Models3118 projects

Robust Speech Recognition via Large-Scale Weak Supervision

Leading open-weight LLM series by DeepSeek. Mixture-of-Experts architecture, competitive with top proprietary models.

Open Source Computer Vision Library

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Tesseract Open Source OCR Engine (main repository)

A latent text-to-image diffusion model

Powerful node-based Stable Diffusion workflow editor. Modular pipeline for advanced image generation.

AI that turns screenshots into code. Drop in an image, get HTML/CSS/JS out. Supports Tailwind CSS.

Stability AI's foundational text-to-image model. Open weights, high quality, huge ecosystem of tools.

Meta's open-source LLM family. State-of-the-art performance, available in 8B to 405B parameters.

Clone a voice in 5 seconds to generate arbitrary speech in real-time

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Ultralytics YOLO26, YOLO11, YOLOv8 — object detection, instance segmentation, semantic segmentation, image classification, pose estimation, object tracking

Ultralytics YOLOv5 in PyTorch > ONNX > CoreML > TFLite

The world's simplest facial recognition api for Python and the command line

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

Image generation platform with offline capabilities. Focus on usability, minimal prompt engineering needed.

Deep learning text-to-speech. Supports 1100+ languages, voice cloning, and fine-tuning.

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

TensorFlow code and pre-trained models for BERT

A generative speech model for daily dialogue.

🔊 Text-Prompted Generative Audio Model

Pure Javascript OCR for more than 100 Languages 📖🎉🖥

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

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

🚀Clone a voice in 5 seconds to generate arbitrary speech in real-time

Instant voice cloning by MIT and MyShell. Audio foundation model.

Real-ESRGAN aims at developing Practical Algorithms for General Image/Video Restoration.

Cross-platform, customizable ML solutions for live and streaming media.

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

Let us control diffusion models!

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

OpenMMLab Detection Toolbox and Benchmark

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Real-time face swap for PC streaming or video calls

Code and documentation to train Stanford's Alpaca models, and generate the data.

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

State-of-the-art 2D and 3D Face Analysis Project

Deezer source separation library including pretrained models.

SoftVC VITS Singing Voice Conversion

Invoke is a leading creative engine for Stable Diffusion models, empowering professionals, artists, and enthusiasts to generate and create visual media using the latest AI-driven technologies. The solution offers an industry leading WebUI, and serves as the foundation for multiple commercial products.

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Generative Models by Stability AI

DeepSpeech is an open source embedded (offline, on-device) speech-to-text engine which can run in real time on devices ranging from a Raspberry Pi 4 to high power GPU servers.

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

SoTA open-source TTS

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Image-to-Image Translation in PyTorch

Code for the paper "Language Models are Unsupervised Multitask Learners"

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training

DeepSeek Coder: Let the Code Write Itself

Contexts Optical Compression

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

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

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Meta's generative audio AI. MusicGen for music, AudioGen for sound effects, and EnCodec for compression.

An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

FinGPT: Open-Source Financial Large Language Models! Revolutionize 🔥 We release the trained model on HuggingFace.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

A TTS model capable of generating ultra-realistic dialogue in one pass.

Industrial-grade speech recognition toolkit: 170x realtime, 50+ languages, speaker diarization, emotion detection, streaming, and OpenAI-compatible API.

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Bring portraits to life!

Torch implementation of neural style algorithm

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

Open-source multimodal LLM with vision, speech, and text. Strong performance on mobile and edge devices.

Stable Diffusion with Core ML on Apple Silicon

JavaScript API for face detection and face recognition in the browser and nodejs with tensorflow.js

Janus-Series: Unified Multimodal Understanding and Generation Models

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Instant neural graphics primitives: lightning fast NeRF and more

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.

Wan: Open and Advanced Large-Scale Video Generative Models

Wan: Open and Advanced Large-Scale Video Generative Models

pix2tex: Using a ViT to convert images of equations into LaTeX code.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

GPT-3: Language Models are Few-Shot Learners

Bringing Old Photo Back to Life (CVPR 2020 oral)

StableLM: Stability AI Language Models

kaldi-asr/kaldi is the official location of the Kaldi project.

Face recognition with deep neural networks.

End-to-End Object Detection with Transformers

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.

Face recognition using Tensorflow

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

High-Resolution Image Synthesis with Latent Diffusion Models

An open source implementation of CLIP.

🚀 Truly open-source AI avatar(digital human) toolkit for offline video generation and digital human cloning.

