iPoster: Content-Aware Layout Generation for Interactive Poster Design via Graph-Enhanced Diffusion Models

TL;DR

iPoster is an interactive framework that generates content-aware poster layouts based on user constraints, using a graph-enhanced diffusion model for high-quality, controllable design.

Contribution

It introduces a unified graph-enhanced diffusion architecture enabling flexible, constraint-based poster layout generation with real-time responsiveness.

Findings

Achieves state-of-the-art layout quality.

Supports flexible user constraints for design.

Provides a responsive, controllable layout generation process.

Abstract

We present iPoster, an interactive layout generation framework that empowers users to guide content-aware poster layout design by specifying flexible constraints. iPoster enables users to specify partial intentions within the intention module, such as element categories, sizes, positions, or coarse initial drafts. Then, the generation module instantly generates refined, context-sensitive layouts that faithfully respect these constraints. iPoster employs a unified graph-enhanced diffusion architecture that supports various design tasks under user-specified constraints. These constraints are enforced through masking strategies that precisely preserve user input at every denoising step. A cross content-aware attention module aligns generated elements with salient regions of the canvas, ensuring visual coherence. Extensive experiments show that iPoster not only achieves state-of-the-art layout quality, but offers a responsive and controllable framework for poster layout design with constraints.