Update README.md
#1
by
anonymous728
- opened
README.md
CHANGED
|
@@ -1,3 +1,25 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model:
|
| 4 |
+
- Wan-AI/Wan2.1-T2V-14B-Diffusers
|
| 5 |
+
- hunyuanvideo-community/HunyuanVideo
|
| 6 |
+
pipeline_tag: text-to-video
|
| 7 |
+
library_name: diffusers
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# VORTA: Efficient Video Diffusion via Routing Sparse Attention
|
| 11 |
+
|
| 12 |
+
> TL;DR - VORTA accelerates video diffusion transformers by sparse attention and dynamic routing, achieving speedup with negligible quality loss.
|
| 13 |
+
|
| 14 |
+
|
| 15 |
+
## Quick Start
|
| 16 |
+
|
| 17 |
+
1. Download the checkpoints into the `./results` directory under the VORTA GitHub code repository.
|
| 18 |
+
```bash
|
| 19 |
+
git lfs install
|
| 20 |
+
git clone [email protected]:anonymous728/VORTA
|
| 21 |
+
```
|
| 22 |
+
_Other alternative methods to download the models can be found [here](https://huggingface.co/docs/hub/models-downloading#using-git)._
|
| 23 |
+
|
| 24 |
+
|
| 25 |
+
2. Follow the `README.md` instructions to run the sampling with speedup. 🤗
|