Multimodal Large Language Model is a Human-Aligned Annotator for Text-to-Image Generation

arXiv:2404.15100v1 Announce Type: new
Abstract: Recent studies have demonstrated the exceptional potentials of leveraging human preference datasets to refine text-to-image generative models, enhancing the alignment between generated images and textual prompts. Despite these advances, current human preference datasets are either prohibitively expensive to construct or suffer from a lack of diversity in preference dimensions, resulting in limited applicability for instruction tuning in open-source text-to-image generative models and hinder further exploration. To address these challenges and promote the alignment of generative …

abstract advances alignment arxiv construct cs.cv cs.mm current datasets generated generative generative models human image image generation images language language model large language large language model multimodal multimodal large language model prompts refine studies text text-to-image textual type