这是一个特性,而不是Bug:测量图像生成器中的创造性流动性
It's a Feature, Not a Bug: Measuring Creative Fluidity in Image Generators
AI总结:
本文通过定义和测量“提示词解释的流动性”,利用自动生成提示词图像链、视觉语义指标及统计测试,实证研究了流行图像生成器中AI创造性行为的一个方面。
摘要:
随着免费图像生成器的兴起,AI生成的艺术已成为一系列激烈争论的焦点,其中之一涉及人类创造力的概念。图像生成AI能否表现出与艺术家相同类型的“创造力”?如果能,这又是如何表现的?本文试图通过实验来定义并实证测量AI创造性行为的一个方面,即在一系列选定的流行图像生成器中量化“提示词解释的流动性”(或简称“流动性”)。为了研究流动性,我们(1)为其引入了明确的定义,(2)创建了以初始“真实”图像为种子的自动生成提示词和图像链,(3)使用现有的视觉和语义指标测量这些链的断裂点,以及(4)使用统计测试和视觉解释来研究这些链,并确定用于生成它们的图像生成器是否表现出显著的流动性。
英文摘要:
With the rise of freely available image generators, AI-generated art has become the centre of a series of heated debates, one of which concerns the concept of human creativity. Can an image generation AI exhibit ``creativity'' of the same type that artists do, and if so, how does that manifest? Our paper attempts to define and empirically measure one facet of creative behavior in AI, by conducting an experiment to quantify the "fluidity of prompt interpretation", or just "fluidity", in a series of selected popular image generators. To study fluidity, we (1) introduce a clear definition for it, (2) create chains of auto-generated prompts and images seeded with an initial "ground-truth: image, (3) measure these chains' breakage points using preexisting visual and semantic metrics, and (4) use both statistical tests and visual explanations to study these chains and determine whether the image generators used to produce them exhibit significant fluidity.
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。