Introducing the YOLOv8 Web UI

Historically, object detection was one of the first deep learning technologies that became viable for consumer use. This was largely thanks to the incredible work of Joseph Redmon and his research team to develop the first generations of You Only Look Once (YOLO) models. There powerful framework enabled people with more casual computing setups to get started with YOLO object detection, and begin to integrate the AI framework into their existing applications.

This tradition was continued with the devlopment of YOLOv5 and YOLOv8 at Ultralytics. They have continued to push the envelope in developing SOTA object detection models with increasingly better options for interfacing the framework. The latest of these comes with the YOLO package from Ultralytics, which makes it much easier to integrate YOLO with existing python code and run in Notebooks.

In this article, we are excited to introduce the YOLOv8 Web UI. Inspired by the work of Automatic1111 and their many contributors to develop an all-in-one application for running Stable Diffusion, we sought to develop a single Gradio application interface for YOLOv8 that can serve all of the model’s key functionalities. In our new application, users can label their images, view those images in ordered galleries, train the full gamut of YOLOv8 models, and generate image label predictions on image and video inputs - all in one easy to use application!

Follow this tutorial to learn how to run the application in Gradient.