T-Stars-Poster: A Framework for Product-Centric Advertising Image Design

TL;DR

T-Stars-Poster is a comprehensive framework that automates advertising image creation by sequentially generating prompts, layouts, backgrounds, and graphics, significantly improving visual appeal and efficiency.

Contribution

It introduces a novel multi-stage, product-centric framework with specialized models and datasets for automated advertising image design, filling a gap in existing methods.

Findings

Produces more visually appealing images in experiments

Outperforms baseline methods in aesthetic quality

Validated through online A/B testing

Abstract

Creating advertising images is often a labor-intensive and time-consuming process. Can we automatically generate such images using basic product information like a product foreground image, taglines, and a target size? Existing methods mainly focus on parts of the problem and lack a comprehensive solution. To bridge this gap, we propose a novel product-centric framework for advertising image design called T-Stars-Poster. It consists of four sequential stages to highlight product foregrounds and taglines while achieving overall image aesthetics: prompt generation, layout generation, background image generation, and graphics rendering. Different expert models are designed and trained for the first three stages: First, a visual language model (VLM) generates background prompts that match the products. Next, a VLM-based layout generation model arranges the placement of product foregrounds, graphic elements (taglines and decorative underlays), and various nongraphic elements (objects from the background prompt). Following this, an SDXL-based model can simultaneously accept prompts, layouts, and foreground controls to generate images. To support T-Stars-Poster, we create two corresponding datasets with over 50,000 labeled images. Extensive experiments and online A/B tests demonstrate that T-Stars-Poster can produce more visually appealing advertising images.