Integrating Large Language Models into Text Animation: An Intelligent Editing System with Inline and Chat Interaction

TL;DR

This paper presents an LLM-assisted text animation editing system that simplifies the workflow for non-professionals by providing real-time suggestions, conversational guidance, and synchronized previews, enhancing creative productivity.

Contribution

It introduces a novel agent-based dual-stream pipeline integrating context-aware suggestions and semantic-animation mapping for intuitive text animation editing.

Findings

System enables non-professionals to complete animation tasks effectively.

Real-time inline suggestions and chat guidance improve editing efficiency.

User study validates the system's usability and pipeline effectiveness.

Abstract

Text animation, a foundational element in video creation, enables efficient and cost-effective communication, thriving in advertisements, journalism, and social media. However, traditional animation workflows present significant usability barriers for non-professionals, with intricate operational procedures severely hindering creative productivity. To address this, we propose a Large Language Model (LLM)-aided text animation editing system that enables real-time intent tracking and flexible editing. The system introduces an agent-based dual-stream pipeline that integrates context-aware inline suggestions and conversational guidance as well as employs a semantic-animation mapping to facilitate LLM-driven creative intent translation. Besides, the system supports synchronized text-animation previews and parametric adjustments via unified controls to improve editing workflow. A user study evaluates the system, highlighting its ability to help non-professional users complete animation workflows while validating the pipeline. The findings encourage further exploration of integrating LLMs into a comprehensive video creation workflow.