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.
Figures & tables
Figure 1. The overall training framework of content-aware layout generation model (shown in the left). The core module is Cross Content-aware Attention Module (shown in the right).
Figure 2. The construction process of GBLM and GILM . For each bboxi , c is the element category, cx and cy are its center coordinates, and w and h are its width and height. Each image is divided into r rows and c columns of patches. See Section 3.2.2 for details.
Figure 3. iPoster’s interactive framework, showing user interaction and mask execution during inference.
Figure 4
PosterLlama ( Seol et al., 2024 )
PosterO ( Hsu and Peng, 2025 )
LayoutDiT ( Li et al., 2024 )
iPoster
Params
7B
8B
49M
33M
Inference Time(s)
7.6
7.5
1.5
1.1
Table 2. Comparison of model parameter counts and end-to-end inference latency for batch size of 1.
Figure 5. Illustration of a representative user scenario. The left side presents a schematic UI mockup depicting user interactions, and the right side shows the resulting layout candidates along with the final posters automatically rendered from them.