TextLap: Customizing Language Models for Text-to-Layout Planning

TL;DR

TextLap is a method that customizes large language models to generate graphical layouts from text instructions, significantly improving layout design quality for various applications.

Contribution

The paper introduces TextLap, a novel approach to adapt LLMs for text-to-layout planning using a curated dataset, outperforming existing methods including GPT-4 based approaches.

Findings

TextLap outperforms strong baselines in layout generation tasks.

It effectively adapts LLMs for graphical design applications.

Demonstrates superior results on image generation and design benchmarks.

Abstract

Automatic generation of graphical layouts is crucial for many real-world applications, including designing posters, flyers, advertisements, and graphical user interfaces. Given the incredible ability of Large language models (LLMs) in both natural language understanding and generation, we believe that we could customize an LLM to help people create compelling graphical layouts starting with only text instructions from the user. We call our method TextLap (text-based layout planning). It uses a curated instruction-based layout planning dataset (InsLap) to customize LLMs as a graphic designer. We demonstrate the effectiveness of TextLap and show that it outperforms strong baselines, including GPT-4 based methods, for image generation and graphical design benchmarks.