1.Comfy-Org / ComfyUI
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
Ranked by Attention Score: stars gained over the last 7 complete days
1–100 of 139 by Attention Score · Oct 27, 2026 – Nov 2, 2026 (UTC)
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface. The fastest local inference engine in the world.
A high-throughput and memory-efficient inference and serving engine for LLMs
Non-autoregressive System 1 decision engine. Typed choice, score and yes/no decisions over any text in a single forward pass, in 100+ languages, with a router that picks the right checkpoint per request.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning
🐍 Geometric Computer Vision Library for Spatial AI
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Ultralytics YOLO27, YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking
零基础入门大模型(LLM)的基础教程:从零手写 GPT-2,一行行看懂大模型是怎么工作的 | Build GPT-2 from scratch in PyTorch, step by step
Nano vLLM
GUI for a Vocal Remover that uses Deep Neural Networks.
We write your reusable computer vision tools. 💜
Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.
LMCache: Supercharge Your LLM with the Fastest KV Cache Layer
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
Stable Diffusion web UI
Learn how to develop, deploy and iterate on production-grade ML applications.
Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch). No cloud, no API key.
Learn ML engineering for free in 4 months! Register here 👇🏼
State-of-the-art 2D and 3D Face Analysis Project
Machine Learning Engineering Open Book
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
Don't memorize ML. Understand it from first principles including Inference, Cuda, Deep Learning, Data Science and Reinforcement Learning
OPAL: a reactive optimizer. A coding agent rewrites the optimizer while your model trains.
Lightweight, powerful real-time speech translation with multilingual support and a multilingual UI.
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
Open3D: A Modern Library for 3D Data Processing
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.
FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠
🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production
Free Course : Data, Machine Learning, Deep Learning and AI Engineering, the long way round: the math, the code, the systems and the security. 173 lessons, 166 runnable labs, no shortcuts. Free under CC BY-NC 4.0.
Visualizer for neural network, deep learning and machine learning models
Ultralytics YOLOv5 in PyTorch for object detection, instance segmentation, classification, training, and export.
Real-time, local speech-to-text with streaming ASR, speaker diarization, translation, and OpenAI/Deepgram-compatible APIs.
A collaboration friendly studio for NeRFs
Deep Learning for humans
An open source implementation of CLIP.
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
The fastai deep learning library
ncnn is a high-performance neural network inference framework optimized for the mobile platform
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Document analysis, Multi-model support, and API connectivity for agents.
The Cloud Native AI Platform
人工智能学习路线图,整理近200个实战案例与项目,免费提供配套教材,零基础入门,就业实战!包括:Python,数学,机器学习,数据分析,深度学习,计算机视觉,自然语言处理,PyTorch tensorflow machine-learning,deep-learning data-analysis data-mining mathematics data-science artificial-intelligence python tensorflow tensorflow2 caffe keras pytorch algorithm numpy pandas matplotlib seaborn nlp cv等热门领域
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
Open standard for machine learning interoperability
Python 开源项目之「自学编程之路」,保姆级教程:AI实验室、宝藏视频、数据结构、学习指南、机器学习实战、深度学习实战、网络爬虫、大厂面经、程序人生、资源分享。
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools
🌸 Run LLMs at home, BitTorrent-style. Fine-tuning and inference up to 10x faster than offloading
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
A PyTorch-based Speech Toolkit
Clone a voice in 5 seconds to generate arbitrary speech in real-time
Fast and Accurate ML in 3 Lines of Code
AI Toolkit for Healthcare Imaging
OpenMMLab Detection Toolbox and Benchmark
Low-code framework for building custom LLMs, neural networks, and other AI models
Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.
A unified, comprehensive and efficient recommendation library
A deep learning toolkit for healthcare AI: EHR (MIMIC, eICU, OMOP), clinical text, signals and imaging. 30+ models, reproducible pipelines.
deep learning for image processing including classification and object-detection etc.
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
Techniques for deep learning with satellite & aerial imagery
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
PennyLane is an open-source quantum software platform for quantum computing, quantum machine learning, and quantum chemistry. Create meaningful quantum algorithms, from inspiration to implementation.
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
PyTorch implementation of YOLOv3, YOLOv3-SPP, and YOLOv3-tiny for real-time object detection with training, validation, inference, and multi-format export.
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
OpenMMLab's next-generation platform for general 3D object detection.
Scalable and user friendly neural :brain: forecasting algorithms.
PyTorch Tutorial for Deep Learning Researchers
RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RNN and transformer - great performance, linear time, constant space (no kv-cache), fast training, infinite ctx_len, and free sentence embedding.
超轻量级中文ocr,支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M
This repository contains demos I made with the Transformers library by HuggingFace.
An elegant PyTorch deep reinforcement learning library.
OpenPCDet Toolbox for LiDAR-based 3D Object Detection.
Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
🏆 A ranked list of awesome machine learning Python libraries. Updated weekly.
A comprehensive list of pytorch related content on github,such as different models,implementations,helper libraries,tutorials etc.
State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
A course in reinforcement learning in the wild
ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.
High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.
Portfolio optimization with deep learning.
PyTorch tutorials and fun projects including neural talk, neural style, poem writing, anime generation (《深度学习框架PyTorch:入门与实战》)
A python library for self-supervised learning and latent world models on images.
An open source DevOps tool from the CNCF for packaging and versioning AI/ML models, datasets, code, and configuration into an OCI Artifact.
Image-to-Image Translation in PyTorch
pytorch handbook是一本开源的书籍,目标是帮助那些希望和使用PyTorch进行深度学习开发和研究的朋友快速入门,其中包含的Pytorch教程全部通过测试保证可以成功运行
本项目将《动手学深度学习》(Dive into Deep Learning)原书中的MXNet实现改为PyTorch实现。