← Search

Rj Mical

2 accepted papers

2023

Character-Aware Models Improve Visual Text Rendering

ACL 2023long

Current image generation models struggle to reliably produce well-formed visual text. In this paper, we investigate a key contributing factor: popular text-to-image models lack character-level input features, making it much harder to predict a word’s visual makeup as a series of glyphs. To quantify…

Cited by 67SourcePDFScholar