TextFace: Text-to-Style Mapping based Face Generation and Manipulation

Xianxu Hou*, Xiaokang Zhang*, Yudong Li, Linlin Shen


As a subtopic of text-to-image synthesis, text-to-face generation has great potential in face-related applications. In this paper, we propose a generic text-to-face framework, namely, TextFace, to achieve diverse and high-quality face image generation from text descriptions. We introduce text-to-style mapping, a novel method where the text description can be directly encoded into the latent space of a pretrained StyleGAN. Guided by our text-image similarity matching and face captioning-based text alignment, the textual latent code can be fed into the generator of a well-trained StyleGAN to produce diverse face images with high resolution (1024 x 1024). Furthermore, our model inherently supports semantic face editing using text descriptions. Finally, experimental results quantitatively and qualitatively demonstrate the superior performance of our model.



  • Diverse text-to-face generation
  • Attention visualization
  • More results
      title={TextFace: Text-to-Style Mapping based Face Generation and Manipulation},
      author={Hou, Xianxu and Zhang, Xiaokang and Li, Yudong and Shen, Linlin},
      journal={IEEE Transactions on Multimedia},