Stars
Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
OpenMMLab Detection Toolbox and Benchmark
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
A playbook for systematically maximizing the performance of deep learning models.
Over 425 terminal color schemes/themes for iTerm/iTerm2. Includes ports to Terminal, Konsole, PuTTY, Xresources, XRDB, Remmina, Termite, XFCE, Tilda, FreeBSD VT, Terminator, Kitty, MobaXterm, LXTer…
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
An unidentifiable mechanism that helps you bypass GFW.
Instant neural graphics primitives: lightning fast NeRF and more
Wan: Open and Advanced Large-Scale Video Generative Models
High-Resolution Image Synthesis with Latent Diffusion Models
High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.
A collection of resources and papers on Diffusion Models
Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).
🐍 Geometric Computer Vision Library for Spatial AI
Code release for NeRF (Neural Radiance Fields)
Real-Time SLAM for Monocular, Stereo and RGB-D Cameras, with Loop Detection and Relocalization Capabilities
Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
[CVPR 2020] 3D Photography using Context-aware Layered Depth Inpainting
A unified framework for 3D content generation.
Infinite Photorealistic Worlds using Procedural Generation
Official repo for consistency models.
The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.