Text-to-image Diffusion Models in Generative AI: A Survey

Abstract--This survey reviews text-to-image diffusion models in the context that diffusion models have emerged to be popular for a wide range of generative tasks. As a self-contained work, this survey starts with a brief introduction of how a basic diffusion model works for image synthesis, followed by how condition or guidance improves learning. Based on that, we present a review of state-of-the-art methods on text-conditioned image synthesis, i.e. text-to-image. We further summarize applications beyond text-to-image generation: text-guided creative generation and text-guided image editing. Beyond the progress made so far, we discuss existing challenges and promising future directions. The volume of the relevant works makes humans read a story in text, they can draw relevant images it increasingly challenging for readers to keep abreast of in their heads by imagination, which helps them understand the recent development of text-to-image diffusion model and enjoy more. However, as far as we that generates visually realistic images from textural descriptions, know, there is no survey work focusing on recent progress i.e., the text-to-image task, is a non-trivial task of diffusion-based text-to-image generation yet. A branch of and therefore can be seen as a major milestone toward related surveys [19], [20], [21], [22] reviews the progress of human-like or general artificial intelligence [1], [2], [3], [4].