README.md

OpenVINO Notebooks

OpenVINO™ Notebooks at GitHub Pages

AI Trends

• Video generation with ZeroScope and OpenVINO
• Convert and Optimize YOLOv9 with OpenVINO™
• Convert and Optimize YOLOv8 real-time object detection with OpenVINO™
• YOLOv8 Oriented Bounding Boxes Object Detection with OpenVINO™
• Convert and Optimize YOLOv8 keypoint detection model with OpenVINO™
• Convert and Optimize YOLOv8 instance segmentation model with OpenVINO™
• Convert and Optimize YOLOv12 real-time object detection with OpenVINO™
• Convert and Optimize YOLOv11 real-time object detection with OpenVINO™
• Convert and Optimize YOLOv11 keypoint detection model with OpenVINO™
• Convert and Optimize YOLOv11 instance segmentation model with OpenVINO™
• Convert and Optimize YOLOv10 with OpenVINO
• Video Subtitle Generation using Whisper and OpenVINO™
• Automatic speech recognition using Whisper and OpenVINO with Generate API
• Wav2Lip: Accurately Lip-syncing Videos and OpenVINO
• Image Generation with Tiny-SD and OpenVINO™
• Text to Image pipeline and OpenVINO with Generate API
• Line-level text detection with Surya
• Image to Video Generation with Stable Video Diffusion
• Stable Fast 3D Mesh Reconstruction and OpenVINO
• Image generation with Stable Diffusion XL and OpenVINO
• Image generation with Torch.FX Stable Diffusion v3 and OpenVINO
• Image generation with Stable Diffusion v3 and OpenVINO
• Infinite Zoom Stable Diffusion v2 and OpenVINO™
• Stable Diffusion with KerasCV and OpenVINO
• Image Generation with Stable Diffusion and IP-Adapter
• Image generation with Stable Cascade and OpenVINO
• Sound Generation with Stable Audio Open and OpenVINO™
• Sound Generation with AudioLDM2 and OpenVINO™
• Visual-Language Assistant with SmolVLM2 and OpenVINO
• Document conversion with SmolDocling and OpenVINO
• Zero-shot Image Classification with SigLIP2
• Object masks from prompts with SAM and OpenVINO
• Single step image generation using SDXL-turbo and OpenVINO
• Image generation with Sana and OpenVINO
• Object masks from prompts with SAM2 and OpenVINO
• Object masks from prompts with SAM2 and OpenVINO for Images
• Visual-language assistant with Qwen2.5VL and OpenVINO
• Omnimodal assistant with Qwen2.5-Omni and OpenVINO
• Visual-language assistant with Qwen2VL and OpenVINO
• Audio-language assistant with Qwen2Audio and OpenVINO
• Generate creative QR codes with ControlNet QR Code Monster and OpenVINO™
• Visual-language assistant with Pixtral and OpenVINO
• Text-to-image generation using PhotoMaker and OpenVINO
• Multimodal assistant with Phi-4-multimodal and OpenVINO
• Visual-language assistant with Phi3-Vision and OpenVINO
• Voice tone cloning with OpenVoice and OpenVINO
• Running OpenCLIP models using OpenVINO™
• Screen Parsing with OmniParser-v2.0 and OpenVINO
• Unified image generation using OmniGen and OpenVINO
• PDF converting with olmOCR model and OpenVINO
• Structure Extraction with NuExtract and OpenVINO
• Visual-language assistant with nanoLLaVA and OpenVINO
• Controllable Music Generation with MusicGen and OpenVINO
• Multimodal RAG for video analytics with LlamaIndex
• Multi LoRA Image Generation
• Visual Content Search using MobileCLIP and OpenVINO
• Visual-language assistant with Llama-3.2-11B-Vision and OpenVINO
• Visual-language assistant with MiniCPM-V2 and OpenVINO
• Omnimodal assistant with MiniCPM-o 2.6 and OpenVINO
• Magika: AI powered fast and efficient file type identification using OpenVINO
• LTX Video and OpenVINO™
• Create a RAG system using OpenVINO and LlamaIndex
• Create a RAG system using OpenVINO and LangChain
• Create a RAG system using OpenVINO GenAI and LangChain
• LLM Instruction-following pipeline with OpenVINO
• Create a native Agent with OpenVINO
• Create an LLM-powered Chatbot using OpenVINO
• Create an LLM-powered Chatbot using OpenVINO Generate API
• Create ReAct Agent using OpenVINO and LangChain
• Create an Agentic RAG using OpenVINO and LlamaIndex
• Create Function-calling Agent using OpenVINO and Qwen-Agent
• Visual-language assistant with LLaVA Next and OpenVINO
• Visual-language assistant with LLaVA and Optimum Intel OpenVINO integration
• Visual-language assistant with LLaVA and OpenVINO Generative API
• Text-to-Image Generation with LCM LoRA and ControlNet Conditioning
• Image generation with Latent Consistency Model and OpenVINO
• Kosmos-2: Multimodal Large Language Model and OpenVINO
• Multimodal understanding and generation with Janus-Pro and OpenVINO
• Visual-language assistant with InternVL2 and OpenVINO
• Image Editing with InstructPix2Pix and OpenVINO
• InstantID: Zero-shot Identity-Preserving Generation using OpenVINO
• Inpainting with OpenVINO GenAI
• Image-to-image generation using OpenVINO GenAI
• Image generation with HunyuanDIT and OpenVINO
• Object detection and masking from prompts with GroundedSAM (GroundingDINO + SAM) and OpenVINO
• Optical Character Recognition with GOT-OCR 2.0 and OpenVINO
• Visual-language assistant with GLM4-V and OpenVINO
• Visual-language assistant with GLM-Edge-V and OpenVINO
• Visual-language assistant with Gemma3 and OpenVINO
• Image generation with Flux.1 and OpenVINO
• Image inpainting and outpainting with FLUX.1 Fill
• Florence-2: Open Source Vision Foundation Model
• Frame interpolation using FILM and OpenVINO
• Object segmentations with FastSAM and OpenVINO
• Object segmentations with EfficientSAM and OpenVINO
• Animating Open-domain Images with DynamiCrafter and OpenVINO
• Automatic speech recognition using Distil-Whisper and OpenVINO
• Depth estimation with DepthAnything and OpenVINO
• Visual-language assistant using DeepSeek-VL2 and OpenVINO
• LLM reasoning with DeepSeek-R1 distilled models
• Text-to-Image Generation with ControlNet Conditioning
• Zero-shot Image Classification with OpenAI CLIP and OpenVINO™
• Virtual Try-On with CatVTON and OpenVINO
• Visual Question Answering and Image Captioning using BLIP and OpenVINO
• Text-to-speech generation using Bark and OpenVINO
• Image-to-Video synthesis with AnimateAnyone and OpenVINO

