Kevin-thu/Epona
Official Code for Epona: Autoregressive Diffusion World Model for Autonomous Driving (ICCV 2025)
This project helps automotive engineers and researchers developing autonomous driving systems to simulate complex driving scenarios. It takes historical driving data and vehicle trajectories as input and generates realistic, minutes-long driving videos at high resolution. Engineers can use this to test and validate their autonomous vehicle control systems in a simulated environment.
311 stars. No commits in the last 6 months.
Use this if you need to generate detailed, realistic driving simulations for autonomous vehicle development, predict future trajectories, or create long-term driving videos controlled by specific paths.
Not ideal if you are looking for a simple, off-the-shelf driving simulator for non-technical users or if your primary need is real-time vehicle operation rather than research and development.
Stars
311
Forks
21
Language
Python
License
MIT
Category
Last pushed
Jul 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Kevin-thu/Epona"
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