From Prompt to Production:Automating Brand-Safe Marketing Imagery with Text-to-Image Models

TL;DR

This paper introduces a scalable, automated pipeline for generating brand-safe marketing images using text-to-image models, balancing automation with human oversight to ensure quality and creativity.

Contribution

It presents a novel fully automated pipeline that maintains image quality and creative variation for marketing, integrating human oversight for brand safety.

Findings

30.77% increase in marketing object fidelity with DINOV2

52.00% increase in human preference for generated images

Achieved scalable, high-quality image generation for marketing use cases

Abstract

Text-to-image models have made significant strides, producing impressive results in generating images from textual descriptions. However, creating a scalable pipeline for deploying these models in production remains a challenge. Achieving the right balance between automation and human feedback is critical to maintain both scale and quality. While automation can handle large volumes, human oversight is still an essential component to ensure that the generated images meet the desired standards and are aligned with the creative vision. This paper presents a new pipeline that offers a fully automated, scalable solution for generating marketing images of commercial products using text-to-image models. The proposed system maintains the quality and fidelity of images, while also introducing sufficient creative variation to adhere to marketing guidelines. By streamlining this process, we ensure a seamless blend of efficiency and human oversight, achieving a $30.77\%$ increase in marketing object fidelity using DINOV2 and a $52.00\%$ increase in human preference over the generated outcome.