Plant diseases are harmful conditions that affect plants, leading to symptoms like wilting, discoloration, and reduced crop yields. Microorganisms like fungi, bacteria, viruses, nematodes, and phytoplasmas typically cause these diseases. Given that agriculture serves as a key source of income and employment for many, the detection of plant diseases becomes a critical task. To address this issue, the authors have implemented Artificial Intelligence algorithms on a visual dataset of Tomato plant leaves containing 8443 RGB images of 4 most common diseases in Tomato crop to make early disease detection easier. The paper comprehensively elucidates the entire process, encompassing image preprocessing, model training, testing procedures, and ultimate deployment, along with a comparative analysis of four distinct Machine Learning and Deep Learning models, namely Random Forest Classifier, Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Visual Geometry Group Neural Network (VGG). After extensive re-search, it has been concluded that RNN outperformed all the models for the entire dataset.