API Overview

• Text to Image pipeline and OpenVINO with Generate API
• Quantize Speech Recognition Models with accuracy control using NNCF PTQ API
• Post-Training Quantization of PyTorch models with NNCF
• Text Generation via Prompt Lookup Decoding using OpenVINO™
• Optimize Preprocessing
• OpenVINO Tokenizers: Incorporate Text Processing Into OpenVINO Pipelines
• Convert models from ModelScope to OpenVINO
• LocalAI and OpenVINO
• Text Generation with LoRA via OpenVINO GenAI
• Quantize NLP models with Post-Training Quantization ​in NNCF
• Run inference in Keras 3 with the OpenVINO™ IR backend
• Convert a JAX Model to OpenVINO™ IR
• Inpainting with OpenVINO GenAI
• Image-to-image generation using OpenVINO GenAI
• Quantization of Image Classification Models
• 🤗 Hugging Face Model Hub with OpenVINO™
• Hello NPU
• Working with GPUs in OpenVINO™
• OpenVINO™ Model conversion
• Big Transfer Image Classification Model Quantization pipeline with NNCF
• Automatic Device Selection with OpenVINO™
• Asynchronous Inference with OpenVINO™

Convert

• YOLOv11 quantization with accuracy control using NNCF
• Classification with ConvNeXt and OpenVINO
• Convert a Tensorflow Lite Model to OpenVINO™
• Using TensorFlow Object Detection API with OpenVINO™
• Convert of TensorFlow Hub models to OpenVINO Intermediate Representation (IR)
• Convert a TensorFlow Model to OpenVINO™
• Line-level text detection with Surya
• Convert a PyTorch Model to OpenVINO™ IR
• Convert a PaddlePaddle Model to OpenVINO™ IR
• Voice tone cloning with OpenVoice and OpenVINO
• OpenVINO Tokenizers: Incorporate Text Processing Into OpenVINO Pipelines
• Object detection and masking from prompts with GroundedSAM (GroundingDINO + SAM) and OpenVINO
• Convert Detectron2 Models to OpenVINO™
• Quantize a Segmentation Model and Show Live Inference
• OpenVINO™ Model conversion

Explainable AI

• OpenVINO™ Explainable AI Toolkit (3/3): Saliency map interpretation
• OpenVINO™ Explainable AI Toolkit (2/3): Deep Dive
• OpenVINO™ Explainable AI Toolkit (1/3): Basic
• Language-Visual Saliency with CLIP and OpenVINO™

First Steps

• OpenVINO™ Runtime API Tutorial
• Text Generation with LoRA via OpenVINO GenAI
• Image-to-image generation using OpenVINO GenAI
• Hello Image Classification
• Hello Image Segmentation
• Hello Object Detection
• OpenVINO™ Explainable AI Toolkit (1/3): Basic

Live Demos

• Style Transfer with OpenVINO™
• Live Human Pose Estimation with OpenVINO™
• Person Tracking with OpenVINO™
• Person Counting System using YOLOV8 and OpenVINO™
• PaddleOCR with OpenVINO™
• Voice tone cloning with OpenVoice and OpenVINO
• Live Object Detection with OpenVINO™
• CLIP model with Jina CLIP and OpenVINO
• Object detection and masking from prompts with GroundedSAM (GroundingDINO + SAM) and OpenVINO
• Quantize a Segmentation Model and Show Live Inference
• Human Action Recognition with OpenVINO™
• Live 3D Human Pose Estimation with OpenVINO

