CTR-Driven Advertising Image Generation with Multimodal Large Language Models

TL;DR

This paper introduces a novel approach using Multimodal Large Language Models optimized with reinforcement learning to generate advertising images that maximize click-through rates, outperforming existing methods in relevance and effectiveness.

Contribution

The authors develop a CTR-optimized image generation framework with a new reward model and product-centric strategy, advancing the use of MLLMs in advertising.

Findings

Achieves state-of-the-art CTR performance in online and offline tests.

Effectively aligns generated images with product features.

Demonstrates the benefit of reinforcement learning in multimodal image generation.

Abstract

In web data, advertising images are crucial for capturing user attention and improving advertising effectiveness. Most existing methods generate background for products primarily focus on the aesthetic quality, which may fail to achieve satisfactory online performance. To address this limitation, we explore the use of Multimodal Large Language Models (MLLMs) for generating advertising images by optimizing for Click-Through Rate (CTR) as the primary objective. Firstly, we build targeted pre-training tasks, and leverage a large-scale e-commerce multimodal dataset to equip MLLMs with initial capabilities for advertising image generation tasks. To further improve the CTR of generated images, we propose a novel reward model to fine-tune pre-trained MLLMs through Reinforcement Learning (RL), which can jointly utilize multimodal features and accurately reflect user click preferences. Meanwhile, a product-centric preference optimization strategy is developed to ensure that the generated background content aligns with the product characteristics after fine-tuning, enhancing the overall relevance and effectiveness of the advertising images. Extensive experiments have demonstrated that our method achieves state-of-the-art performance in both online and offline metrics. Our code and pre-trained models are publicly available at: https://github.com/Chenguoz/CAIG.