A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

SGLang is a fast serving framework for large language models and vision language models.

🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser instance that lets you automate the web without worrying about infrastructure.

The codebase of our paper "Improving the Training of Rectified Flows"

Implementation of rectified flow and some of its followup research / improvements in Pytorch

Minimal implementation of scalable rectified flow transformers, based on SD3's approach

A bibliography and survey of the papers surrounding o1

Creating a diffusion model from scratch in PyTorch to learn exactly how they work.

[AAAI 2023] Exploring CLIP for Assessing the Look and Feel of Images

[CVPR 2024] SinSR: Diffusion-Based Image Super-Resolution in a Single Step

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

An Open Large Reasoning Model for Real-World Solutions

Fast Python implementations of Poisson image editing, using Pytorch and NumPy.

DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model

The Globe from Github's homepage implemented in ThreeJS with beautiful shading.

A suite of image and video neural tokenizers

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

VPTQ, A Flexible and Extreme low-bit quantization algorithm

Official Implementation of LOTUS: Diffusion-based Visual Foundation Model for High-quality Dense Prediction

Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

Google's Operations Research tools:

Vchitect-2.0: Parallel Transformer for Scaling Up Video Diffusion Models

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Efficient Segment Anything in Medical Images

Repo is required for the code of our research paper on micro-budget training of large scale diffusion model.

The official implementation of the EMNLP 2023 paper LLM-FP4

Karras et al. (2022) diffusion models for PyTorch

Official PyTorch implementation of the paper: Flow Matching in Latent Space