The official repository of "Astra : General Interactive World Model with Autoregressive Denoising"

Sharp Monocular View Synthesis in Less Than a Second

WorldPlay: Interactive World Modeling with Real-Time Latency and Geometric Consistency

Native and Compact Structured Latents for 3D Generation

An interactive Formula 1 race visualisation and data analysis tool built with Python! 🏎️

Official repository of "Multi-view Pyramid Transformer: Look Coarser to See Broader"

Official implementation of Lotus-2: Advancing Geometric Dense Prediction with Powerful Image Generative Model

[NeurIPS 2025]"DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling"

📷 Camera-controlled text-to-video generation, now with intrinsics, distortion and orientation control!

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation

A tool for running and customizing real-time, interactive generative AI pipelines and models

LongLive: Real-time Interactive Long Video Generation

Glance: Accelerating Diffusion Models with 1 Sample

[arXiv'25] AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend

Official implementation of Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling

ComfyUI nodes for the different projection models and camera movements

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

SAM 3D Objects

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

ComfyUI support for DepthAnything V3 model

Depth Anything 3

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