PosterCopilot：面向专业平面设计的布局推理与可控编辑系统

PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design

December 3, 2025

作者: Jiazhe Wei, Ken Li, Tianyu Lao, Haofan Wang, Liang Wang, Caifeng Shan, Chenyang Si

cs.AI

摘要

平面设计作为现代视觉传达的基石，是推广文化及商业活动的重要媒介。尽管近期研究尝试利用大型多模态模型实现设计流程自动化，但现有方法常存在几何布局失准问题，且缺乏专业工作流所需的逐层迭代编辑能力。为此，我们提出PosterCopilot框架，通过增强布局推理与可控编辑功能推动专业平面设计发展。具体而言，我们设计了渐进式三阶段训练策略：扰动监督微调、视觉现实对齐的强化学习、审美反馈强化学习，使多模态模型具备几何理解与美学推理的版式设计能力。此外，我们开发了完整工作流，将训练后的设计模型与生成模型耦合，在保持全局视觉一致性的同时，实现图层可控的迭代式编辑与精准元素优化。大量实验表明，PosterCopilot能生成几何精确且美学卓越的布局，为专业迭代设计提供前所未有的可控性。

English

Graphic design forms the cornerstone of modern visual communication, serving as a vital medium for promoting cultural and commercial events. Recent advances have explored automating this process using Large Multimodal Models (LMMs), yet existing methods often produce geometrically inaccurate layouts and lack the iterative, layer-specific editing required in professional workflows. To address these limitations, we present PosterCopilot, a framework that advances layout reasoning and controllable editing for professional graphic design. Specifically, we introduce a progressive three-stage training strategy that equips LMMs with geometric understanding and aesthetic reasoning for layout design, consisting of Perturbed Supervised Fine-Tuning, Reinforcement Learning for Visual-Reality Alignment, and Reinforcement Learning from Aesthetic Feedback. Furthermore, we develop a complete workflow that couples the trained LMM-based design model with generative models, enabling layer-controllable, iterative editing for precise element refinement while maintaining global visual consistency. Extensive experiments demonstrate that PosterCopilot achieves geometrically accurate and aesthetically superior layouts, offering unprecedented controllability for professional iterative design.