). Images of the subjects are usually captured in different conditions, environments and under different angles.

We include a file dataset/prompts\_and\_classes.txt which contains all of the prompts used in the paper for live subjects and objects, as well as the class name used for the subjects.

The images have either been captured by the paper authors, or sourced from www.unsplash.com

The dataset/references\_and\_licenses.txt file contains a list of all the reference links to the images in www.unsplash.com - and attribution to the photographer, along with the license of the image.

### [project page](https://dreambooth.github.io/) | [arxiv](https://arxiv.org/abs/2208.12242)

## Academic Citation

If you use this work please cite:
```
@inproceedings{ruiz2023dreambooth,
title={Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation},
author={Ruiz, Nataniel and Li, Yuanzhen and Jampani, Varun and Pritch, Yael and Rubinstein, Michael and Aberman, Kfir},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year={2023}
}
```

## Disclaimer

This is not an officially supported Google product.

# “DreamBooth”数据集卡片
## 谷歌论文《DreamBooth：面向主题驱动生成的文本到图像扩散模型微调》配套数据集
本数据集涵盖15个不同类别下的30个主题样本。其中9个为活体主题（犬类与猫类），剩余21个为物体主题。每个主题的图像数量不固定，介于4至6张之间。这些主题图像通常在不同条件、环境与角度下拍摄。

数据集内附带`dataset/prompts_and_classes.txt`文件，其中收录了论文中用于活体主题与物体主题的全部提示词（Prompt），以及各主题对应的类别名称。

本数据集内的图像要么由论文作者亲自拍摄，要么源自www.unsplash.com平台。

`dataset/references_and_licenses.txt`文件收录了所有来自www.unsplash.com的图像的引用链接、摄影师署名信息，以及对应图像的授权协议。

### [项目主页](https://dreambooth.github.io/) | [arxiv论文](https://arxiv.org/abs/2208.12242)

## 学术引用
若您使用本研究工作，请引用如下文献：

@inproceedings{ruiz2023dreambooth,
title={Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation},
author={Ruiz, Nataniel and Li, Yuanzhen and Jampani, Varun and Pritch, Yael and Rubinstein, Michael and Aberman, Kfir},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year={2023}
}

## 免责声明
本项目并非谷歌官方支持的产品。