NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.
☆11,567Aug 20, 2026Updated this week
Alternatives and similar repositories for cosmos
Users that are interested in cosmos are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Simulation platform for general-purpose robotics & embodied AI learning.☆29,780Updated this week
- A suite of image and video neural tokenizers☆1,733Feb 11, 2025Updated last year
- ☆13,396Jun 16, 2026Updated 2 months ago
- Code to pretrain, fine-tune, and evaluate DreamZero and run sim & real-world evals☆2,572Apr 19, 2026Updated 4 months ago
- NVIDIA Isaac GR00T N1.7 - A Foundation Model for Generalist Robots.☆7,871Aug 10, 2026Updated last week
- 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.
- Our inference and training framework to run on the Cosmos Models☆476Updated this week
- Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…☆816Jun 7, 2026Updated 2 months ago
- SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer☆8,792Updated this week
- [CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer☆14,250May 19, 2026Updated 3 months ago
- PyTorch code and models for VJEPA2 self-supervised learning from video.☆4,487Mar 23, 2026Updated 4 months ago
- [RSS 2026] Causal video-action world model for generalist robot control☆1,784Jul 9, 2026Updated last month
- Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the …☆1,351Jun 8, 2026Updated 2 months ago
- Open-source unified multimodal model☆6,153May 4, 2026Updated 3 months ago
- OpenVLA: An open-source vision-language-action model for robotic manipulation.☆6,855Mar 23, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- A unified inference and post-training framework for accelerated video generation.☆3,989Updated this week
- 🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning☆26,783Updated this week
- Advancing Open-source World Models☆4,376Jul 9, 2026Updated last month
- [IROS 2025 Best Paper Award Finalist & IEEE TRO 2026] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems☆3,146May 29, 2026Updated 2 months ago
- Reference PyTorch implementation and models for DINOv3☆11,216Jul 15, 2026Updated last month
- code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"☆1,286Jul 6, 2026Updated last month
- Wan: Open and Advanced Large-Scale Video Generative Models☆16,869Mar 5, 2026Updated 5 months ago
- The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained mode…☆19,731May 30, 2026Updated 2 months ago
- [CVPR 2025 Highlight] GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control☆1,404Jun 15, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ViPE: Video Pose Engine for Geometric 3D Perception☆2,080Updated this week
- [ICLR 2026] π^3: Permutation-Equivariant Visual Geometry Learning☆2,115Jul 3, 2026Updated last month
- Cosmos-Predict2 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…☆793Oct 29, 2025Updated 9 months ago
- Official implementation of Continuous 3D Perception Model with Persistent State☆1,484Aug 27, 2025Updated 11 months ago
- Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.☆19,810Jan 30, 2026Updated 6 months ago
- Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…☆953Jun 7, 2026Updated 2 months ago
- Cosmos Policy☆854Jan 23, 2026Updated 6 months ago
- Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)☆3,483Sep 12, 2025Updated 11 months ago
- [CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision☆2,788Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- Native Multimodal Models are World Learners☆1,549Dec 30, 2025Updated 7 months ago
- Depth Anything 3☆6,172Jul 27, 2026Updated 3 weeks ago
- Official codebase for Fast-WAM: Do World Action Models Need Test-time Future Imagination?☆1,328Updated this week
- RoboVerse: Towards a Unified Platform, Dataset and Benchmark for Scalable and Generalizable Robot Learning☆1,808Updated this week
- Official Implementation of paper "MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion"☆1,383Jun 16, 2025Updated last year
- Unified framework for robot learning built on NVIDIA Isaac Sim☆7,923Updated this week
- Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"☆1,995Feb 25, 2026Updated 5 months ago