Recent Trends in Text-to-Image GAN

Generating genuine images from textual description is challenging for both computer vision and linguistic representation in text-to-image synthesis. Generative adversarial networks (GAN) are an emerging generative model that has been producing great results by generating high-quality images with diverse images. The present review provides an overview of GAN with its background like architecture, game theory key ideas, loss functions, performance metrics and challenges. Recent and relevant text-to-image GAN models are discussed, including Gradual Refinement GAN (GR-GAN), Generative Adversarial CLIPS (GALIP), GigaGAN and StyleGAN-T with their architecture, dataset used highlighting limitations, strengths, year, and applications and comparing their performance metrics like Inception Score (IS) and Fréchet Inception Distance (FID) with identifying future directions, such as drawing boundaries for open research challenges. The present review functions as an extensive knowledge base and is highly valuable for researchers and practitioners who are interested in learning more about text-to-image using GANs.