flymin/MagicDrive-V2

[ICCV 2025] Official implementation of the paper “MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control”

40
/ 100
Emerging

This project helps autonomous driving researchers and developers create realistic, high-resolution, and long street-view videos. By taking detailed 3D geometry and motion controls as input, it generates diverse video sequences that simulate real-world driving conditions with consistent views. It's designed for professionals working on training and testing autonomous vehicle systems.

701 stars. No commits in the last 6 months.

Use this if you need to generate synthetic street-view videos with precise control over 3D geometry and motion for autonomous driving research and development.

Not ideal if you are looking for a general-purpose video generation tool unrelated to autonomous driving simulations.

autonomous-driving synthetic-data-generation vehicle-simulation robotics computer-vision-research
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

701

Forks

27

Language

Python

License

AGPL-3.0

Last pushed

Jun 26, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/flymin/MagicDrive-V2"

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