Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
An open source code repository of driving world models, with training, inferencing, evaluation tools, and pretrained checkpoints.
| Date | Stars |
|---|---|
| 2026-07-24 | 407 |
| 2026-07-25 | 407 |
| 2026-07-28 | 407 |
| 2026-07-30 | 407 |
| 2026-08-06 | 407 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Open Driving World Models (OpenDWM) [](https://youtu.be/j9RRj-xzOA4) [<img src=https://img.shields.io/badge/%E4%B8%AD%E6%96%87%E7%AE%80%E4%BB%8B-blue>](README_intro_zh.md) https://github.com/user-attachments/assets/649d3b81-3b1f-44f9-9f51-4d1ed7756476 Welcome to the OpenDWM project! This is an open-source initiative, focusing on autonomous driving video generation. Our mission is to provide a high-quality, controllable tool for generating autonomous driving videos using the latest technology. We aim to build a codebase that is both user-friendly and highly reusable, and hope to continuously improve the project through the collective wisdom of the community. The driving world models generate multi-view images or videos of autonomous driving scenes based on text and road environment layout conditions. Whether it's the environment, weather conditions, vehicle type, or driving path, you can adjust them according to your needs. The highlights are as follows: 1. **Transparent and reproducable training.** We provide complete training codes and configurations, allowing everyone to reproduce experiments, fine-tune on their own data, and customize development features as needed. 2. **Significant improvement in the environmental diversity.** Through the use of multiple datasets, the model's generalization ability has been enhanced like never before. Take the example of a generation task controlled by layout conditions, such as a snowy city street or a lakeside highway with distant snow mountains, these scenarios are impossible tasks for generative models trained with a single dataset. 3. **Greatly improved generation quality.** Support for popular model architectures (SD 2.1, 3.5) enables more convenient utilization of the advanced pre-training generation capabilities within the community. Various training techniques, including multitasking and self-supervision, allow the model to utilize the information in autonomous driving video data more effectively. 4. **Convenient evaluation.** Evaluation follows the popular framework `torchmetrics`, which is easy to configure, develop, and integrate into the pipeline. Public configurations (such as FID, FVD on the nuScenes validation set) are provided to align other research works. Furthermore, our code modules are designed with high reusability in mind, for easy application in other projects. Currently, the project has implemented the following papers: > [UniMLVG: Unified Framework for Multi-view Long Video Generation with Comprehensive Control Capabilities for Autonomous Driving](https://sensetime-fvg.github.io/UniMLVG)<br> > Rui Chen<sup>1,2</sup>, Zehuan Wu<sup>2</sup>, Yichen Liu<sup>2</sup>, Yuxin Guo<sup>2</sup>, Jingcheng Ni<sup>2</sup>, Haifeng Xia<sup>1</sup>, Siyu Xia<sup>1</sup><br> > <sup>1</sup>Southeast University <sup>2</sup>SenseTime Research > [MaskGWM: A Generalizable Driving World Model with Video Mask Reconstruction](https://sensetime-fvg.github.io/MaskGWM)<br> > Jingcheng Ni, Yuxin Guo, Yichen Liu, Rui Chen, Lewei Lu, Zehuan Wu<br> > SenseTime Research ## News * [2025/5/6] Release the [CTSD 3.5 with CogVideoX VAE](#video-models) for faster generation. * [2025/4/23] Update the [LiDAR VQVAE (including KITTI-360), LiDAR generation models](#lidar-models), and release the [DFoT on CTSD 3.5 model](#video-models). * [2025/3/17] Experimental release the [Interactive Generation with Carla](docs/InteractiveGeneration.md) * [2025/3/7] Release the [LiDAR Generation](#lidar-models) * [2025/3/4] Release the [CTSD 3.5 with layout condition](#video-models) * [2025/2/7] Release the [UniMLVG](#video-models) ## Setup Hardware requirement: * Training and testing multi-view image generation or short video (<= 6 frames per iteration) generation requires 32GB GPU memory (e.g. V100) * Training and testing multi-view long video (6 ~ 40 frames per iteration) generation requires 80GB GPU memory (e.g. A100, H100) Software requir
Excerpt of 17,141 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:b49f498dd66a71c8, topic:diffusion-models, readme:image generation
matched fp:b49f498dd66a71c8, topic:video-generation, readme:video generation
matched fp:b49f498dd66a71c8, topic:autonomous-driving, readme:autonomous driving