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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Jian, Zhang, Ruiyi, Zhou, Yufan, Healey, Jennifer, Gu, Jiuxiang, Xu, Zhiqiang, Chen, Changyou
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912075058511872
author Chen, Jian
Zhang, Ruiyi
Zhou, Yufan
Healey, Jennifer
Gu, Jiuxiang
Xu, Zhiqiang
Chen, Changyou
author_facet Chen, Jian
Zhang, Ruiyi
Zhou, Yufan
Healey, Jennifer
Gu, Jiuxiang
Xu, Zhiqiang
Chen, Changyou
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12844
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TextLap: Customizing Language Models for Text-to-Layout Planning
Chen, Jian
Zhang, Ruiyi
Zhou, Yufan
Healey, Jennifer
Gu, Jiuxiang
Xu, Zhiqiang
Chen, Changyou
Computation and Language
Machine Learning
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.
title TextLap: Customizing Language Models for Text-to-Layout Planning
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2410.12844