Single image super-resolution is a digital image processing technique that can obtain a corresponding high-resolution image from a low-resolution image. The growth of deep convolutional neural networks in the field of computer vision has greatly benefited recent research on super-resolution. However, the convolutional neural networks often have a large number of parameters, which increases the model’s computational cost and limits its application in practical situations. In order to solve the problem, we propose a lightweight generative adversarial network model using the inception block. According to extensive experimental results on image super-resolution using four widely used datasets, our model not only achieves high scores on the peak signal to noise ratio/structural similarity index matrix, but also enables faster computation compared to other image super-resolution models.