2024
An Empirical Study and Analysis of Text-to-Image Generation Using Large Language Model-Powered Textual Representation
ECCV 2024poster
"One critical prerequisite for faithful text-to-image generation is the accurate understanding of text inputs. Existing methods leverage the text encoder of the CLIP model to represent input prompts. However, the pre-trained CLIP model can merely encode English with a maximum token length of 77. Mor…