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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Zeyang, Wang, Le, Zhou, Sanping, Wu, Yuxuan, Sun, Xiaolong, Hua, Gang, Li, Haoxiang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915664185262080
author Liu, Zeyang
Wang, Le
Zhou, Sanping
Wu, Yuxuan
Sun, Xiaolong
Hua, Gang
Li, Haoxiang
author_facet Liu, Zeyang
Wang, Le
Zhou, Sanping
Wu, Yuxuan
Sun, Xiaolong
Hua, Gang
Li, Haoxiang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_08897
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniLayDiff: A Unified Diffusion Transformer for Content-Aware Layout Generation
Liu, Zeyang
Wang, Le
Zhou, Sanping
Wu, Yuxuan
Sun, Xiaolong
Hua, Gang
Li, Haoxiang
Computer Vision and Pattern Recognition
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.
title UniLayDiff: A Unified Diffusion Transformer for Content-Aware Layout Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.08897