Khattat: Enhancing Readability and Concept Representation of Semantic Typography

TL;DR

Khattat is an automated system that combines language models, semantic font understanding, and diffusion-based stylization to create expressive, readable typography that visually conveys word meanings across languages.

Contribution

The paper introduces an end-to-end system integrating LLMs, FontCLIP, and diffusion models for semantic typography, enhancing readability and expressiveness automatically.

Findings

Improves readability of stylized typography across languages

Automatically generates concept-representative typography designs

Outperforms baselines in readability and versatility

Abstract

Designing expressive typography that visually conveys a word's meaning while maintaining readability is a complex task, known as semantic typography. It involves selecting an idea, choosing an appropriate font, and balancing creativity with legibility. We introduce an end-to-end system that automates this process. First, a Large Language Model (LLM) generates imagery ideas for the word, useful for abstract concepts like freedom. Then, the FontCLIP pre-trained model automatically selects a suitable font based on its semantic understanding of font attributes. The system identifies optimal regions of the word for morphing and iteratively transforms them using a pre-trained diffusion model. A key feature is our OCR-based loss function, which enhances readability and enables simultaneous stylization of multiple characters. We compare our method with other baselines, demonstrating great readability enhancement and versatility across multiple languages and writing scripts.