Model Demos

• Video generation with ZeroScope and OpenVINO
• Convert and Optimize YOLOv9 with OpenVINO™
• Convert and Optimize YOLOv8 real-time object detection with OpenVINO™
• YOLOv8 Oriented Bounding Boxes Object Detection with OpenVINO™
• Convert and Optimize YOLOv8 keypoint detection model with OpenVINO™
• Convert and Optimize YOLOv8 instance segmentation model with OpenVINO™
• Convert and Optimize YOLOv12 real-time object detection with OpenVINO™
• Convert and Optimize YOLOv11 real-time object detection with OpenVINO™
• Convert and Optimize YOLOv11 keypoint detection model with OpenVINO™
• Convert and Optimize YOLOv11 instance segmentation model with OpenVINO™
• Convert and Optimize YOLOv10 with OpenVINO
• Video Subtitle Generation using Whisper and OpenVINO™
• Automatic speech recognition using Whisper and OpenVINO with Generate API
• Wav2Lip: Accurately Lip-syncing Videos and OpenVINO
• Monodepth Estimation with OpenVINO
• Image Background Removal with U^2-Net and OpenVINO™
• Vehicle Detection And Recognition with OpenVINO™
• Image Generation with Tiny-SD and OpenVINO™
• Selfie Segmentation using TFLite and OpenVINO
• Text to Image pipeline and OpenVINO with Generate API
• Table Question Answering using TAPAS and OpenVINO™
• Line-level text detection with Surya
• Image to Video Generation with Stable Video Diffusion
• Stable Fast 3D Mesh Reconstruction and OpenVINO
• Image generation with Stable Diffusion XL and OpenVINO
• Image generation with Torch.FX Stable Diffusion v3 and OpenVINO
• Image generation with Stable Diffusion v3 and OpenVINO
• Infinite Zoom Stable Diffusion v2 and OpenVINO™
• Stable Diffusion v2.1 using OpenVINO TorchDynamo backend
• Text-to-Image Generation with Stable Diffusion and OpenVINO™
• Stable Diffusion with KerasCV and OpenVINO
• Image Generation with Stable Diffusion and IP-Adapter
• Image generation with Stable Cascade and OpenVINO
• Sound Generation with Stable Audio Open and OpenVINO™
• Text Generation via Speculative Decoding using FastDraft and OpenVINO™
• Sound Generation with AudioLDM2 and OpenVINO™
• Visual-Language Assistant with SmolVLM2 and OpenVINO
• Document conversion with SmolDocling and OpenVINO
• One Step Sketch to Image translation with pix2pix-turbo and OpenVINO
• Zero-shot Image Classification with SigLIP2
• Object masks from prompts with SAM and OpenVINO
• Single step image generation using SDXL-turbo and OpenVINO
• Image generation with Sana and OpenVINO
• Object masks from prompts with SAM2 and OpenVINO
• Object masks from prompts with SAM2 and OpenVINO for Images
• Text-to-Video retrieval with S3D MIL-NCE and OpenVINO
• Background removal with RMBG v1.4 and OpenVINO
• Text-to-Music generation using Riffusion and OpenVINO
• Visual-language assistant with Qwen2.5VL and OpenVINO
• Omnimodal assistant with Qwen2.5-Omni and OpenVINO
• Visual-language assistant with Qwen2VL and OpenVINO
• Audio-language assistant with Qwen2Audio and OpenVINO
• Generate creative QR codes with ControlNet QR Code Monster and OpenVINO™
• Visual-language assistant with Pixtral and OpenVINO
• PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis with OpenVINO
• Document Visual Question Answering Using Pix2Struct and OpenVINO™
• Text-to-image generation using PhotoMaker and OpenVINO
• Multimodal assistant with Phi-4-multimodal and OpenVINO
• Visual-language assistant with Phi3-Vision and OpenVINO
• Text-to-speech (TTS) with Parler-TTS and OpenVINO
• Text-to-Speech synthesis using OuteTTS and OpenVINO
• Optical Character Recognition (OCR) with OpenVINO™
• Voice tone cloning with OpenVoice and OpenVINO
• Running OpenCLIP models using OpenVINO™
• Universal Segmentation with OneFormer and OpenVINO
• Screen Parsing with OmniParser-v2.0 and OpenVINO
• Unified image generation using OmniGen and OpenVINO
