A Comparative Analysis of Text-to-Image Generation Models: Diffusion and Autoencoder Approaches

Text-to-image generation is a technique of creating images based on text descriptions. Recently, so many research publications has been done in this area, showing its popularity. In this work, we reviewed various autoregressive models, nonautoregressive models, GANs, energy-based models, multimodal methods and diffusion models used for text to image generation tasks. We also discuss important techniques commonly used in these models, such as autoencoders, attention mechanisms, and classifier-free guidance. For application, we performed a comparative analysis of diffusion and autoencoder models for text to image generation tasks taking Flowers-HD5 dataset. The results shows that the autoencoder achieves rapid convergence and significantly lower reconstruction loss (~0.01 range), producing sharp and faithful results. While the diffusion model, despite higher loss (~0.1–0.25), generates images with greater diversity