LayoutDiT: Exploring Content-Graphic Balance in Layout Generation with Diffusion Transformer

TL;DR

LayoutDiT is a novel diffusion transformer framework that effectively balances content and graphic features to generate high-quality, visually appealing layouts, addressing limitations of previous methods in spatial accuracy and aesthetics.

Contribution

We propose LayoutDiT, which introduces an adaptive balancing factor and a saliency bounding box to improve content-graphic harmony in layout generation using diffusion transformers.

Findings

Outperforms existing methods in constrained and unconstrained settings

Generates layouts with fewer overlaps and better spatial alignment

Achieves higher aesthetic quality and content coherence

Abstract

Layout generation is a foundation task of graphic design, which requires the integration of visual aesthetics and harmonious expression of content delivery. However, existing methods still face challenges in generating precise and visually appealing layouts, including blocking, overlapping, small-sized, or spatial misalignment. We found that these methods overlook the crucial balance between learning content-aware and graphic-aware features. This oversight results in their limited ability to model the graphic structure of layouts and generate reasonable layout arrangements. To address these challenges, we introduce LayoutDiT, an effective framework that balances content and graphic features to generate high-quality, visually appealing layouts. Specifically, we first design an adaptive factor that optimizes the model's awareness of the layout generation space, balancing the model's performance in both content and graphic aspects. Secondly, we introduce a graphic condition, the saliency bounding box, to bridge the modality difference between images in the visual domain and layouts in the geometric parameter domain. In addition, we adapt a diffusion transformer model as the backbone, whose powerful generative capability ensures the quality of layout generation. Benefiting from the properties of diffusion models, our method excels in constrained settings without introducing additional constraint modules. Extensive experimental results demonstrate that our method achieves superior performance in both constrained and unconstrained settings, significantly outperforming existing methods.