主题(文档)
复数
代表(政治)
计算机科学
图像(数学)
生成语法
人工智能
注释
质量(理念)
生成模型
自然语言处理
语言学
万维网
政治
政治学
法学
哲学
认识论
作者
Han Qiao,Vivian Liu,Lydia B. Chilton
出处
期刊:Creativity and Cognition
日期:2022-06-20
被引量:19
标识
DOI:10.1145/3527927.3532792
摘要
Advances in text-to-image generative models have made it easier for people to create art by just prompting models with text. However, creating through text leaves users with limited control over the final composition or the way the subject is represented. A potential solution is to use image prompts alongside text prompts to condition the model. To better understand how and when image prompts can improve subject representation in generations, we conduct an annotation experiment to quantify their effect on generations of abstract, concrete plural, and concrete singular subjects. We find that initial images improved subject representation across all subject types, with the most noticeable improvement in concrete singular subjects. In an analysis of different types of initial images, we find that icons and photos produced high quality generations of different aesthetics. We conclude with design guidelines for how initial images can improve subject representation in AI art.
科研通智能强力驱动
Strongly Powered by AbleSci AI