SenseTime-FVG/OpenDWM
An open source code repository of driving world models, with training, inferencing, evaluation tools, and pretrained checkpoints.
Generates photorealistic multi-view autonomous driving videos with fine-grained control over environment, weather, vehicles, and trajectories through text and spatial layout conditions. Built on diffusion models (SD 2.1/3.5) with cross-view temporal architecture, it combines multi-dataset training for improved generalization and supports both RGB video and LiDAR point cloud generation. Evaluation integrates with torchmetrics on standard benchmarks (nuScenes FVD/FID), and modular code design enables reuse across driving perception and simulation projects.
379 stars. No commits in the last 6 months.
Stars
379
Forks
46
Language
Python
License
MIT
Category
Last pushed
Jun 19, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/SenseTime-FVG/OpenDWM"
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.
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
ModelTC/LightX2V
Light Image Video Generation Inference Framework
Lightricks/LTX-Video
Official repository for LTX-Video