Stars
Official inference framework for 1-bit LLMs
A generative world for general-purpose robotics & embodied AI learning.
Enjoy the magic of Diffusion models!
Expose your FastAPI endpoints as Model Context Protocol (MCP) tools, with Auth!
A collaboration friendly studio for NeRFs
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
Sharp Monocular View Synthesis in Less Than a Second
Open Vision Agents by Stream. Build Vision Agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.
Infinite Photorealistic Worlds using Procedural Generation
[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning.
XLeRobot: Practical Dual-Arm Mobile Home Robot for $660
deepbeepmeep / Wan2GP
Forked from Wan-Video/Wan2.1A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.
Native and Compact Structured Latents for 3D Generation
User-friendly, commercial-grade software for processing aerial imagery.
An extensive node suite that enables ComfyUI to process 3D inputs (Mesh & UV Texture, etc) using cutting edge algorithms (3DGS, NeRF, etc.)
An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities
Official codebase for "Self Forcing: Bridging Training and Inference in Autoregressive Video Diffusion" (NeurIPS 2025 Spotlight)
pySLAM is a hybrid Python/C++ Visual SLAM pipeline supporting monocular, stereo, and RGB-D cameras. It provides a broad set of modern local and global feature extractors, multiple loop-closure stra…
MapAnything: Universal Feed-Forward Metric 3D Reconstruction
The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…
[CVPR 2025 Best Paper Nomination] FoundationStereo: Zero-Shot Stereo Matching