Textured Word-As-Image illustration

TL;DR

This paper introduces an automatic pipeline that generates textured text images aligned with semantic concepts, allowing real-time customization while maintaining readability, useful for design and artistic purposes.

Contribution

It presents a novel method combining semantic input, texture generation via stable diffusion, and real-time adjustments to produce legible, semantically aligned textured text images.

Findings

Effective semantic-texture alignment demonstrated

High user satisfaction in readability and customization

Real-time adjustment feature enhances usability

Abstract

In this paper, we propose a novel fully automatic pipeline to generate text images that are legible and strongly aligned to the desired semantic concept taken from the users' inputs. In our method, users are able to put three inputs into the system, including a semantic concept, a word, and a letter. The semantic concept will be used to change the shape of the input letter and generate the texture based on the pre-defined prompt using stable diffusion models. Our pipeline maps the texture on a text image in a way that preserves the readability of the whole output while preserving legibility. The system also provides real-time adjustments for the user to change the scale of the texture and apply it to the text image. User evaluations demonstrate that our method effectively represents semantic meaning without compromising legibility, making it a robust and innovative tool for graphic design, logo creation, and artistic typography.