Research

Paper

AI LLM February 24, 2026

AnimeAgent: Is the Multi-Agent via Image-to-Video models a Good Disney Storytelling Artist?

Authors

Hailong Yan, Shice Liu, Tao Wang, Xiangtao Zhang, Yijie Zhong, Jinwei Chen, Le Zhang, Bo Li

Abstract

Custom Storyboard Generation (CSG) aims to produce high-quality, multi-character consistent storytelling. Current approaches based on static diffusion models, whether used in a one-shot manner or within multi-agent frameworks, face three key limitations: (1) Static models lack dynamic expressiveness and often resort to "copy-paste" pattern. (2) One-shot inference cannot iteratively correct missing attributes or poor prompt adherence. (3) Multi-agents rely on non-robust evaluators, ill-suited for assessing stylized, non-realistic animation. To address these, we propose AnimeAgent, the first Image-to-Video (I2V)-based multi-agent framework for CSG. Inspired by Disney's "Combination of Straight Ahead and Pose to Pose" workflow, AnimeAgent leverages I2V's implicit motion prior to enhance consistency and expressiveness, while a mixed subjective-objective reviewer enables reliable iterative refinement. We also collect a human-annotated CSG benchmark with ground-truth. Experiments show AnimeAgent achieves SOTA performance in consistency, prompt fidelity, and stylization.

Metadata

arXiv ID: 2602.20664
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-02-24
Fetched: 2026-02-25 06:05

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.20664v1</id>\n    <title>AnimeAgent: Is the Multi-Agent via Image-to-Video models a Good Disney Storytelling Artist?</title>\n    <updated>2026-02-24T08:14:24Z</updated>\n    <link href='https://arxiv.org/abs/2602.20664v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.20664v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Custom Storyboard Generation (CSG) aims to produce high-quality, multi-character consistent storytelling. Current approaches based on static diffusion models, whether used in a one-shot manner or within multi-agent frameworks, face three key limitations: (1) Static models lack dynamic expressiveness and often resort to \"copy-paste\" pattern. (2) One-shot inference cannot iteratively correct missing attributes or poor prompt adherence. (3) Multi-agents rely on non-robust evaluators, ill-suited for assessing stylized, non-realistic animation. To address these, we propose AnimeAgent, the first Image-to-Video (I2V)-based multi-agent framework for CSG. Inspired by Disney's \"Combination of Straight Ahead and Pose to Pose\" workflow, AnimeAgent leverages I2V's implicit motion prior to enhance consistency and expressiveness, while a mixed subjective-objective reviewer enables reliable iterative refinement. We also collect a human-annotated CSG benchmark with ground-truth. Experiments show AnimeAgent achieves SOTA performance in consistency, prompt fidelity, and stylization.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-02-24T08:14:24Z</published>\n    <arxiv:comment>Tech Report</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Hailong Yan</name>\n    </author>\n    <author>\n      <name>Shice Liu</name>\n    </author>\n    <author>\n      <name>Tao Wang</name>\n    </author>\n    <author>\n      <name>Xiangtao Zhang</name>\n    </author>\n    <author>\n      <name>Yijie Zhong</name>\n    </author>\n    <author>\n      <name>Jinwei Chen</name>\n    </author>\n    <author>\n      <name>Le Zhang</name>\n    </author>\n    <author>\n      <name>Bo Li</name>\n    </author>\n  </entry>"
}