arXiv cs.AI· Yanwei Huang, Mingxuan Zhu, Shujie Li, Shiyuan Liu, Yuanxing Zhang, Arpit Narechania·· 4 小时前AI 评分29
SkillPE:面向创造力的电影化技能演化,用于文本到视频提示词增强
SkillPE: Creativity-Oriented Cinematic Skill Evolution for Text-to-Video Prompt Enhancement
AI 导读
SkillPE 是一个面向创造力的提示词增强框架,通过参考引导探索系统演化可复用的电影化技能,从专家知识初始化并规范化 20 个结构化种子技能。它检索电影参考并分为共鸣、失谐与发散三类,前两者优化技能适用性与执行,发散项通过受控变异激发替代性电影化实现。在 StoryEval 和 VBench 上,其 7 分制四维评测较种子技能最高提升 1.10 分,较最强外部基线提升 1.02 分。
正文 · 原文
Abstract:Achieving high-quality cinematic text-to-video generation remains challenging for non-experts, whose prompts often lack professional narrative and creative design. Existing prompt enhancement (PE) methods and static cinematic skills offer limited capabilities for exploring diverse creative realizations. We propose SkillPE, a creativity-oriented PE framework that systematically evolves reusable cinematic skills through reference-guided exploration. Starting from expert-provided cinematic knowledge, SkillPE initializes and normalizes 20 structured seed skills. It then retrieves movie references categorized as resonators (good matches), dissonants (weak matches), and divergents (creatively inspiring near-misses). Resonators and dissonants refine skill applicability and execution, while divergents inspire alternative cinematic realizations through controlled mutations that preserve user intent. Candidate skills are assessed through generated videos along prompt fidelity, cinematic quality, narrative appeal, and creativity to construct the final skill libraries. Experiments on StoryEval and VBench demonstrate improvements of up to 1.10 points over seed skills and 1.02 points over the strongest external baseline on a 7-point four-dimensional evaluation scale. Overall, SkillPE offers a practical approach to balancing fidelity and creativity in cinematic text-to-video generation.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2609.34335 [cs.CV] |
| (or arXiv:2609.34335v2 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2609.34335 arXiv-issued DOI via DataCite |
Submission history
From: Yanwei Huang [view email]
[v1]
Mon, 28 Sep 2026 05:11:39 UTC (14,778 KB)
[v2]
Tue, 17 Nov 2026 15:19:37 UTC (14,316 KB)
来源:arXiv cs.AI · arxiv.org