flymin/MagicDrive-V2
[ICCV 2025] Official implementation of the paper “MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control”
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.
Stars
701
Forks
27
Language
Python
License
AGPL-3.0
Category
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.
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