CreatiDesign: A Unified Multi-Conditional Diffusion Transformer for Creative Graphic Design
Hui Zhang, Dexiang Hong, Maoke Yang, Yutao Cheng, Zhao Zhang, Weidong Chen, Jie Shao, Xinglong Wu, Zuxuan Wu, Yu-Gang Jiang

TL;DR
CreatiDesign introduces a unified multi-condition diffusion transformer with a multimodal attention mask for precise control in automated graphic design, supported by a large annotated dataset.
Contribution
It presents a novel architecture and dataset for multi-condition graphic design generation, improving control and harmony over existing methods.
Findings
Outperforms existing models in adhering to user design intent.
Introduces a new dataset with 400K samples for multi-condition graphic design.
Demonstrates effective integration of heterogeneous design elements.
Abstract
Graphic design plays a vital role in visual communication across advertising, marketing, and multimedia entertainment. Prior work has explored automated graphic design generation using diffusion models, aiming to streamline creative workflows and democratize design capabilities. However, complex graphic design scenarios require accurately adhering to design intent specified by multiple heterogeneous user-provided elements (\eg images, layouts, and texts), which pose multi-condition control challenges for existing methods. Specifically, previous single-condition control models demonstrate effectiveness only within their specialized domains but fail to generalize to other conditions, while existing multi-condition methods often lack fine-grained control over each sub-condition and compromise overall compositional harmony. To address these limitations, we introduce CreatiDesign, a…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
