Abstract: The current facial attribute transformation based on generative adversarial networks (GAN) and GAN-based method has problems of low resolution and feature loss of the generated image. Based on the GeneGAN network, this paper proposes a face attribute conversion algorithm based on feature enhancement. By increasing the network depth in the generation network, establishing a high- and low-dimensional feature coupling channel, and extracting and comparing specific attribute depth features to optimize the identity and features of the generated image. Experiment based on CelebA dataset shows that the high-resolution images generated by the proposed algorithm have a better improvement in maintaining image identity information, and have a greater improvement in visual effects and objective indicators.