ziplab/BLADE

This is the official PyTorch implementation of "BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation."

27
/ 100
Experimental

This project helps video creators and digital artists generate high-quality videos much faster. You provide existing video generation models (like CogVideoX or WanX) and text prompts, and it produces videos up to six times quicker. It's designed for professionals who need to rapidly produce video content without sacrificing visual quality.

No commits in the last 6 months.

Use this if you are a video content creator or digital artist looking to drastically speed up the generation of AI-powered videos while maintaining high visual quality.

Not ideal if you are creating simple images or very short animations, as the benefits of accelerated video generation may not be as pronounced.

video-generation digital-art content-creation media-production creative-workflows
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 7 / 25
Maturity 7 / 25
Community 11 / 25

How are scores calculated?

Stars

40

Forks

5

Language

Python

License

Last pushed

Oct 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/ziplab/BLADE"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.