• PDF converting with olmOCR model and OpenVINO
• Structure Extraction with NuExtract and OpenVINO
• Visual-language assistant with nanoLLaVA and OpenVINO
• Named entity recognition with OpenVINO™
• Controllable Music Generation with MusicGen and OpenVINO
• Multimodal RAG for video analytics with LlamaIndex
• Multi LoRA Image Generation
• Visual Content Search using MobileCLIP and OpenVINO
• MMS: Scaling Speech Technology to 1000+ languages with OpenVINO™
• Visual-language assistant with Llama-3.2-11B-Vision and OpenVINO
• Visual-language assistant with MiniCPM-V2 and OpenVINO
• Omnimodal assistant with MiniCPM-o 2.6 and OpenVINO
• Industrial Meter Reader
• Magika: AI powered fast and efficient file type identification using OpenVINO
• LTX Video and OpenVINO™
• Create a RAG system using OpenVINO and LlamaIndex
• Create a RAG system using OpenVINO and LangChain
• Create a RAG system using OpenVINO GenAI and LangChain
• LLM Instruction-following pipeline with OpenVINO
• Create a native Agent with OpenVINO
• Create an LLM-powered Chatbot using OpenVINO
• Create an LLM-powered Chatbot using OpenVINO Generate API
• Create ReAct Agent using OpenVINO and LangChain
• Create an Agentic RAG using OpenVINO and LlamaIndex
• Create Function-calling Agent using OpenVINO and Qwen-Agent
• Visual-language assistant with LLaVA Next and OpenVINO
• Visual-language assistant with LLaVA and Optimum Intel OpenVINO integration
• Visual-language assistant with LLaVA and OpenVINO Generative API
• Text-to-Speech synthesis using Llasa and OpenVINO
• Text-to-Image Generation with LCM LoRA and ControlNet Conditioning
• Image generation with Latent Consistency Model and OpenVINO
• Kosmos-2: Multimodal Large Language Model and OpenVINO
• Text-to-Speech synthesis using Kokoro and OpenVINO
• OpenVINO optimizations for Knowledge graphs
• Multimodal understanding and generation with Janus-Pro and OpenVINO
• Visual-language assistant with InternVL2 and OpenVINO
• Image Editing with InstructPix2Pix and OpenVINO
• InstantID: Zero-shot Identity-Preserving Generation using OpenVINO
• Inpainting with OpenVINO GenAI
• Image-to-image generation using OpenVINO GenAI
• Image generation with HunyuanDIT and OpenVINO
• Handwritten Chinese and Japanese OCR with OpenVINO™
• Object detection and masking from prompts with GroundedSAM (GroundingDINO + SAM) and OpenVINO
• Grammatical Error Correction with OpenVINO
• Optical Character Recognition with GOT-OCR 2.0 and OpenVINO
• Visual-language assistant with GLM4-V and OpenVINO
• Visual-language assistant with GLM-Edge-V and OpenVINO
• Visual-language assistant with Gemma3 and OpenVINO
• High-Quality Text-Free One-Shot Voice Conversion with FreeVC and OpenVINO™
• Image generation with Flux.1 and OpenVINO
• Image inpainting and outpainting with FLUX.1 Fill
• Florence-2: Open Source Vision Foundation Model
• Frame interpolation using FILM and OpenVINO
• Object segmentations with FastSAM and OpenVINO
• Audio compression with EnCodec and OpenVINO
• Object segmentations with EfficientSAM and OpenVINO
• Animating Open-domain Images with DynamiCrafter and OpenVINO
• Automatic speech recognition using Distil-Whisper and OpenVINO
• Depth estimation with DepthAnything and OpenVINO
• Visual-language assistant using DeepSeek-VL2 and OpenVINO
• LLM reasoning with DeepSeek-R1 distilled models
• Colorize grayscale images using 🎨 DDColor and OpenVINO
• Text-to-Image Generation with ControlNet Conditioning
• Zero-shot Image Classification with OpenAI CLIP and OpenVINO™
• Language-Visual Saliency with CLIP and OpenVINO™
• Virtual Try-On with CatVTON and OpenVINO
• Visual Question Answering and Image Captioning using BLIP and OpenVINO
• Text-to-speech generation using Bark and OpenVINO
• Image-to-Video synthesis with AnimateAnyone and OpenVINO
• Part Segmentation of 3D Point Clouds with OpenVINO™