20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.

Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages

PaddleFormers is an easy-to-use library of pre-trained large language model zoo based on PaddlePaddle.

Easy-to-use and powerful LLM and SLM library with awesome model zoo.

Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX.

Software that can generate photos from paintings, turn horses into zebras, perform style transfer, and more.

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

Enjoy the magic of Diffusion models!

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System, End-to-End Speech Translation and Keyword Spotting. Won NAACL2022 Best Demo Award.

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

HunyuanVideo: A Systematic Framework For Large Video Generation Model

OCR & Document Extraction using vision models

100+ Chinese Word Vectors 上百种预训练中文词向量

An open-source tool-augmented conversational language model from Fudan University

COLMAP - Structure-from-Motion and Multi-View Stereo

Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch

Meta's AI that brings children's drawings to life. Automatically animates humanoid figures.

An open-source NLP research library, built on PyTorch.

Super Resolution for images using deep learning.

A collaboration friendly studio for NeRFs

A PyTorch-based Speech Toolkit

Semantic segmentation models with 500+ pretrained convolutional and transformer-based backbones.

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

A paper list of object detection using deep learning.

YOLOv10: Real-Time End-to-End Object Detection [NeurIPS 2024]

🐍 Geometric Computer Vision Library for Spatial AI

LAVIS - A One-stop Library for Language-Vision Intelligence

A fast, local neural text to speech system

一款入门级的人脸、视频、文字检测以及识别的项目.

"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator All-in-One)"

Custom photo generation with Stable Diffusion. Generate personalized images from a few photos.

TensorFlow CNN for fast style transfer ⚡🖥🎨🖼

[CVPR 2024] Official repository for "MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model"

Kimi K2 is the large language model series developed by Moonshot AI team

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

Image-to-image translation with conditional adversarial nets

Ultralytics YOLOv3 in PyTorch > ONNX > CoreML > TFLite

YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

An easy 1-click way to create beautiful artwork on your PC using AI, with no tech knowledge. Provides a browser UI for generating images from text prompts and images. Just enter your text prompt, and see the generated image.

[ECCV 2024] Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

Pre-Training with Whole Word Masking for Chinese BERT（中文BERT-wwm系列模型）

AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

:robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

A robust, efficient, low-latency speech-to-text library with advanced voice activity detection, wake word activation and instant transcription.

Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.

End-to-End Speech Processing Toolkit

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

Best Practices, code samples, and documentation for Computer Vision.

tiny vision language model

The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."

A PyTorch implementation of the Transformer model in "Attention is All You Need".

ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.

A modern approach for Computer Vision on the web

Robust Video Matting in PyTorch, TensorFlow, TensorFlow.js, ONNX, CoreML!

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

Easy-to-use image segmentation library with awesome pre-trained model zoo, supporting wide-range of practical tasks in Semantic Segmentation, Interactive Segmentation, Panoptic Segmentation, Image Matting, 3D Segmentation, etc.

Keras implementations of Generative Adversarial Networks.

Multilingual Document Layout Parsing in a Single Vision-Language Model

Speech recognition module for Python, supporting several engines and APIs, online and offline.

A python library built to empower developers to build applications and systems with self-contained Computer Vision capabilities

Text-to-3D & Image-to-3D & Mesh Exportation with NeRF + Diffusion.

Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.

CodeGeeX: An Open Multilingual Code Generation Model (KDD 2023)

[NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. of "Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction". An *ultra-simple, user-friendly yet state-of-the-art* codebase for autoregressive image generation!

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces

EmotiVoice 😊: a Multi-Voice and Prompt-Controlled TTS Engine

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

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.

Text-audio foundation model from Boson AI

Official Python inference and LoRA trainer package for the LTX-2 audio–video generative model.

Leading free and open-source face recognition system

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, Wav2Lip, picture repair, image editing, photo2cartoon, image style transfer, GPEN, and so on.

Code for the paper "Jukebox: A Generative Model for Music"

PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models

all kinds of text classification models and more with deep learning

An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io/vallex/

fast-stable-diffusion + DreamBooth

Run Stable Diffusion on Mac natively

Stable Diffusion web UI

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

Chinese version of GPT2 training code, using BERT tokenizer.

⚡ TabPFN: Foundation Model for Tabular Data ⚡

Object detection, 3D detection, and pose estimation using center point detection:

CodeGeeX2: A More Powerful Multilingual Code Generation Model