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

TL;DR

PosterCopilot is a novel framework that enhances layout reasoning and provides controllable, iterative editing capabilities for professional graphic design using advanced training strategies for multimodal models.

Contribution

It introduces a three-stage training strategy and a complete workflow enabling geometric understanding and layer-specific editing in graphic design LMMs.

Findings

Achieves geometrically accurate layouts

Provides aesthetically superior designs

Enables layer-controllable iterative editing

Abstract

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.