This directory contains interactive demos aimed at demonstrating how OpenVINO performs as an AI optimization and inference engine (cloud, client, and edge), and attracting more people to Intel's booth at events.
Please note: even though you can find here a lot of useful OpenVINO code, education is not the main purpose of this directory. If you are interested in educational content visit ai_ref_kits.
Currently, there are the following demos:
The demo generates images in a reasonable time (seconds) on Intel hardware.
Paint Your Dreams | |
---|---|
Related AI concepts | Visual GenAI, LCM, image generation |
Platforms | Client (CPU, GPU), Cloud (CPU, GPU) |
Owner | @adrianboguszewski |
The demo works as a virtual AI assistant. The default personality is a healthcare assistant, whose task is to greet the patient and summarize the patient's condition based on the conversation and uploaded examination report.
Virtual AI Assistant | |
---|---|
Related AI concepts | LLM, RAG, GenAI, Llama3, LLamaIndex |
Platforms | Client (CPU, GPU, NPU), Cloud (CPU, GPU) |
Owner | @adrianboguszewski |
The demo counts people (or any other selected object) standing in front of the webcam, presenting differences in performance between various precisions and devices on the used platform.
People Counter | |
---|---|
Related AI concepts | object detection, object counting, YOLO11, YOLOv8 |
Platforms | Client (CPU, GPU, NPU), Edge (CPU) |
Owner | @adrianboguszewski |
The demo detects, tracks and counts defined objects in front of the webcam. The default object is a hazelnut, but it can be changed to any other object. It works especially good with a conveyor belt.
Spot a Defect | |
---|---|
Related AI concepts | object detection, object tracking, object counting, YOLOWorld |
Platforms | Client (CPU, GPU, NPU), Edge (CPU) |
Owner | @adrianboguszewski |
The demo blurs the background behind a person on a webcam. The app is built using NodeJS and Electron technologies. It can be run from the compiled exe file or using npm.
Hide Your Mess Behind | |
---|---|
Related AI concepts | image segmentation |
Platforms | Client (CPU, GPU, NPU), Edge (CPU) |
Owner | @Roszczyk, @adrianboguszewski |
The demo estimates poses of all people standing in front of the webcam.
Strike a Pose | |
---|---|
Related AI concepts | pose estimation, YOLO11, YOLOv8 |
Platforms | Client (CPU, GPU, NPU), Edge (CPU) |
Owner | @adrianboguszewski |
The demo detects people in front of the webcam and changes them into skeletons with a pumpkin head.
Spooky Demo | |
---|---|
Related AI concepts | pose estimation, Open Pose |
Platforms | Client (CPU, GPU, NPU), Edge (CPU) |
Owner | @adrianboguszewski |
The demo detects people in front of the webcam and changes them into Santa Claus (the biggest face) and reindeer (all other faces).
Santa Claus Demo | |
---|---|
Related AI concepts | face detection, landmarks regression, emotion recognition |
Platforms | Client (CPU, GPU, NPU), Edge (CPU) |
Owner | @adrianboguszewski |
Please follow the rules defined in the contributing guide to add a demo to this repository.
- Open a discussion topic
- Create an issue
- Learn more about OpenVINO
- Explore OpenVINO’s documentation