Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling

Paper

• Arxiv: Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling

Project Page

• STG Project Page

Todos

• Update README
• Update STG with HunyuanVideo, CogVideoX, Open-Sora, SVD

Acknowledgements

This project is built upon the following works:

• Mochi
• LTX-Video

Start Guide

1. Mochi

   • For installation and requirements, refer to the official repository.

   • Update demos/config.py with your desired settings and simply run:

     python ./demos/cli.py

2. LTX-Video

   • For installation and requirements, refer to the official repository.

   Using CFG (Default Model):

   python inference.py --ckpt_dir './weights' --prompt "A man ..."

   To utilize STG, use the following command:

   python inference.py --ckpt_dir './weights' --prompt "A man ..." --stg_mode stg-a --stg_scale 1.0 --stg_block_idx 19 --do_rescaling True

   Key Parameters:

   • stg_mode: Choose between stg-a or stg-r.
   • stg_scale: Recommended values are ≤2.0.
   • stg_block_idx: Specify the block index for applying STG.
   • do_rescaling: Set to True to enable rescaling.