BrandFusion: A Multi-Agent Framework for Seamless Brand Integration in Text-to-Video Generation

TL;DR

BrandFusion is a multi-agent framework that enables seamless and natural integration of brands into text-to-video content, improving recognizability and semantic fidelity for commercial applications.

Contribution

It introduces the first framework for automatic brand embedding in T2V videos, combining offline knowledge base construction with online prompt refinement.

Findings

Outperforms baselines in semantic preservation and brand recognizability

Demonstrates effectiveness across 20 brands and multiple T2V models

Enhances user satisfaction and supports T2V monetization

Abstract

The rapid advancement of text-to-video (T2V) models has revolutionized content creation, yet their commercial potential remains largely untapped. We introduce, for the first time, the task of seamless brand integration in T2V: automatically embedding advertiser brands into prompt-generated videos while preserving semantic fidelity to user intent. This task confronts three core challenges: maintaining prompt fidelity, ensuring brand recognizability, and achieving contextually natural integration. To address them, we propose BrandFusion, a novel multi-agent framework comprising two synergistic phases. In the offline phase (advertiser-facing), we construct a Brand Knowledge Base by probing model priors and adapting to novel brands via lightweight fine-tuning. In the online phase (user-facing), five agents jointly refine user prompts through iterative refinement, leveraging the shared knowledge base and real-time contextual tracking to ensure brand visibility and semantic alignment. Experiments on 18 established and 2 custom brands across multiple state-of-the-art T2V models demonstrate that BrandFusion significantly outperforms baselines in semantic preservation, brand recognizability, and integration naturalness. Human evaluations further confirm higher user satisfaction, establishing a practical pathway for sustainable T2V monetization.