Collecting infrared images from fields is difficult, high-costing and time-consuming. In order to address this problem, an infrared image generation method based on conditional generative adversarial networks is proposed. In the proposed method, the D-LinkNet network is utilized to build the generative model, enabling improved learning of rich image textures and identification of dependencies between images. Moreover, the PatchGAN architecture is employed to build a discriminant model to process the high-frequency components of the images effectively and reduce the amount of calculation required. In addition, batch normalization is used to optimize the training process, and thereby the instability and mode collapse of the generated adversarial network training can be alleviated. Finally, experimental verification is conducted on the produced infrared/visible light dataset. The experimental results reveal that high-quality and reliable infrared data are generated by the proposed algorithm.