Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,74 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model:
|
| 4 |
+
- Wan-AI/Wan2.1-T2V-14B
|
| 5 |
+
pipeline_tag: text-to-video
|
| 6 |
+
---
|
| 7 |
+
<div align="center">
|
| 8 |
+
|
| 9 |
+
<h1>
|
| 10 |
+
Wan-Alpha
|
| 11 |
+
</h1>
|
| 12 |
+
|
| 13 |
+
<h3>Wan-Alpha: High-Quality Text-to-Video Generation with Alpha Channel</h3>
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
[](https://arxiv.org/abs/)
|
| 18 |
+
[](https://donghaotian123.github.io/Wan-Alpha/)
|
| 19 |
+
[](https://huggingface.co/htdong/Wan-Alpha)
|
| 20 |
+
|
| 21 |
+
</div>
|
| 22 |
+
|
| 23 |
+
<img src="assets/teaser.png" alt="Wan-Alpha Qualitative Results" style="max-width: 100%; height: auto;">
|
| 24 |
+
|
| 25 |
+
>Qualitative results of video generation using **Wan-Alpha**. Our model successfully generates various scenes with accurate and clearly rendered transparency. Notably, it can synthesize diverse semi-transparent objects, glowing effects, and fine-grained details such as hair.
|
| 26 |
+
|
| 27 |
+
---
|
| 28 |
+
|
| 29 |
+
## 🔥 News
|
| 30 |
+
* **[2025.09.30]** Released Wan-Alpha v1.0, the Wan2.1-14B-T2V–adapted weights and inference code are now open-sourced.
|
| 31 |
+
|
| 32 |
+
---
|
| 33 |
+
## 🌟 Showcase
|
| 34 |
+
|
| 35 |
+
### Text-to-Video Generation with Alpha Channel
|
| 36 |
+
|
| 37 |
+
|
| 38 |
+
| Prompt | Preview Video | Alpha Video |
|
| 39 |
+
| :---: | :---: | :---: |
|
| 40 |
+
| "Medium shot. A little girl holds a bubble wand and blows out colorful bubbles that float and pop in the air. The background of this video is transparent. Realistic style." | <img src="assets/girl.gif" width="320" height="180" style="object-fit:contain; display:block; margin:auto;"/> | <img src="assets/girl_pha.gif" width="335" height="180" style="object-fit:contain; display:block; margin:auto;"/> |
|
| 41 |
+
|
| 42 |
+
### For more results, please visit [Our Website](https://donghaotian123.github.io/Wan-Alpha/)
|
| 43 |
+
|
| 44 |
+
## 🚀 Quick Start
|
| 45 |
+
|
| 46 |
+
Please see [Github](https://github.com/WeChatCV/Wan-Alpha) for code running details
|
| 47 |
+
```
|
| 48 |
+
|
| 49 |
+
## 🤝 Acknowledgements
|
| 50 |
+
|
| 51 |
+
This project is built upon the following excellent open-source projects:
|
| 52 |
+
* [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio) (training/inference framework)
|
| 53 |
+
* [Wan2.1](https://github.com/Wan-Video/Wan2.1) (base video generation model)
|
| 54 |
+
* [LightX2V](https://github.com/ModelTC/LightX2V) (inference acceleration)
|
| 55 |
+
* [WanVideo_comfy](https://huggingface.co/Kijai/WanVideo_comfy) (inference acceleration)
|
| 56 |
+
|
| 57 |
+
We sincerely thank the authors and contributors of these projects.
|
| 58 |
+
|
| 59 |
+
---
|
| 60 |
+
|
| 61 |
+
## ✏ Citation
|
| 62 |
+
|
| 63 |
+
If you find our work helpful for your research, please consider citing our paper:
|
| 64 |
+
|
| 65 |
+
```bibtex
|
| 66 |
+
@article{
|
| 67 |
+
}
|
| 68 |
+
```
|
| 69 |
+
|
| 70 |
+
---
|
| 71 |
+
|
| 72 |
+
## 📬 Contact Us
|
| 73 |
+
|
| 74 |
+
If you have any questions or suggestions, feel free to reach out via [GitHub Issues](https://github.com/WeChatCV/Wan-Alpha/issues) . We look forward to your feedback!
|