Alternatives and similar repositories for Cosmos

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

• 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…
  ☆3,679Updated last week
• NVIDIA / Cosmos-Tokenizer
  A suite of image and video neural tokenizers
  ☆1,691Updated 9 months ago
• Tencent-Hunyuan / HunyuanVideo
  HunyuanVideo: A Systematic Framework For Large Video Generation Model
  ☆11,357Updated 2 weeks ago
• Physical-Intelligence / openpi
  ☆9,107Updated 2 weeks ago
• QwenLM / Qwen3-VL
  Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
  ☆16,785Updated last week
• Genesis-Embodied-AI / Genesis
  A generative world for general-purpose robotics & embodied AI learning.
  ☆27,712Updated this week
• manycore-research / SpatialLM
  [NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling
  ☆4,102Updated 2 months ago
• deepseek-ai / Janus
  Janus-Series: Unified Multimodal Understanding and Generation Models
  ☆17,624Updated 10 months ago
• NVlabs / Sana
  SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
  ☆4,761Updated last week
• openvla / openvla
  OpenVLA: An open-source vision-language-action model for robotic manipulation.
  ☆4,573Updated 8 months ago
• microsoft / Magma
  [CVPR 2025] Magma: A Foundation Model for Multimodal AI Agents
  ☆1,867Updated 2 months ago
• facebookresearch / vjepa2
  PyTorch code and models for VJEPA2 self-supervised learning from video.
  ☆2,503Updated 3 months ago
• Wan-Video / Wan2.1
  Wan: Open and Advanced Large-Scale Video Generative Models
  ☆14,798Updated this week
• microsoft / TRELLIS
  Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
  ☆11,109Updated last month
• apple / ml-depth-pro
  Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.
  ☆5,033Updated 7 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…
  ☆1,911Updated 11 months ago
• SandAI-org / MAGI-1
  MAGI-1: Autoregressive Video Generation at Scale
  ☆3,563Updated 5 months ago
• ByteDance-Seed / Bagel
  Open-source unified multimodal model
  ☆5,409Updated last month
• Lightricks / LTX-Video
  Official repository for LTX-Video
  ☆8,850Updated last month
• cambrian-mllm / cambrian
  Cambrian-1 is a family of multimodal LLMs with a vision-centric design.
  ☆1,974Updated 3 weeks ago
• StarsfieldAI / R1-V
  Witness the aha moment of VLM with less than $3.
  ☆3,997Updated 6 months ago
• simplescaling / s1
  s1: Simple test-time scaling
  ☆6,605Updated 5 months ago
• huggingface / nanoVLM
  The simplest, fastest repository for training/finetuning small-sized VLMs.
  ☆4,331Updated last month
• facebookresearch / sapiens
  High-resolution models for human tasks.
  ☆5,233Updated last year
• facebookresearch / chameleon
  Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
  ☆2,068Updated last year
• facebookresearch / sam2
  The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained mode…
  ☆17,881Updated 11 months ago
• genmoai / mochi
  The best OSS video generation models, created by Genmo
  ☆3,521Updated 3 weeks ago
• Jiayi-Pan / TinyZero
  Minimal reproduction of DeepSeek R1-Zero
  ☆12,444Updated 7 months ago
• OpenDriveLab / AgiBot-World
  [IROS 2025 Award Finalist] The Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems
  ☆2,625Updated last month
• NovaSky-AI / SkyThought
  Sky-T1: Train your own O1 preview model within $450
  ☆3,358Updated 4 months ago