自适应提示引导用于文本到图像生成
Adaptive Prompt Elicitation for Text-to-Image Generation
AI总结:
本文提出自适应提示引导技术,通过交互式意图推断框架提升文本到图像生成与用户意图的对齐效率,实验表明其在准确性和效率上均优于现有方法。
摘要:
将文本到图像生成与用户意图对齐仍具挑战性,因为用户经常提供模糊输入且难以应对模型特性。我们提出自适应提示引导(APE),一种能自适应提出视觉查询以帮助用户细化提示而无需大量写作的技术。我们的技术贡献是基于信息论框架的交互式意图推断公式。APE利用语言模型先验知识将潜在用户意图表示为可解释的特征需求,自适应生成视觉查询,并将获取的需求编译成有效的提示。在IDEA-Bench和DesignBench上的评估表明,APE在对齐性上更强且效率更高。与128名参与者进行的用户研究显示,在无增加工作量的情况下,感知对齐度提高了19.8%。我们的工作为提示提供了系统的方法,为文本到图像模型的主流提示交互范式提供了有效且高效的补充。
英文摘要:
Aligning text-to-image generation with user intent remains challenging, as users frequently provide ambiguous inputs and struggle with model idiosyncrasies. We propose Adaptive Prompt Elicitation (APE), a technique that adaptively poses visual queries to help users refine prompts without extensive writing. Our technical contribution is a formulation of interactive intent inference under an information-theoretic framework. APE represents latent user intent as interpretable feature requirements using language model priors, adaptively generates visual queries, and compiles elicited requirements into effective prompts. Evaluation on IDEA-Bench and DesignBench shows that APE achieves stronger alignment with improved efficiency. A user study with 128 participants on user-defined tasks demonstrates 19.8% higher perceived alignment without increased workload. Our work contributes a principled approach to prompting that offers an effective and efficient complement to the prevailing prompt-based interaction paradigm with text-to-image models.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。