Ultralytics YOLOv8.2 ReleaseUltralytics YOLOv8.2 ReleaseUltralytics YOLOv8.2 Release Arrow
A woman's smile being identified with object detection

Train AI models in seconds with Ultralytics YOLO

Explore our state-of-the-art AI architecture to train and deploy your highly-accurate AI models like a pro

Monthly Visits

to Ultralytics Products

Images Analyzed

with Ultralytics pip pacage

Models Trained

with Ultralytics pip pacage

GitHub Stars

total for all Ultralytics respositoies


achieving milestones with a team of <20

Boost your business or research in 3 simple steps

YOLO for enterprises

Scale your business with AI

Integrate Ultralytics YOLO into your applications or oprimize the ML model pipeline with our no-code solution.

No matter whether you’re an aspiring start-up or a large enterprise – YOLO offers efficient and scalable solutions for computer vision problems.

Bottles being detected in a manufacturing facility next to a chart that shows how well a vision AI model is being trained
Viruses being identified through segmentation
YOLO for academics

Boost your academic research with AI

Conduct thorough evaluations and testing of newly developed algorithms and models and easily publish scientific papers for your research.

YOLO for technical users

Boost work efficiency

Ultralytics YOLO is an efficient tool for professionals working in computer vision and ML that can help create accurate object detection models.

Simplify the ML development process and improve collaboration among team members using our no-code platform.

A valve being identified with object detection
A woman's face being identified with object detection
YOLO for enthusiasts

Try YOLO for personal experiments

Learn and experiment with computer vision and object detection, or use Ultralytics YOLO for personal projects and learning.

Test Ultralytics YOLO now

Have a go using our API by uploading your own image and watch as Ultralytics YOLO identifies objects using our pre-trained models

Drag and drop your image here.

Doing the impossible..

Image examples
Zidane yelling during a soccer gameMen looking at a computerA group of people having a meal together
Or upload image from your device
Upload image from your device
Drop down icon
An app on a phone that is identifying the mask someone is wearing with object detection

Once trained on Ultralytics HUB, you can test your models in our Vision AI app for iOS and Android

Check mark
Browse pre-trained YOLO models
Check mark
Test your own models on your smartphone
Check mark
Manage all your Ultralytics HUB projects in one place

The best AI architecture you’ll ever use

Simple usage with a few clicks

Train models, view results, track losses and metrics with our no-code solution or pip install with just two lines of code to get started

Versatile object

Enhance object detection and segmentation with new features: backbone network, anchor-free detection head, and loss function

Well-documented workflows

We offer thorough documentation and examples for YOLOv8's 4 main modes - predicting, validating, training, and exporting

Spotless code

Our code is written from scratch and documented comprehensively with examples, both in the code and in our Ultralytics Docs

YOLO model library

YOLOv8 supports all YOLO versions, even those of competitors (Google MobileNet etc.)

Multiple format and platform support

Easily export trained models to most common formats (ONNX, OpenVINO, CoreML, etc.) an run them on various platforms, from CPUs to GPUsrting

Glenn Jocher

Glenn Jocher

Ultralytics Founder & CEO

After 2 years of continuous research and development, we are excited to announce the release of Ultralytics YOLOv8. This YOLO model sets a new standard in real-time detection and segmentation, making it easier to develop simple and effective AI solutions for a wide range of use cases.

About us
Enterprise license
Upload image datasets
Achieve grand business goals
Integrate Ultralytics YOLO into your product
No need to open-source your work
No-code platform
Ultralytics YOLO on HUB
Upload image datasets
Choose ML models to train or create yours
Deploy your model anywhere

Contribute on GitHub

Github logo
Github logo
Github logo

We've transformed the core structure of the architecture from a simple version into a robust platform. And now, YOLOv8 is designed to support any YOLO architecture, not just v8. We're excited to support user-contributed models, tasks, and applications.

Star the repository on GitHub
Men looking at a computer