ziplab/BLADE
This is the official PyTorch implementation of "BLADE: Block-Sparse Attention Meets Step Distillation for Efficient Video Generation."
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.
Stars
40
Forks
5
Language
Python
License
—
Category
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.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators