Chaining Text-to-image and Large Language Model: A Novel Approach for Generating Personalized E-Commerce Banners

Text-to-image models such as stable diffusion have opened a plethora ofopportunities for generating art. Recent literature has surveyed the use oftext-to-image models for enhancing the work of many creative artists. Manye-commerce platforms employ a manual process to generate the banners, which istime-consuming and has limitations of scalability. In this work, we demonstratethe use of text-to-image models for generating personalized web banners withdynamic content for online shoppers based on their interactions. The novelty inthis approach lies in converting users' interaction data to meaningful promptswithout human intervention. To this end, we utilize a large language model(LLM) to systematically extract a tuple of attributes from itemmeta-information. The attributes are then passed to a text-to-image model viaprompt engineering to generate images for the banner. Our results show that theproposed approach can create high-quality personalized banners for users.