Wildfires pose a significant threat, necessitating robust fire detection systems. Deep learning-based techniques, particularly those utilizing object detection models like YOLOv8, offer a promising alternative for fire and smoke detection. In this paper, we present a YOLOv8-based method for fire and smoke detection in images. We constructed a comprehensive dataset and trained a YOLOv8 model to achieve high accuracy in detecting fire and smoke. The results suggest the effectiveness of one of the recent models of YOLO.