Joint model for classification and detection with YOLOv8

Hi, I am doing a project where I classify and detect at the same time. I learned that YOLOv8 can be used for both tasks. I have tried both but not simultaneously. Given that, is it possible to perform both tasks under a single model. Basically, for an input image, there will be a classification and bounding boxes for the objects detected.

Some projects use a “two-stage detection model” which involves running one model (i.e. an object detection model) then another model (i.e. classification). You can use any combination of models you want, but you have to run inference separately (i.e. YOLOv8 object detection then YOLOv8 classification).