Text-to-Face Generation with StyleGAN2

TL;DR

This paper introduces a novel text-to-face generation framework using StyleGAN2 and BERT embeddings, achieving high-resolution, semantically aligned facial images with improved quality and similarity metrics.

Contribution

The study demonstrates the effective integration of StyleGAN2 with text embeddings for high-resolution face generation from descriptions, surpassing existing methods.

Findings

Generated images achieve 57% similarity to ground truth

Semantic face distance of 0.92 indicates good alignment

FID score of 118.097 shows promising image quality

Abstract

Synthesizing images from text descriptions has become an active research area with the advent of Generative Adversarial Networks. The main goal here is to generate photo-realistic images that are aligned with the input descriptions. Text-to-Face generation (T2F) is a sub-domain of Text-to-Image generation (T2I) that is more challenging due to the complexity and variation of facial attributes. It has a number of applications mainly in the domain of public safety. Even though several models are available for T2F, there is still the need to improve the image quality and the semantic alignment. In this research, we propose a novel framework, to generate facial images that are well-aligned with the input descriptions. Our framework utilizes the high-resolution face generator, StyleGAN2, and explores the possibility of using it in T2F. Here, we embed text in the input latent space of StyleGAN2 using BERT embeddings and oversee the generation of facial images using text descriptions. We trained our framework on attribute-based descriptions to generate images of 1024x1024 in resolution. The images generated exhibit a 57% similarity to the ground truth images, with a face semantic distance of 0.92, outperforming state-of-the-artwork. The generated images have a FID score of 118.097 and the experimental results show that our model generates promising images.