UniLayDiff: A Unified Diffusion Transformer for Content-Aware Layout Generation

TL;DR

UniLayDiff introduces a single, end-to-end trainable diffusion transformer model that unifies various content-aware layout generation tasks, improving quality and versatility in graphic design automation.

Contribution

It is the first model to unify diverse content-aware layout generation tasks using a Multi-Modal Diffusion Transformer with relation constraint fine-tuning.

Findings

Achieves state-of-the-art performance across multiple layout generation tasks.

Successfully unifies unconditional and conditional layout generation in one model.

Enhances layout quality through relation constraint integration.

Abstract

Content-aware layout generation is a critical task in graphic design automation, focused on creating visually appealing arrangements of elements that seamlessly blend with a given background image. The variety of real-world applications makes it highly challenging to develop a single model capable of unifying the diverse range of input-constrained generation sub-tasks, such as those conditioned by element types, sizes, or their relationships. Current methods either address only a subset of these tasks or necessitate separate model parameters for different conditions, failing to offer a truly unified solution. In this paper, we propose UniLayDiff: a Unified Diffusion Transformer, that for the first time, addresses various content-aware layout generation tasks with a single, end-to-end trainable model. Specifically, we treat layout constraints as a distinct modality and employ Multi-Modal Diffusion Transformer framework to capture the complex interplay between the background image, layout elements, and diverse constraints. Moreover, we integrate relation constraints through fine-tuning the model with LoRA after pretraining the model on other tasks. Such a schema not only achieves unified conditional generation but also enhances overall layout quality. Extensive experiments demonstrate that UniLayDiff achieves state-of-the-art performance across from unconditional to various conditional generation tasks and, to the best of our knowledge, is the first model to unify the full range of content-aware layout generation tasks.