AnimeAgent: Is the Multi-Agent via Image-to-Video models a Good Disney Storytelling Artist?
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917291250155520 |
|---|---|
| author | Yan, Hailong Liu, Shice Wang, Tao Zhang, Xiangtao Zhong, Yijie Chen, Jinwei Zhang, Le Li, Bo |
| author_facet | Yan, Hailong Liu, Shice Wang, Tao Zhang, Xiangtao Zhong, Yijie Chen, Jinwei Zhang, Le Li, Bo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_20664 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AnimeAgent: Is the Multi-Agent via Image-to-Video models a Good Disney Storytelling Artist? Yan, Hailong Liu, Shice Wang, Tao Zhang, Xiangtao Zhong, Yijie Chen, Jinwei Zhang, Le Li, Bo Computer Vision and Pattern Recognition 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. |
| title | AnimeAgent: Is the Multi-Agent via Image-to-Video models a Good Disney Storytelling Artist? |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.20664 |