AI RESEARCH
NumColor: Precise Numeric Color Control in Text-to-Image Generation
arXiv CS.CV
•
ArXi:2603.13547v1 Announce Type: new Text-to-image diffusion models excel at generating images from natural language descriptions, yet fail to interpret numerical colors such as hex codes and RGB values (rgb(255,87,51)). This limitation stems from subword tokenization, which fragments color codes into semantically meaningless tokens that text encoders cannot map to coherent color representations. We present NumColor, that enables precise numerical color control across multiple diffusion architectures.