thu-ml/Causal-Forcing

Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation"

42
/ 100
Emerging

This project helps video creators, animators, and content producers generate high-quality, real-time videos from text descriptions or a single image. You provide text prompts or an initial image, and it outputs dynamic video clips with improved visual quality and motion. It's designed for professionals who need efficient, high-fidelity video generation.

456 stars.

Use this if you need to quickly create visually rich and fluid video content from text prompts or an initial image, especially for applications requiring real-time performance.

Not ideal if your primary need is for generating videos longer than a few seconds (81 frames) without additional extensions.

video-generation animation creative-content digital-media real-time-rendering
No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 11 / 25
Community 11 / 25

How are scores calculated?

Stars

456

Forks

21

Language

Python

License

Apache-2.0

Last pushed

Mar 11, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/thu-ml/Causal-Forcing"

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