Commit
•
e47ae10
1
Parent(s):
3047418
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# This Repository
|
| 6 |
+
|
| 7 |
+
This repository contains pruned `.safetensors` versions of [DragNUWA](https://huggingface.co/yinsming/DragNUWA) uploaded by [yinsming](https://huggingface.co/yinsming). The following text is a copy of that repository's README at time of upload.
|
| 8 |
+
|
| 9 |
+
# DragNUWA
|
| 10 |
+
|
| 11 |
+
**DragNUWA** enables users to manipulate backgrounds or objects within images directly, and the model seamlessly translates these actions into **camera movements** or **object motions**, generating the corresponding video.
|
| 12 |
+
|
| 13 |
+
See our paper: [DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory](https://arxiv.org/abs/2308.08089)
|
| 14 |
+
|
| 15 |
+
Github repository: [https://github.com/ProjectNUWA/DragNUWA](https://github.com/ProjectNUWA/DragNUWA)
|
| 16 |
+
|
| 17 |
+
<a src="https://img.shields.io/badge/%F0%9F%A4%97-Open%20in%20Spaces-blue" href="https://huggingface.co/spaces/yinsming/DragNUWA">
|
| 18 |
+
<img src="https://img.shields.io/badge/%F0%9F%A4%97-Open%20in%20Spaces-blue" alt="Open in Spaces">
|
| 19 |
+
</a>
|
| 20 |
+
<a src="https://colab.research.google.com/assets/colab-badge.svg" href="TOBEDONE">
|
| 21 |
+
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open in Colab">
|
| 22 |
+
</a>
|
| 23 |
+
|
| 24 |
+
### DragNUWA 1.5 (Updated on Jan 8, 2024)
|
| 25 |
+
|
| 26 |
+
**DragNUWA 1.5** enables Stable Video Diffusion to animate an image according to specific path.
|
| 27 |
+
|
| 28 |
+
<p align="center">
|
| 29 |
+
<img src="assets/DragNUWA1.5/Figure1.gif" width="90%">
|
| 30 |
+
</p>
|
| 31 |
+
|
| 32 |
+
<p align="center">
|
| 33 |
+
<img src="assets/DragNUWA1.5/Figure2.gif" width="90%">
|
| 34 |
+
</p>
|
| 35 |
+
<p align="center">
|
| 36 |
+
<img src="assets/DragNUWA1.5/Figure3.gif" width="90%">
|
| 37 |
+
</p>
|
| 38 |
+
<p align="center">
|
| 39 |
+
<img src="assets/DragNUWA1.5/Figure4.gif" width="90%">
|
| 40 |
+
</p>
|
| 41 |
+
|
| 42 |
+
### Citation
|
| 43 |
+
```bibtex
|
| 44 |
+
@article{yin2023dragnuwa,
|
| 45 |
+
title={Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory},
|
| 46 |
+
author={Yin, Shengming and Wu, Chenfei and Liang, Jian and Shi, Jie and Li, Houqiang and Ming, Gong and Duan, Nan},
|
| 47 |
+
journal={arXiv preprint arXiv:2308.08089},
|
| 48 |
+
year={2023}
|
| 49 |
+
}
|
| 50 |
+
```
|
| 51 |
+
|