In the past few years, Generative Adversarial Networks as a deep generative model has received more and more attention. Mode collapsing is one of the challenges in the study of Generative Adversarial Networks. In order to solve this problem, we deduce a new algorithm on the basis of Wasserstein GAN. We add a generated distribution entropy term to the objective function of generator net and maximize the entropy to increase the diversity of fake images. And then Stein Variational Gradient Descent algorithm is used for optimization. We named our method SW-GAN. In order to substantiate our theoretical analysis, we perform experiments on MNIST and CIFAR-10, and the results demonstrate superiority of our method.