Coffee is one of the most widely consumed beverages globally, and its production is significantly threatened by various leaf diseases, leading to substantial economic losses for farmers. To reduce this a deep learning-based approach for the detection of coffee leaf diseases utilizing Convolutional Neural Networks (CNNs) and transfer learning techniques are used. A diverse dataset of coffee leaf images are collected, representing healthy leaves and those affected by common diseases, including coffee leaf rust, bacterial blight, and leaf spot. The dataset was augmented through techniques such as rotation, flipping, and scaling to enhance model robustness. Transfer learning with pre-trained models, specifically Densenet and ResNet, fine-tuning them on our dataset to leverage their powerful feature extraction capabilities. The suggested model was examined and achieving an 82.3% accuracy and primary objective is to enhance the model’s accuracy in detecting leaf-based diseases by leveraging advanced deep learning techniques and this is crucial for agricultural practices.