Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,46 @@ pipeline_tag: text-to-video
|
|
| 7 |
|
| 8 |
<p align="center">
|
| 9 |
<h2 align="center"><i>StoryMem</i>: Multi-shot Long Video Storytelling with Memory</h1>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
|
| 11 |
<div align="center">
|
| 12 |
<img src="./assets/teaser.png", width="800">
|
|
@@ -117,3 +157,17 @@ To create your own story script, you can follow the system prompt below, which w
|
|
| 117 |
To improve consistency, it would be better to provide
|
| 118 |
more explicit character descriptions in each shot prompt, helping the model match the intended memory.
|
| 119 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
<p align="center">
|
| 9 |
<h2 align="center"><i>StoryMem</i>: Multi-shot Long Video Storytelling with Memory</h1>
|
| 10 |
+
<p align="center">
|
| 11 |
+
<span class="author-block">
|
| 12 |
+
<a href="https://kevin-thu.github.io/homepage/" target="_blank">Kaiwen Zhang</a>,
|
| 13 |
+
</span>
|
| 14 |
+
<span class="author-block">
|
| 15 |
+
<a href="https://liming-jiang.com/" target="_blank">Liming Jiang</a><sup>✝</sup>,
|
| 16 |
+
</span>
|
| 17 |
+
<span class="author-block">
|
| 18 |
+
<a href="https://angtianwang.github.io/" target="_blank">Angtian Wang</a>,
|
| 19 |
+
</span>
|
| 20 |
+
<span class="author-block">
|
| 21 |
+
<a href="https://www.jacobzhiyuanfang.me/" target="_blank">Jacob Zhiyuan Fang</a>,
|
| 22 |
+
</span><br>
|
| 23 |
+
<span class="author-block">
|
| 24 |
+
<a href="https://tiancheng-zhi.github.io/" target="_blank">Tiancheng Zhi</a>,
|
| 25 |
+
</span>
|
| 26 |
+
<span class="author-block">
|
| 27 |
+
<a href="https://scholar.google.com/citations?user=0TIYjPAAAAAJ&hl=en" target="_blank">Qing Yan</a>,
|
| 28 |
+
</span>
|
| 29 |
+
<span class="author-block">
|
| 30 |
+
<a href="https://scholar.google.com/citations?user=VeTCSyEAAAAJ" target="_blank">Hao Kang</a>,
|
| 31 |
+
</span>
|
| 32 |
+
<span class="author-block">
|
| 33 |
+
<a href="https://scholar.google.com/citations?user=mFC0wp8AAAAJ&hl=en" target="_blank">Xin Lu</a>,
|
| 34 |
+
</span>
|
| 35 |
+
<span class="author-block">
|
| 36 |
+
<a href="https://xingangpan.github.io/" target="_blank">Xingang Pan</a><sup>§</sup>
|
| 37 |
+
</p>
|
| 38 |
+
|
| 39 |
+
<p align="center">
|
| 40 |
+
<sep>✝</sep>Project Lead
|
| 41 |
+
<sep>§</sep>Corresponding Author
|
| 42 |
+
</p>
|
| 43 |
+
|
| 44 |
+
<p align="center">
|
| 45 |
+
<a href="https://arxiv.org/abs/2512.19539"><img alt='arXiv' src="https://img.shields.io/badge/arXiv-2512.19539-b31b1b.svg"></a>
|
| 46 |
+
<a href="https://kevin-thu.github.io/StoryMem/"><img alt='page' src="https://img.shields.io/badge/Project-Website-orange"></a>
|
| 47 |
+
<a href="https://huggingface.co/Kevin-thu/StoryMem"><img alt="Huggingface" src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Model-orange"></a>
|
| 48 |
+
<!-- <a href="https://twitter.com/sze68zkw"><img alt='Twitter' src="https://img.shields.io/twitter/follow/sze68zkw?label=%40KaiwenZhang"></a> -->
|
| 49 |
+
</p>
|
| 50 |
|
| 51 |
<div align="center">
|
| 52 |
<img src="./assets/teaser.png", width="800">
|
|
|
|
| 157 |
To improve consistency, it would be better to provide
|
| 158 |
more explicit character descriptions in each shot prompt, helping the model match the intended memory.
|
| 159 |
|
| 160 |
+
## ❤️ Ackowledgement
|
| 161 |
+
Our implementation is based on [Wan2.2](https://github.com/Wan-Video/Wan2.2/tree/main). Thanks for the great open-source work!
|
| 162 |
+
|
| 163 |
+
## 📌 Citation
|
| 164 |
+
If any part of our paper or code is helpful to your research, please consider citing our work 📝 and give us a star ⭐. Thanks for your support!
|
| 165 |
+
```bibtex
|
| 166 |
+
@article{zhang2025storymem,
|
| 167 |
+
title={{StoryMem}: Multi-shot Long Video Storytelling with Memory},
|
| 168 |
+
author={Zhang, Kaiwen and Jiang, Liming and Wang, Angtian and Fang, Jacob Zhiyuan and Zhi, Tiancheng and Yan, Qing and Kang, Hao and Lu, Xin and Pan, Xingang},
|
| 169 |
+
journal={arXiv preprint},
|
| 170 |
+
volume={arXiv:2512.19539},
|
| 171 |
+
year={2025}
|
| 172 |
+
}
|
| 173 |
+
```
|