ETPDesigner: Multi-Agent Orchestration for Interactive Multimodal Electronic Theater Program

2026-07-22

AI Summary

This work addresses the limitations of existing text-to-image methods in handling long-form script narratives and maintaining visual consistency across multi-page electronic theater programs (ETPs). To overcome these challenges, we propose a multi-agent collaborative framework that directly generates high-quality, stylistically coherent multi-page ETPs from raw scripts while enabling character animation and real-time voice interaction. The framework incorporates a global style anchoring mechanism to ensure cross-page visual consistency and integrates modules for semantic script analysis, hierarchical character composition, portrait animation, customized voice synthesis, and a personalized large language model, thereby transforming static programs into immersive interactive experiences. Extensive experiments on our newly curated, professional-grade ETP-Pro benchmark demonstrate that our approach significantly outperforms current methods in semantic fidelity, aesthetic consistency, and interactivity.

Abstract

Electronic Theater Programs (ETPs) serve as critical promotional media in the performing arts, comprising a multi-page collection of heterogeneous visual assets such as theatrical posters, performance details, and character portraits. However, existing text-to-image paradigms struggle with such complex design tasks due to their inability to comprehend long-context narratives and maintain visual consistency across multiple distinct pages. To address this, we introduce ETPDesigner, a collaborative Multi-Agent framework that directly synthesizes high-quality ETPs from raw dramatic scripts. Emulating a professional design pipeline, our framework orchestrates specialized agents for semantic script analysis, core poster synthesis, functional background generation, and the stratified composition of character assets. Central to ETPDesigner is a global style anchor mechanism that extracts visual priors from the core poster to enforce strict aesthetic uniformity across all generated components. Furthermore, we elevate the ETP from a static publication to an immersive interactive companion. By integrating portrait animation, customized speech synthesis, and persona-grounded Large Language Models (LLMs), our system enables users to engage in real-time, voice-enabled conversations with the generated virtual characters. To rigorously benchmark this task, we construct ETP-Pro, a domain-specific benchmark of professional theater posters and high-quality character portraits. Extensive evaluations demonstrate our method's superiority in producing semantically faithful, aesthetically consistent, and highly interactive program sets.

Problem

• Electronic Theater Programs
• text-to-image generation
• visual consistency
• multimodal interaction
• long-context understanding

Innovation

• Multi-Agent Orchestration
• Global Style Anchor
• Interactive Multimodal ETP
• Persona-Grounded LLMs
• Visual Consistency