Diseases in potato plants cause tremendous damage to the yield. CNN constitutes a possible solution for the early detection of early and late blight diseases. This paper does a detailed comparison based on performance and suitability of a new model and Pre Trained models in context of detecting an early blight or a late blight in Potato Crops. This investigation comprises a comparative analysis including their accuracy and loss. Through meticulous testing and training, this study aims to provide cognizance into the efficiency of these architectures for automated identification of blight diseases in potatoes, important for crop disease management. The images after adequate preprocessing and augmentation (by using techniques such as Random Flip and Random Rotation) were feeded to the five pre-trained models-InceptionV3, ResNet152v2, MobileNetV2, DenseNet121 and VGG16 neural network architectures and one custom CNN model GreenNet101 over a total of 10 epochs; out of which MobileNetV2 gives out the best accuracy of over 99.99%.