Design Guidelines for Prompt Engineering Text-to-Image Generative Models 论文

2022CHI Conference on Human Factors in Computing Systems引用 537

Generative Adversarial Networks and Image SynthesisAesthetic Perception and AnalysisComputer Graphics and Visualization Techniques

Generative Adversarial Networks and Image Synthesis Computer Graphics and Visualization Techniques Aesthetic Perception and Analysis

关系图谱

作者

摘要

Text-to-image generative models are a new and powerful way to generate visual artwork. However, the open-ended nature of text as interaction is double-edged; while users can input anything and have access to an infinite range of generations, they also must engage in brute-force trial and error with the text prompt when the result quality is poor. We conduct a study exploring what prompt keywords and model hyperparameters can help produce coherent outputs. In particular, we study prompts structured to include subject and style keywords and investigate success and failure modes of these prompts. Our evaluation of 5493 generations over the course of five experiments spans 51 abstract and concrete subjects as well as 51 abstract and figurative styles. From this evaluation, we present design guidelines that can help people produce better outcomes from text-to-image generative models.

作者查看全部 (2)

Lydia B. Chilton

Vivian Liu

Design Guidelines for Prompt Engineering Text-to-Image Generative Models 论文

详细信息

摘要

作者查看全部 (2)

相关技术查看全部 (1)

相关事件

相关文章