Best Prompts for Text-to-Image Models and How to Find Them

Autor:	Pavlichenko, Nikita, Ustalov, Dmitry
Rok vydání:	2022
Předmět:	Computer Science - Human-Computer Interaction Computer Science - Computation and Language Computer Science - Computer Vision and Pattern Recognition H.5.2 H.3.3
Druh dokumentu:	Working Paper
DOI:	10.1145/3539618.3592000
Popis:	Recent progress in generative models, especially in text-guided diffusion models, has enabled the production of aesthetically-pleasing imagery resembling the works of professional human artists. However, one has to carefully compose the textual description, called the prompt, and augment it with a set of clarifying keywords. Since aesthetics are challenging to evaluate computationally, human feedback is needed to determine the optimal prompt formulation and keyword combination. In this paper, we present a human-in-the-loop approach to learning the most useful combination of prompt keywords using a genetic algorithm. We also show how such an approach can improve the aesthetic appeal of images depicting the same descriptions. Comment: 13 pages (6 main pages), 7 figures, 4 tables, accepted at SIGIR '23 Short Paper Track
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2209.11711 Zobrazit plný text záznamu View this record from Arxiv