Hugging Face's logo

anonymous728
/
VORTA

Text-to-Video
Diffusers
Model card Files
xet
Community
3
VORTA / README.md
anonymous728's picture
anonymous728
Update README.md
9984cfb verified
preview code
|
raw
history blame contribute delete
863 Bytes
metadata
license: mit
base_model:
  - Wan-AI/Wan2.1-T2V-14B-Diffusers
  - hunyuanvideo-community/HunyuanVideo
pipeline_tag: text-to-video
library_name: diffusers

VORTA: Efficient Video Diffusion via Routing Sparse Attention

TL;DR - VORTA accelerates video diffusion transformers by sparse attention and dynamic routing, achieving speedup with negligible quality loss.

Quick Start

  1. Download the checkpoints into the ./results directory under the VORTA GitHub code repository.
git lfs install
git clone [email protected]:anonymous728/VORTA
# mv VORTA/<model_name> results/, <model_name>: wan-14B, hunyuan; e.g.
mv VORTA/wan-14B results/

Other alternative methods to download the models can be found here.

  1. Follow the README.md instructions to run the sampling with speedup. 🤗