Solar activity forecasting plays a crucial role in various domains, including space weather prediction and satellite communications. With the emergence of large artificial intelligence (AI) models, there is a growing interest in exploring their potential to improve the accuracy of solar activity forecasting. This paper presents a study on the application of AI with large models in solar activity forecasting. We investigate the effectiveness of leveraging deep learning techniques, such as convolutional neural networks (CNNs), residual neural networks (ResNets), and Long Short-Term Memory (LSTM) networks, to capture complex patterns and dependencies in solar data. Additionally, we explore the benefits of using large models, such as Mask AutoEncoder, CLIP, Florence, and ALIGN, to integrate intelligent processing tasks and enhance predictive capabilities.