Model Training

• Quantization Aware Training with NNCF, using TensorFlow Framework
• Quantization-Sparsity Aware Training with NNCF, using PyTorch framework
• Quantization Aware Training with NNCF, using PyTorch framework

Optimize

• YOLOv11 quantization with accuracy control using NNCF
• Quantization Aware Training with NNCF, using TensorFlow Framework
• SpeechBrain Emotion Recognition with OpenVINO
• Quantize Speech Recognition Models with accuracy control using NNCF PTQ API
• Accelerate Inference of Sparse Transformer Models with OpenVINO™ and 4th Gen Intel® Xeon® Scalable Processors
• Quantization-Sparsity Aware Training with NNCF, using PyTorch framework
• Quantization Aware Training with NNCF, using PyTorch framework
• Post-Training Quantization of PyTorch models with NNCF
• Optimize Preprocessing
• Voice tone cloning with OpenVoice and OpenVINO
• OpenVINO Tokenizers: Incorporate Text Processing Into OpenVINO Pipelines
• Quantize NLP models with Post-Training Quantization ​in NNCF
• OpenVINO optimizations for Knowledge graphs
• Quantization of Image Classification Models
• Object detection and masking from prompts with GroundedSAM (GroundingDINO + SAM) and OpenVINO
• Quantize a Segmentation Model and Show Live Inference
• Big Transfer Image Classification Model Quantization pipeline with NNCF