Prompting for Discovery: Flexible Sense-Making for AI Art-Making with Dreamsheets

要旨

Design space exploration (DSE) for Text-to-Image (TTI) models entails navigating a vast, opaque space of possible image outputs, through a commensurately vast input space of hyperparameters and prompt text. Perceptually small movements in prompt-space can surface unexpectedly disparate images. How can interfaces support end-users in reliably steering prompt-space explorations towards interesting results? Our design probe, DreamSheets, supports user-composed exploration strategies with LLM-assisted prompt construction and large-scale simultaneous display of generated results, hosted in a spreadsheet interface. Two studies, a preliminary lab study and an extended two-week study where five expert artists developed custom TTI sheet-systems, reveal various strategies for targeted TTI design space exploration---such as using templated text generation to define and layer semantic ``axes'' for exploration. We identified patterns in exploratory structures across our participants' sheet-systems: configurable exploration ``units'' that we distill into a UI mockup, and generalizable UI components to guide future interfaces.

著者
Shm Garanganao. Almeda
University of California: Berkeley, Berkeley, California, United States
J.D. Zamfirescu-Pereira
UC Berkeley, Berkeley, California, United States
Kyu Won Kim
UC Berkeley, Berkeley, California, United States
Pradeep Mani Rathnam
UC Berkeley, Berkeley, California, United States
Bjoern Hartmann
UC Berkeley, Berkeley, California, United States
論文URL

https://doi.org/10.1145/3613904.3642858

動画

会議: CHI 2024

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2024.acm.org/)

セッション: Creative Media and AI

323C
5 件の発表
2024-05-15 20:00:00
2024-05-15 21:20:00