AniME: Adaptive Multi-Agent Planning for Long Animation Generation

TL;DR

AniME is a multi-agent system that automates long-form anime production by coordinating specialized agents to generate cinematic animations with consistent characters and synchronized audio, streamlining AI-driven anime creation.

Contribution

Introduces AniME, a novel multi-agent framework with a global memory and adaptive control for scalable, automated long-form anime generation.

Findings

Produces consistent characters across episodes

Synchronizes audio and visual elements effectively

Scalable for full-length anime production

Abstract

We present AniME, a director-oriented multi-agent system for automated long-form anime production, covering the full workflow from a story to the final video. The director agent keeps a global memory for the whole workflow, and coordinates several downstream specialized agents. By integrating customized Model Context Protocol (MCP) with downstream model instruction, the specialized agent adaptively selects control conditions for diverse sub-tasks. AniME produces cinematic animation with consistent characters and synchronized audio visual elements, offering a scalable solution for AI-driven anime creation.