Alternatives and similar repositories for Cosmos:

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

• QwenLM / Qwen2.5-VL
  Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
  ☆10,262Updated this week
• NVIDIA / Cosmos-Tokenizer
  A suite of image and video neural tokenizers
  ☆1,621Updated 2 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…
  ☆3,201Updated last week
• Physical-Intelligence / openpi
  ☆3,189Updated last week
• yangchris11 / samurai
  Official repository of "SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory"
  ☆6,747Updated last month
• NVIDIA / Isaac-GR00T
  NVIDIA Isaac GR00T N1 is the world's first open foundation model for generalized humanoid robot reasoning and skills.
  ☆3,635Updated 3 weeks ago
• manycore-research / SpatialLM
  SpatialLM: Large Language Model for Spatial Understanding
  ☆3,132Updated last month
• Genesis-Embodied-AI / Genesis
  A generative world for general-purpose robotics & embodied AI learning.
  ☆24,924Updated this week
• deepseek-ai / Janus
  Janus-Series: Unified Multimodal Understanding and Generation Models
  ☆17,204Updated 3 months ago
• microsoft / Magma
  [CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents
  ☆1,623Updated this week
• eloialonso / diamond
  DIAMOND (DIffusion As a Model Of eNvironment Dreams) is a reinforcement learning agent trained in a diffusion world model. NeurIPS 2024 S…
  ☆1,804Updated 5 months ago
• deepseek-ai / DeepSeek-VL
  DeepSeek-VL: Towards Real-World Vision-Language Understanding
  ☆3,816Updated last year
• deepseek-ai / DeepSeek-VL2
  DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding
  ☆4,793Updated 2 months ago
• NVlabs / Sana
  SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
  ☆4,098Updated this week
• SandAI-org / MAGI-1
  MAGI-1: Autoregressive Video Generation at Scale
  ☆2,857Updated last week
• deepseek-ai / DreamCraft3D
  [ICLR 2024] Official implementation of DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
  ☆2,920Updated 2 weeks ago
• MoonshotAI / Kimi-k1.5
  ☆3,325Updated 2 months ago
• openvla / openvla
  OpenVLA: An open-source vision-language-action model for robotic manipulation.
  ☆2,710Updated last month
• deepseek-ai / DeepSeek-V2
  DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
  ☆4,887Updated 7 months ago
• deepseek-ai / DeepSeek-Coder-V2
  DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
  ☆5,711Updated 7 months ago
• meta-llama / llama-stack
  Composable building blocks to build Llama Apps
  ☆7,766Updated this week
• QwenLM / Qwen2.5-Omni
  Qwen2.5-Omni is an end-to-end multimodal model by Qwen team at Alibaba Cloud, capable of understanding text, audio, vision, video, and pe…
  ☆2,867Updated this week
• apple / ml-4m
  4M: Massively Multimodal Masked Modeling
  ☆1,719Updated 2 months ago
• landing-ai / vision-agent
  Vision agent
  ☆4,558Updated this week
• volcengine / verl
  verl: Volcano Engine Reinforcement Learning for LLMs
  ☆7,626Updated this week
• NVlabs / describe-anything
  Implementation for Describe Anything: Detailed Localized Image and Video Captioning
  ☆908Updated last week
• microsoft / TRELLIS
  Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
  ☆9,293Updated last week
• unslothai / unsloth
  Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
  ☆38,242Updated this week
• facebookresearch / jepa
  PyTorch code and models for V-JEPA self-supervised learning from video.
  ☆2,979Updated 2 months ago
• agentica-project / rllm
  Democratizing Reinforcement Learning for LLMs
  ☆3,182Updated 3 weeks ago