StyleT2F: Generating Human Faces from Textual Description Using StyleGAN2
This work addresses the need for text-to-face generation in AI-driven image synthesis, offering a method for manipulating facial features with disentanglement, though it appears incremental as it builds on existing StyleGAN2 techniques.
The authors tackled the problem of generating detailed human faces from textual descriptions by controlling StyleGAN2's output using text, achieving correct feature capture and consistency between input text and output images.
AI-driven image generation has improved significantly in recent years. Generative adversarial networks (GANs), like StyleGAN, are able to generate high-quality realistic data and have artistic control over the output, as well. In this work, we present StyleT2F, a method of controlling the output of StyleGAN2 using text, in order to be able to generate a detailed human face from textual description. We utilize StyleGAN's latent space to manipulate different facial features and conditionally sample the required latent code, which embeds the facial features mentioned in the input text. Our method proves to capture the required features correctly and shows consistency between the input text and the output images. Moreover, our method guarantees disentanglement on manipulating a wide range of facial features that sufficiently describes a human face.