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.
☆786Oct 29, 2025Updated 8 months ago
Alternatives and similar repositories for cosmos-predict2
Users that are interested in cosmos-predict2 are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆807Jun 7, 2026Updated 3 weeks ago
- Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆458Jun 7, 2026Updated 3 weeks ago
- DreamGen: Nvidia GEAR Lab's initiative to solve the robotics data problem using world models☆585Oct 24, 2025Updated 8 months ago
- Cosmos Curator is a powerful video curation system that processes, analyzes, and organizes video content using advanced AI models and dis…☆224Jun 11, 2026Updated 3 weeks ago
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆1,309Jun 8, 2026Updated 3 weeks ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆950Jun 7, 2026Updated 3 weeks ago
- [ICLR’26] Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control☆108Feb 8, 2026Updated 4 months ago
- [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control☆1,377Jun 15, 2026Updated 3 weeks ago
- A suite of image and video neural tokenizers☆1,724Feb 11, 2025Updated last year
- [ICLR 2026] Codebase for paper "Geometry-aware 4D Video Generation for Robot Manipulation"☆123Jan 10, 2026Updated 5 months ago
- Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models☆505Mar 10, 2026Updated 3 months ago
- [SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control☆822Jun 9, 2025Updated last year
- Official PyTorch Implementation of Unified Video Action Model (RSS 2025)☆393Jul 23, 2025Updated 11 months ago
- [ICCV 2025 & ICCV 2025 RIWM Outstanding Paper] Aether: Geometric-Aware Unified World Modeling☆598Oct 26, 2025Updated 8 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomou…☆10,890Updated this week
- Official repository of Learning to Act from Actionless Videos through Dense Correspondences.☆261Apr 25, 2024Updated 2 years ago
- [T-PAMI 2025] V3D: Video Diffusion Models are Effective 3D Generators☆519Mar 26, 2024Updated 2 years ago
- Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"☆1,376Jun 16, 2025Updated last year
- [ICCV 2025] DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness☆187Feb 11, 2026Updated 4 months ago
- ☆100Sep 4, 2024Updated last year
- [TPAMI 2025] ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis☆1,567Dec 13, 2025Updated 6 months ago
- Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression☆41Feb 17, 2025Updated last year
- Distributed Robot Interaction Dataset.☆377Sep 15, 2025Updated 9 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆4,292Mar 23, 2026Updated 3 months ago
- Code for ICCV'2025 (Best student paper honorable mention) "RayZer: A Self-supervised Large View Synthesis Model"☆440Nov 24, 2025Updated 7 months ago
- Official Repo for Self-Forcing++ High Quality Long Video Generation☆263Oct 13, 2025Updated 8 months ago
- [ICLR 2026 Oral] DiffusionNFT: Online Diffusion Reinforcement with Forward Process☆943Feb 10, 2026Updated 4 months ago
- [CVPR 2026] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations☆573Apr 22, 2026Updated 2 months ago
- ☆129Apr 18, 2025Updated last year
- [ICLR 2026] Streaming 4D Visual Geometry Transformer☆933Oct 27, 2025Updated 8 months ago
- Official implementation of Continuous 3D Perception Model with Persistent State☆1,445Aug 27, 2025Updated 10 months ago
- [ICCV 2025, Oral] TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models☆856Dec 17, 2025Updated 6 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICLR 2026] OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling☆484Apr 16, 2026Updated 2 months ago
- (CVPR 2025) From Slow Bidirectional to Fast Autoregressive Video Diffusion Models☆1,382Aug 7, 2025Updated 10 months ago
- Official code for NeurIPS 2024 paper LRM-Zero: Training Large Reconstruction Models with Synthesized Data☆154Oct 7, 2024Updated last year
- News: the 10k dataset is ready for download.☆643Feb 10, 2026Updated 4 months ago
- Scalable and memory-optimized training of diffusion models☆1,358May 26, 2026Updated last month
- ICCV 2025 | TesserAct: Learning 4D Embodied World Models☆401Aug 4, 2025Updated 11 months ago
- [ICLR 2025] LAPA: Latent Action Pretraining from Videos☆549Jan 22, 2025Updated last year