Alternatives and similar repositories for Cosmos

Users that are interested in Cosmos are comparing it to the libraries listed below

• NVIDIA / Cosmos-Tokenizer
  A suite of image and video neural tokenizers
  ☆1,668Updated 7 months ago
• NVlabs / VILA
  VILA is a family of state-of-the-art vision language models (VLMs) for diverse multimodal AI tasks across the edge, data center, and clou…
  ☆3,539Updated last month
• facebookresearch / sapiens
  High-resolution models for human tasks.
  ☆5,143Updated 9 months ago
• Physical-Intelligence / openpi
  ☆4,971Updated last week
• facebookresearch / vjepa2
  PyTorch code and models for VJEPA2 self-supervised learning from video.
  ☆2,177Updated 2 weeks ago
• NVlabs / Sana
  SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
  ☆4,491Updated this week
• Genesis-Embodied-AI / Genesis
  A generative world for general-purpose robotics & embodied AI learning.
  ☆27,236Updated this week
• manycore-research / SpatialLM
  SpatialLM: Training Large Language Models for Structured Indoor Modeling
  ☆3,942Updated 2 weeks ago
• microsoft / Magma
  [CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents
  ☆1,802Updated 3 months ago
• openvla / openvla
  OpenVLA: An open-source vision-language-action model for robotic manipulation.
  ☆3,819Updated 5 months ago
• NVIDIA / Isaac-GR00T
  NVIDIA Isaac GR00T N1.5 is the world's first open foundation model for generalized humanoid robot reasoning and skills.
  ☆4,881Updated last week
• yangchris11 / samurai
  Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
  ☆6,947Updated 5 months ago
• QwenLM / Qwen2.5-VL
  Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
  ☆12,483Updated 4 months ago
• OpenDriveLab / AgiBot-World
  [IROS 2025] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
  ☆2,353Updated this week
• facebookresearch / jepa
  PyTorch code and models for V-JEPA self-supervised learning from video.
  ☆3,200Updated 6 months ago
• SandAI-org / MAGI-1
  MAGI-1: Autoregressive Video Generation at Scale
  ☆3,481Updated 3 months ago
• eloialonso / diamond
  DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 S…
  ☆1,864Updated 9 months ago
• isaac-sim / IsaacLab
  Unified framework for robot learning built on NVIDIA Isaac Sim
  ☆4,832Updated this week
• facebookresearch / co-tracker
  CoTracker is a model for tracking any point (pixel) on a video.
  ☆4,553Updated 7 months ago
• MoonshotAI / Kimi-k1.5
  ☆3,462Updated 6 months ago
• genmoai / mochi
  The best OSS video generation models, created by Genmo
  ☆3,394Updated last week
• nerfies / nerfies.github.io
  ☆3,511Updated last year
• facebookresearch / lingua
  Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
  ☆4,710Updated last month
• facebookresearch / perception_models
  State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!
  ☆1,607Updated last week
• ByteDance-Seed / Bagel
  Open-source unified multimodal model
  ☆4,993Updated 3 weeks ago
• facebookresearch / dinov3
  Reference PyTorch implementation and models for DINOv3
  ☆6,749Updated last week
• huggingface / lerobot
  🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
  ☆17,289Updated this week
• deepseek-ai / DreamCraft3D
  [ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
  ☆2,968Updated 4 months ago
• stepfun-ai / Step-Video-T2V
  ☆3,108Updated 6 months ago
• huggingface / nanoVLM
  The simplest, fastest repository for training/finetuning small-sized VLMs.
  ☆4,026Updated last week