A Versatile Multimodal Agent for Multimedia Content Generation

TL;DR

This paper introduces a versatile MultiMedia-Agent system that automates complex multimodal content creation, integrating various media types and optimizing plans for improved multimedia generation.

Contribution

It presents a novel agent-based framework with a two-stage correlation strategy and skill acquisition theory for training data curation and content generation.

Findings

The MultiMedia-Agent outperforms existing models in multimedia content quality.

The proposed training approach enhances plan optimization and content coherence.

The system effectively integrates multimodal inputs for end-to-end content creation.

Abstract

With the advancement of AIGC (AI-generated content) technologies, an increasing number of generative models are revolutionizing fields such as video editing, music generation, and even film production. However, due to the limitations of current AIGC models, most models can only serve as individual components within specific application scenarios and are not capable of completing tasks end-to-end in real-world applications. In real-world applications, editing experts often work with a wide variety of images and video inputs, producing multimodal outputs -- a video typically includes audio, text, and other elements. This level of integration across multiple modalities is something current models are unable to achieve effectively. However, the rise of agent-based systems has made it possible to use AI tools to tackle complex content generation tasks. To deal with the complex scenarios, in this paper, we propose a MultiMedia-Agent designed to automate complex content creation. Our agent system includes a data generation pipeline, a tool library for content creation, and a set of metrics for evaluating preference alignment. Notably, we introduce the skill acquisition theory to model the training data curation and agent training. We designed a two-stage correlation strategy for plan optimization, including self-correlation and model preference correlation. Additionally, we utilized the generated plans to train the MultiMedia-Agent via a three stage approach including base/success plan finetune and preference optimization. The comparison results demonstrate that the our approaches are effective and the MultiMedia-Agent can generate better multimedia content compared to novel models.