ChronoMagic

<div align=center>
<img src="https://github.com/PKU-YuanGroup/MagicTime/blob/main/__assets__/magictime_logo.png?raw=true" width="150px">
</div>
<h2 align="center"> <a href="https://pku-yuangroup.github.io/MagicTime/">[TPAMI 2025] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators</a></h2>

<h5 align="center"> If you like our project, please give us a star ⭐ on GitHub for the latest update. </h5>

## 🐳 ChronoMagic Dataset
ChronoMagic with 2265 metamorphic time-lapse videos, each accompanied by a detailed caption. We released the subset of ChronoMagic used to train MagicTime. The dataset can be downloaded at [HuggingFace Dataset](https://huggingface.co/datasets/BestWishYsh/ChronoMagic), or you can download it with the following command. Some samples can be found on our [Project Page](https://pku-yuangroup.github.io/MagicTime/).
```bash
huggingface-cli download --repo-type dataset \
--resume-download BestWishYsh/ChronoMagic \
--local-dir BestWishYsh/ChronoMagic \
--local-dir-use-symlinks False
```

## 💡 Description
- **Repository:** [Code](https://github.com/PKU-YuanGroup/MagicTime), [Page](https://pku-yuangroup.github.io/MagicTime/), [Data](https://huggingface.co/datasets/BestWishYsh/ChronoMagic)
- **Paper:** [https://huggingface.co/papers/2404.05014](https://huggingface.co/papers/2404.05014)
- **Point of Contact:** [Shenghai Yuan]([e-mail])
- **License:** CC-BY-4.0

## ✏️ Citation
If you find our paper and code useful in your research, please consider giving a star and citation.

```BibTeX
@article{yuan2025magictime,
title={Magictime: Time-lapse video generation models as metamorphic simulators},
author={Yuan, Shenghai and Huang, Jinfa and Shi, Yujun and Xu, Yongqi and Zhu, Ruijie and Lin, Bin and Cheng, Xinhua and Yuan, Li and Luo, Jiebo},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2025},
publisher={IEEE}
}
```

<div align=center>
<img src="https://github.com/PKU-YuanGroup/MagicTime/blob/main/__assets__/magictime_logo.png?raw=true" width="150px">
</div>
<h2 align="center"> <a href="https://pku-yuangroup.github.io/MagicTime/">[TPAMI 2025] MagicTime: 作为变形模拟器的延时视频生成模型</a></h2>

<h5 align="center">如果您喜爱本项目，请前往GitHub为我们点亮Star ⭐ 以获取最新动态。</h5>

## 🐳 ChronoMagic 数据集
ChronoMagic 数据集包含2265条变形延时视频，每条视频均配有详细的文本描述。我们公开了用于训练MagicTime的ChronoMagic子集。该数据集可通过[HuggingFace数据集（HuggingFace Dataset）](https://huggingface.co/datasets/BestWishYsh/ChronoMagic)下载，或通过以下命令获取。部分示例可在我们的[项目主页](https://pku-yuangroup.github.io/MagicTime/)查看。
bash
huggingface-cli download --repo-type dataset
--resume-download BestWishYsh/ChronoMagic
--local-dir BestWishYsh/ChronoMagic
--local-dir-use-symlinks False

## 💡 数据集说明
- **代码仓库（Repository):** [代码（Code）](https://github.com/PKU-YuanGroup/MagicTime), [项目主页（Page）](https://pku-yuangroup.github.io/MagicTime/), [数据集（Data）](https://huggingface.co/datasets/BestWishYsh/ChronoMagic)
- **论文（Paper):** [https://huggingface.co/papers/2404.05014](https://huggingface.co/papers/2404.05014)
- **联系方式（Point of Contact):** [袁胜海（Shenghai Yuan）]([e-mail])
- **许可协议（License):** CC-BY-4.0

## ✏️ 引用格式
如果您的研究中用到了本论文或代码，请考虑为我们点亮Star并添加引用。

BibTeX
@article{yuan2025magictime,
title={Magictime: Time-lapse video generation models as metamorphic simulators},
author={Yuan, Shenghai and Huang, Jinfa and Shi, Yujun and Xu, Yongqi and Zhu, Ruijie and Lin, Bin and Cheng, Xinhua and Yuan, Li and Luo, Jiebo},
journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
year={2025},
publisher={IEEE}
}