PosterLlama: Bridging Design Ability of Langauge Model to Contents-Aware Layout Generation
This addresses the need for more semantically rich and visually appealing layouts in fields like advertising and web UI design, representing an incremental improvement over prior generative models.
The authors tackled the problem of content-aware layout generation in graphic design by introducing PosterLlama, which reformats layout elements into HTML code to leverage language models' design knowledge, resulting in outperforming existing methods across benchmarks with support for various conditions like unconditional generation and layout completion.
Visual layout plays a critical role in graphic design fields such as advertising, posters, and web UI design. The recent trend towards content-aware layout generation through generative models has shown promise, yet it often overlooks the semantic intricacies of layout design by treating it as a simple numerical optimization. To bridge this gap, we introduce PosterLlama, a network designed for generating visually and textually coherent layouts by reformatting layout elements into HTML code and leveraging the rich design knowledge embedded within language models. Furthermore, we enhance the robustness of our model with a unique depth-based poster augmentation strategy. This ensures our generated layouts remain semantically rich but also visually appealing, even with limited data. Our extensive evaluations across several benchmarks demonstrate that PosterLlama outperforms existing methods in producing authentic and content-aware layouts. It supports an unparalleled range of conditions, including but not limited to unconditional layout generation, element conditional layout generation, layout completion, among others, serving as a highly versatile user manipulation tool.