Skip to content

About

high-performance inference and serving library for interactive autoregressive video and world models

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

518 stars

Watchers

2 watching

Forks

Latest commit

 

History

722 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

FlashDreams

License: Apache 2.0 Documentation

FlashDreams is a high-performance inference and serving library for interactive autoregressive video and world models. It began as the optimized runtime behind the NVIDIA OmniDreams closed-loop demo for GTC 2026 and has grown into a general platform for real-time world-model applications across gaming, autonomous vehicles, robotics, simulated or virtual environments, and more.

Quickstart

The complete setup is in our quick-start guide.

Checkout Our Demos! 🎉

Quick-start to our interactive driving demo is here.

Checkout our game-like crazy-robotaxi demo here.

Developer guides

For Demo Developers

Make demos using world-models with our Demo API.

For Model Developers

Implement world-models with our Inferencing API.

Contributing

For how to contribute, see CONTRIBUTING.md. New integrations, bug reports, feature requests, performance tuning, and documentation edits are all welcome.

Use GitHub Issues to report defects or request improvements.

Join us on the NVIDIA Omniverse Discord to share your results and take part in technical discussion! Channel: #flashdreams

Security

To report a potential security vulnerability, follow the coordinated disclosure process in SECURITY.md.

License

FlashDreams is released under the Apache License 2.0. Third-party components and their licenses are listed in THIRD-PARTY-NOTICES and NOTICE. The repository is REUSE-compliant; see REUSE.toml and LICENSES/. The independently packaged Ludus renderer retains its own Apache license file; upstream cudaraster terms and per-file exceptions are described in the third-party notices.

Citation

If FlashDreams is useful in your research or product, please cite the project:

@misc{flashdreams2026,
  title        = {FlashDreams: High-performance inference and serving for
                  interactive autoregressive video and world models},
  author       = {{FlashDreams Contributors}},
  year         = {2026},
  howpublished = {\url{https://github.com/NVIDIA/flashdreams}},
}

@misc{nvidia2026omnidreams,
  title         = {{NVIDIA} {OmniDreams}: Real-Time Generative World Model for Closed-Loop Autonomous Vehicle Simulation},
  author        = {Basant, Aarti and Kar, Amlan and Paschalidou, Despoina and Wei, Fangyin and Ferroni, Francesco and Garcia Cobo, Guillermo and Turki, Haithem and Ling, Huan and Seo, Jaewoo and Lucas, James and Wu, Jay Zhangjie and Wang, Jialiang and Lorraine, Jonathan and Gao, Jun and He, Kai and Tothova, Katarina and Xie, Kevin and Tyszkiewicz, Micha{\l} and Wu, Qi and de Lutio, Riccardo and Li, Ruilong and Fidler, Sanja and Kim, Seung Wook and Shen, Tianchang and Cao, Tianshi and Pfaff, Tobias and Lew, William and Wu, Xindi and Ren, Xuanchi and Lu, Yifan and Zhang, Yuxuan and Gojcic, Zan and Wang, Zian},
  year          = {2026},
  eprint        = {2606.03159},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CV},
  doi           = {10.48550/arXiv.2606.03159},
  url           = {https://arxiv.org/abs/2606.03159},
}

About

high-performance inference and serving library for interactive autoregressive video and world models

Topics

Resources

Code of conduct

Contributing

Security policy

Stars

518 stars

Watchers

2 watching

Forks

Releases

Packages

Contributors

Languages