nvidia-cosmos / cosmos-predict2Links
Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world models for downstream applications.
☆263Updated this week
Alternatives and similar repositories for cosmos-predict2
Users that are interested in cosmos-predict2 are comparing it to the libraries listed below
Sorting:
- ☆128Updated 5 months ago
- [ArXiv 2025] WorldMem: Long-term Consistent World Simulation with Memory☆170Updated 3 weeks ago
- [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"☆367Updated 3 weeks ago
- Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation☆110Updated this week
- Generative World Explorer☆146Updated last week
- DeepVerse: 4D Autoregressive Video Generation as a World Model☆124Updated 3 weeks ago
- Benchmarking physical understanding in generative video models☆176Updated last month
- Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation☆255Updated 7 months ago
- EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation☆108Updated 7 months ago
- A Video Tokenizer Evaluation Dataset☆125Updated 5 months ago
- Multi-SpatialMLLM Multi-Frame Spatial Understanding with Multi-Modal Large Language Models☆123Updated last month
- PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation (ECCV 2024)☆303Updated 8 months ago
- Aether: Geometric-Aware Unified World Modeling☆358Updated 3 weeks ago
- Official implementation of "Self-Improving Video Generation"☆66Updated 2 months ago
- ☆99Updated 3 months ago
- Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆273Updated last week
- UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, a…☆107Updated 2 months ago
- [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".☆117Updated last week
- CustomDiffusion360: Customizing Text-to-Image Diffusion with Camera Viewpoint Control☆170Updated 6 months ago
- MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance☆122Updated 2 months ago
- Official implementation of Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion☆202Updated last year
- [CVPR 2025] Official code for Using Diffusion Priors for Video Amodal Segmentation☆77Updated 2 weeks ago
- Code release of our paper "DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation".☆105Updated 3 months ago
- A list of works on video generation towards world model☆151Updated this week
- Generative Omnimatte (CVPR 2025)☆100Updated 3 weeks ago
- Official Implementation of Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics☆91Updated 5 months ago
- official repo of paper for "CamI2V: Camera-Controlled Image-to-Video Diffusion Model"☆133Updated 3 months ago
- A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.☆121Updated last week
- Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics☆119Updated last month
- [CVPR2025 Highlight] PAR: Parallelized Autoregressive Visual Generation. https://yuqingwang1029.github.io/PAR-project☆164Updated 3 months ago