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

268Citations
Citations of this article
283Readers
Mendeley users who have this article in their library.
Get full text

Abstract

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.

References Powered by Scopus

Semantics derived automatically from language corpora contain human-like biases

1761Citations
N/AReaders
Get full text

Concreteness ratings for 40 thousand generally known English word lemmas

1280Citations
N/AReaders
Get full text

Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm

366Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Generative AI and ChatGPT: Applications, challenges, and AI-human collaboration

308Citations
N/AReaders
Get full text

Attend-And-Excite: Attention-Based Semantic Guidance for Text-To-Image Diffusion Models

123Citations
N/AReaders
Get full text

The Creativity of Text-to-Image Generation

101Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Liu, V., & Chilton, L. B. (2022). Design Guidelines for Prompt Engineering Text-to-Image Generative Models. In Conference on Human Factors in Computing Systems - Proceedings. Association for Computing Machinery. https://doi.org/10.1145/3491102.3501825

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 49

60%

Researcher 12

15%

Professor / Associate Prof. 11

13%

Lecturer / Post doc 10

12%

Readers' Discipline

Tooltip

Computer Science 39

52%

Engineering 17

23%

Design 11

15%

Business, Management and Accounting 8

11%

Article Metrics

Tooltip
Mentions
References: 3
Social Media
Shares, Likes & Comments: 18

Save time finding and organizing research with Mendeley

Sign up for free