Lists (6)
Stars
Official implementation of "MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second".
A list of works on video generation towards world model
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.
Scaling Novel View Synthesis for Static and Dynamic Scenes
[SIGGRAPH Asia'25] Enabling Reference-based Camera Control via Context without Explicit 3D Estimation
MotionStream: Real-Time Video Generation with Interactive Motion Controls
[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation
A curated collection of fun and creative examples generated with Nano Banana🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the community's development…
A plugin for oh-my-zsh to copy your shell configuration to another machine over ssh.
Native Multimodal Models are World Learners
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.
official repo for ArtiLatent (siggraph asia 2025)
Wan: Open and Advanced Large-Scale Video Generative Models
Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"
Official Implementations for Paper - HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives
[Preprint 2025] Ditto: Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset
Code for "FlashWorld: High-quality 3D Scene Generation within Seconds"
Trace Anything: Representing Any Video in 4D via Trajectory Fields
Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"
An open-source academic paper management tool.
This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation''