Alternatives and similar repositories for cosmos-predict2

Users that are interested in cosmos-predict2 are comparing it to the libraries listed below

• nvidia-cosmos / cosmos-predict1
  Cosmos-Predict1 is a collection of general-purpose world foundation models for Physical AI that can be fine-tuned into customized world m…
  ☆357Updated last month
• nvidia-cosmos / cosmos-transfer1
  Cosmos-Transfer1 is a world-to-world transfer model designed to bridge the perceptual divide between simulated and real-world environment…
  ☆689Updated this week
• kwsong0113 / diffusion-forcing-transformer
  [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"
  ☆512Updated 3 months ago
• GenEx-world / genex
  Generative World Explorer
  ☆157Updated 3 months ago
• google-deepmind / physics-IQ-benchmark
  Benchmarking physical understanding in generative video models
  ☆202Updated last week
• stevenlsw / physgen
  PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation (ECCV 2024)
  ☆311Updated 11 months ago
• xizaoqu / WorldMem
  [NeurIPS 2025] WorldMem: Long-term Consistent World Simulation with Memory
  ☆238Updated last month
• NVIDIA / GR00T-Dreams
  Nvidia GEAR Lab's initiative to solve the robotics data problem using world models
  ☆319Updated last month
• phyworld / phyworld
  ☆143Updated 9 months ago
• nvidia-cosmos / cosmos-reason1
  Cosmos-Reason1 models understand the physical common sense and generate appropriate embodied decisions in natural language through long c…
  ☆736Updated last week
• InternRobotics / Aether
  [ICCV 2025] Aether: Geometric-Aware Unified World Modeling
  ☆490Updated 3 months ago
• SpatialVision / Orient-Anything
  Orient Anything, ICML 2025
  ☆318Updated 4 months ago
• ziangcao0312 / PhysX-3D
  PhysX: Physical-Grounded 3D Asset Generation (NeurIPS 2025, Spotlight)
  ☆273Updated 3 weeks ago
• HorizonRobotics / EmbodiedGen
  Towards a Generative 3D World Engine for Embodied Intelligence
  ☆309Updated last week
• Little-Podi / AdaWorld
  [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".
  ☆161Updated 3 months ago
• yangzhou24 / OmniWorld
  OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
  ☆368Updated 2 weeks ago
• ShuangLI59 / unified_video_action
  Official PyTorch Implementation of Unified Video Action Model (RSS 2025)
  ☆274Updated 2 months ago
• ZCMax / LLaVA-3D
  [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World
  ☆324Updated 3 months ago
• facebookresearch / nwm
  Official code for the CVPR 2025 paper "Navigation World Models".
  ☆406Updated last month
• NVlabs / TokenBench
  A Video Tokenizer Evaluation Dataset
  ☆134Updated 9 months ago
• LatentActionPretraining / LAPA
  [ICLR 2025] LAPA: Latent Action Pretraining from Videos
  ☆381Updated 8 months ago
• facebookresearch / locate-3d
  Open source repo for Locate 3D Model, 3D-JEPA and Locate 3D Dataset
  ☆373Updated 4 months ago
• alibaba-damo-academy / WorldVLA
  WorldVLA: Towards Autoregressive Action World Model
  ☆435Updated last month
• myscience / open-genie
  Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).
  ☆208Updated last year
• basilevh / gcd
  Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation
  ☆270Updated last month
• KwaiVGI / GameFactory
  [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos
  ☆423Updated 6 months ago
• a1600012888 / PhysDreamer
  Code for PhysDreamer
  ☆585Updated 8 months ago
• InternRobotics / Infinite-Mobility
  ☆172Updated 2 months ago
• baaivision / UniVLA
  Unified Vision-Language-Action Model
  ☆203Updated 2 months ago
• AgibotTech / Genie-Envisioner
  ☆280Updated last month