Agriculture plays a crucial role in the global economy, supporting millions of farmers in rural areas by providing a means of living through the cultivation of a wide variety of crops. However, due to limited resources and expertise, accurately diagnosing plant diseases in a timely manner is often a challenging task, wasted time, resources, and potential crop loss as farmers work to manage affected plants. We introduced the YOLOv8 model, which is designed to provide precise detection and classification to solve these issues. YOLOv8 is a cutting-edge model for identifying objects, known for its exceptional speed and accuracy. With just one forward pass, it can detect every object in an image. YOLOv8 lightweight architecture allows for deployment on devices with limited processing power, such as low-cost agricultural drones or smartphones. This accessibility allows farmers to detect disease in real time when they are working in the field directly. The model’s efficiency ensures rapid processing times and minimal resource consumption, making it ideal for real-time applications. This combination of accessibility and efficiency positions of YOLOv8 is used as a useful tool for early disease detection and intervention in agriculture. The proposed model shows excellent mAP50 as compared to other existing model for plant leaf disease detection and experimental results achieved a precision of 71.4%, a recall of 69.1%, mAP@50 of 73.9%, and mAP@50–95 of 65.9% on the PlantDoc datasets.