SkillPE:面向文本到视频提示工程的创意导向电影技能进化
SkillPE: Creativity-Oriented Cinematic Skill Evolution for Text-to-Video Prompt Engineering
- HKUST(香港科技大学)
- KlingAI(可灵AI)
- Shanghai Jiaotong University(上海交通大学)
- The University of Hong Kong(香港大学)
机构由 AI 辅助整理,请以论文原文为准。
AI总结:
SkillPE是一个提示工程框架,通过从专家种子进化可复用的电影技能,并利用电影参考分类(共鸣器、不和谐音、发散项)来优化技能应用和激发创意,在StoryEval和VBench上提升了文本到视频生成的保真度与创造力。
AI中文摘要:
对于非专家而言,在文本到视频生成中实现高质量、电影般的效果仍然具有挑战性,因为他们的提示往往缺乏专业的叙事和创意设计。我们提出了SkillPE,一个提示工程(PE)框架,它从专家撰写的种子中进化出可复用的电影技能。SkillPE以细粒度的格式表示镜头逻辑、构图、灯光、声音设计和其他电影制作线索,并检索电影参考,将其分类为共鸣器(良好匹配)、不和谐音(弱匹配)和发散项(具有创意用途的近似未命中)。前两者优化了技能应用的时间和方式,而发散项则在保持用户意图的同时,以不同的修改程度激发替代性的电影实现。候选技能通过生成的视频在提示保真度、电影质量、叙事吸引力和创造力方面进行评估,以构建最终的技能库。在StoryEval和VBench上的实验显示,在7点四维评估中,相对于最强外部基线最高提升1.40分,相对于种子技能提升0.51分,同时在基准原生指标上保持竞争力。总体而言,SkillPE提供了一种在电影文本到视频生成中平衡保真度和创造力的实用方法。代码可在该https URL获取。
英文摘要:
Achieving high-quality, cinematic results in text-to-video generation remains challenging for non-experts, whose prompts often lack professional narrative and creative design. We propose SkillPE, a prompt engineering (PE) framework that evolves reusable cinematic skills from expert-authored seeds. SkillPE represents shot logic, composition, lighting, sound design, and other filmmaking cues in a fine-grained format, and retrieves movie references categorized as resonators (good matches), dissonants (weak matches), and divergents (creatively useful near-misses). The first two refine when and how a skill should be applied, while divergents inspire alternative cinematic realizations at different degrees of modification while preserving the 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 show improvements of up to 1.40 points over the strongest external baseline and 0.51 points over seed skills on 7-point four-dimensional evaluation, while remaining competitive on benchmark-native metrics. Overall, SkillPE offers a practical approach to balancing fidelity and creativity in cinematic text-to-video generation. Code is available at https://github.com/Ais0n/SkillPE .