Stars
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
Robust Speech Recognition via Large-Scale Weak Supervision
🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming
openpilot is an operating system for robotics. Currently, it upgrades the driver assistance system on 300+ supported cars.
YOLOv5 🚀 in PyTorch > ONNX > CoreML > TFLite
CLI platform to experiment with codegen. Precursor to: https://lovable.dev
Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: …
Official Code for DragGAN (SIGGRAPH 2023)
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
A lightweight, dependency-free Python library (and command-line utility) for downloading YouTube Videos.
Generate 3D objects conditioned on text or images
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
PyTorch3D is FAIR's library of reusable components for deep learning with 3D data
A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch
Reverse Engineering: Decompiling Binary Code with Large Language Models
A Python framework for accelerated simulation, data generation and spatial computing.
SUPIR aims at developing Practical Algorithms for Photo-Realistic Image Restoration In the Wild. Our new online demo is also released at suppixel.ai.
ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation
A PyTorch Library for Accelerating 3D Deep Learning Research
Outpainting with Stable Diffusion on an infinite canvas
A procedural Blender pipeline for photorealistic training image generation
The state-of-the-art image restoration model without nonlinear activation functions.
[ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"
A Unified Framework for Surface Reconstruction
Prevent PyTorch's `CUDA error: out of memory` in just 1 line of code.
We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.
NVIDIA Kaolin Wisp is a PyTorch library powered by NVIDIA Kaolin Core to work with neural fields (including NeRFs, NGLOD, instant-ngp and VQAD).
A General NeRF Acceleration Toolbox in PyTorch.