From Elements to Design: A Layered Approach for Automatic Graphic Design Composition

TL;DR

This paper introduces LaDeCo, a layered multimodal model that improves automatic graphic design composition by incorporating hierarchical planning and element attributes, enabling more effective and versatile design generation.

Contribution

LaDeCo is the first layered approach integrating hierarchical planning into large multimodal models for comprehensive graphic design composition.

Findings

LaDeCo outperforms specialized models in some subtasks without task-specific training.

It enables applications like resolution adjustment, element filling, and design variation.

Experimental results confirm LaDeCo's effectiveness in design composition.

Abstract

In this work, we investigate automatic design composition from multimodal graphic elements. Although recent studies have developed various generative models for graphic design, they usually face the following limitations: they only focus on certain subtasks and are far from achieving the design composition task; they do not consider the hierarchical information of graphic designs during the generation process. To tackle these issues, we introduce the layered design principle into Large Multimodal Models (LMMs) and propose a novel approach, called LaDeCo, to accomplish this challenging task. Specifically, LaDeCo first performs layer planning for a given element set, dividing the input elements into different semantic layers according to their contents. Based on the planning results, it subsequently predicts element attributes that control the design composition in a layer-wise manner, and includes the rendered image of previously generated layers into the context. With this insightful design, LaDeCo decomposes the difficult task into smaller manageable steps, making the generation process smoother and clearer. The experimental results demonstrate the effectiveness of LaDeCo in design composition. Furthermore, we show that LaDeCo enables some interesting applications in graphic design, such as resolution adjustment, element filling, design variation, etc. In addition, it even outperforms the specialized models in some design subtasks without any task-specific training.