Stars
Native and Compact Structured Latents for 3D Generation
cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
Code for "FlashWorld: High-quality 3D Scene Generation within Seconds"
MotionStream: Real-Time Video Generation with Interactive Motion Controls
Official Torch/CUDA Implementation of Faithful Contouring
Industry-level video foundation model for unified Text-to-Video (T2V) and Image-to-Video (I2V) generation.
EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory
(NeurIPS 2024 Oral 🔥) Improved Distribution Matching Distillation for Fast Image Synthesis
SOTAMak1r / Infinite-Forcing
Forked from guandeh17/Self-ForcingInfinite-Forcing: Towards Infinite-Long Video Generation
Official implementation of WorldForge: Unlocking Emergent 3D/4D Generation in Video Diffusion Model via Training-Free Guidance
🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"
A machine learning-based video super resolution and frame interpolation framework. Est. Hack the Valley II, 2018.
A unified inference and post-training framework for accelerated video generation.
SpatialVID: A Large-Scale Video Dataset with Spatial Annotations
Community trainer for Lightricks' LTX Video model 🎬 ⚡️
An open-source toolbox for fast sampling of diffusion models. Official implementations of our works published in ICML, NeurIPS, CVPR, J. Stat. Mech.
Reference implementation of the Transformer architecture optimized for Apple Neural Engine (ANE)
[ICCV 2025 Oral] MVTracker: Multi-view 3D Point Tracking
A lightweight point-based visualization tool used for inspecting Gaussian data, designing camera motion, and exporting setups for external Gaussian renderers.
[3DV 2026 Oral] VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space
[3DV 2026] FastMesh: Efficient Artistic Mesh Generation via Component Decoupling