Lists (3)
Stars
StreamDiffusion, Live Stream APP
A part-based 3D generation framework & the largest and most comprehensively annotated 3D part dataset.
StreamingVLM: Real-Time Understanding for Infinite Video Streams
Official Torch/CUDA Implementation of Faithful Contouring
[arXiv 2025] Generative View Stitching
Cosmos-Transfer2.5, built on top of Cosmos-Predict2.5, produces high-quality world simulations conditioned on multiple spatial control inputs.
Krea Realtime 14B. An open-source realtime AI video model.
A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.
Simple IO APIs with pluggable storage backends and rich format handlers.
Official repo for: Epipolar Geometry Improves Video Generation Models
Repository of the paper "AnyUp: Universal Feature Upsampling".
Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
[NeurIPS 2025] Pixel-Perfect Depth
Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for simulating and predicting the future state of the world in the form of video.
Official Repo for Rolling Forcing: Autoregressive Long Video Diffusion in Real Time
HunyuanImage-3.0: A Powerful Native Multimodal Model for Image Generation
Hunyuan3D-Omni: A Unified Framework for Controllable Generation of 3D Assets
A minimal implementation of DeepMind's Genie world model
Official code of paper: MeshMosaic: Scaling Artist Mesh Generation via Local-to-Global Assembly.
Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
Fake Blender Python API module collection for the code completion.
LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.
Open Overleaf/ShareLaTex projects in vscode, with full collaboration support.
[NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"
OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling
Anonymous Github is a proxy server to support anonymous browsing of Github repositories for open-science code and data.