Alternatives and similar repositories for cosmos-predict2

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

• google-deepmind / physics-IQ-benchmark
  Benchmarking physical understanding in generative video models
  ☆182Updated last month
• phyworld / phyworld
  ☆129Updated 6 months ago
• xizaoqu / WorldMem
  [ArXiv 2025] WorldMem: Long-term Consistent World Simulation with Memory
  ☆176Updated last month
• kwsong0113 / diffusion-forcing-transformer
  [ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"
  ☆394Updated 2 weeks ago
• stevenlsw / physgen
  PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation (ECCV 2024)
  ☆304Updated 8 months ago
• GenEx-world / genex
  Generative World Explorer
  ☆148Updated last month
• 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…
  ☆290Updated 3 weeks ago
• 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…
  ☆537Updated last week
• SpatialVision / Orient-Anything
  Orient Anything, ICML 2025
  ☆292Updated 2 months ago
• NVlabs / TokenBench
  A Video Tokenizer Evaluation Dataset
  ☆127Updated 6 months ago
• Video-as-Agent / VideoAgent
  Official implementation of "Self-Improving Video Generation"
  ☆67Updated 2 months ago
• liuff19 / LangScene-X
  [ICCV 2025] LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion
  ☆232Updated last week
• SOTAMak1r / DeepVerse
  DeepVerse: 4D Autoregressive Video Generation as a World Model
  ☆129Updated 3 weeks ago
• Little-Podi / AdaWorld
  [ICML'25] The PyTorch implementation of paper: "AdaWorld: Learning Adaptable World Models with Latent Actions".
  ☆125Updated last month
• zzyunzhi / scene-language
  (CVPR 2025 Highlight) The Scene Language: Representing Scenes with Programs, Words, and Embeddings
  ☆224Updated this week
• OpenRobotLab / Aether
  [ICCV 2025] Aether: Geometric-Aware Unified World Modeling
  ☆388Updated last week
• basilevh / gcd
  Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation
  ☆257Updated 8 months ago
• facebookresearch / Multi-SpatialMLLM
  Multi-SpatialMLLM Multi-Frame Spatial Understanding with Multi-Modal Large Language Models
  ☆133Updated last month
• KwaiVGI / GameFactory
  [ICCV 2025] GameFactory: Creating New Games with Generative Interactive Videos
  ☆325Updated 3 months ago
• haoyi-duan / WorldScore
  Official implementation for WorldScore: A Unified Evaluation Benchmark for World Generation
  ☆114Updated 2 weeks ago
• ZCMax / LLaVA-3D
  [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World
  ☆281Updated this week
• Hritikbansal / videophy
  Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics
  ☆127Updated 2 months ago
• KwaiVGI / RoboMaster
  [ARXIV’25] Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control
  ☆71Updated last week
• vlongle / articulate-anything
  [ICLR 2025] Official implementation of Articulate-Anything
  ☆115Updated last week
• JeffWang987 / EgoVid
  EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation
  ☆109Updated 8 months ago
• liuff19 / Video-T1
  [ICCV 2025] Video-T1: Test-Time Scaling for Video Generation
  ☆278Updated 2 weeks ago
• a1600012888 / LaCT
  Code release for paper "Test-Time Training Done Right"
  ☆176Updated last week
• baaivision / UniVLA
  Unified Vision-Language-Action Model
  ☆128Updated 2 weeks ago
• HVision-NKU / DepthAnythingAC
  Official code for the paper: Depth Anything At Any Condition
  ☆227Updated last week
• imlixinyang / Director3D
  Code for "Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text" (NeurIPS 2024).
  ☆351Updated 4 months ago