AniMaker: Multi-Agent Animated Storytelling with MCTS-Driven Clip Generation

TL;DR

AniMaker is a multi-agent framework that generates coherent storytelling animations from text by using MCTS-driven clip generation and a specialized evaluation system, improving quality and efficiency over existing methods.

Contribution

This paper introduces AniMaker, the first multi-agent system combining MCTS-based clip generation and a novel animation evaluation framework for story-coherent video creation from text.

Findings

Achieves higher quality animations as per VBench and AniEval metrics.

Significantly improves multi-candidate clip generation efficiency.

Creates more coherent and story-consistent animations from text input.

Abstract

Despite rapid advancements in video generation models, generating coherent storytelling videos that span multiple scenes and characters remains challenging. Current methods often rigidly convert pre-generated keyframes into fixed-length clips, resulting in disjointed narratives and pacing issues. Furthermore, the inherent instability of video generation models means that even a single low-quality clip can significantly degrade the entire output animation's logical coherence and visual continuity. To overcome these obstacles, we introduce AniMaker, a multi-agent framework enabling efficient multi-candidate clip generation and storytelling-aware clip selection, thus creating globally consistent and story-coherent animation solely from text input. The framework is structured around specialized agents, including the Director Agent for storyboard generation, the Photography Agent for video clip generation, the Reviewer Agent for evaluation, and the Post-Production Agent for editing and voiceover. Central to AniMaker's approach are two key technical components: MCTS-Gen in Photography Agent, an efficient Monte Carlo Tree Search (MCTS)-inspired strategy that intelligently navigates the candidate space to generate high-potential clips while optimizing resource usage; and AniEval in Reviewer Agent, the first framework specifically designed for multi-shot animation evaluation, which assesses critical aspects such as story-level consistency, action completion, and animation-specific features by considering each clip in the context of its preceding and succeeding clips. Experiments demonstrate that AniMaker achieves superior quality as measured by popular metrics including VBench and our proposed AniEval framework, while significantly improving the efficiency of multi-candidate generation, pushing AI-generated storytelling animation closer to production standards.