Update README.md
Browse files
README.md
CHANGED
|
@@ -22,9 +22,24 @@ pipeline_tag: image-to-video
|
|
| 22 |
|
| 23 |
- For usage instructions, please see **https://github.com/thu-ml/TurboDiffusion**
|
| 24 |
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Citation
|
| 27 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
@inproceedings{zhang2025sageattention,
|
| 29 |
title={SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration},
|
| 30 |
author={Zhang, Jintao and Wei, Jia and Zhang, Pengle and Zhu, Jun and Chen, Jianfei},
|
|
|
|
| 22 |
|
| 23 |
- For usage instructions, please see **https://github.com/thu-ml/TurboDiffusion**
|
| 24 |
|
| 25 |
+
- [**TurboDiffusion Technical Report**](https://jt-zhang.github.io/files/TurboDiffusion_Technical_Report.pdf): Accelerating Video Generation by 100--205 Times
|
| 26 |
+
|
| 27 |
|
| 28 |
## Citation
|
| 29 |
```
|
| 30 |
+
@article{zhang2025turbodiffusion,
|
| 31 |
+
title={TurboDiffusion Technical Report: Accelerating Video Generation by 100--205 Times},
|
| 32 |
+
author={Zhang, Jintao and Zheng, Kaiwen and Jiang, Kai and Wang, Haoxu and Stoica, Ion and Gonzalez, Joseph E. and Chen, Jianfei and Zhu, Jun},
|
| 33 |
+
year={2025}
|
| 34 |
+
}
|
| 35 |
+
|
| 36 |
+
@software{turbodiffusion2025,
|
| 37 |
+
title={TurboDiffusion: Accelerating Video Generation by 100--205 Times},
|
| 38 |
+
author = {The TurboDiffusion Team},
|
| 39 |
+
url = {https://github.com/thu-ml/TurboDiffusion},
|
| 40 |
+
year={2025}
|
| 41 |
+
}
|
| 42 |
+
|
| 43 |
@inproceedings{zhang2025sageattention,
|
| 44 |
title={SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration},
|
| 45 |
author={Zhang, Jintao and Wei, Jia and Zhang, Pengle and Zhu, Jun and Chen, Jianfei},
|