@inproceedings{rosenman-etal-2024-neuroprompts,
title = "{N}euro{P}rompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation",
author = "Rosenman, Shachar and
Lal, Vasudev and
Howard, Phillip",
editor = "Aletras, Nikolaos and
De Clercq, Orphee",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
month = mar,
year = "2024",
address = "St. Julians, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-demo.17",
pages = "159--167",
abstract = "Despite impressive recent advances in text-to-image diffusion models, obtaining high-quality images often requires prompt engineering by humans who have developed expertise in using them. In this work, we present NeuroPrompts, an adaptive framework that automatically enhances a user{'}s prompt to improve the quality of generations produced by text-to-image models. Our framework utilizes constrained text decoding with a pre-trained language model that has been adapted to generate prompts similar to those produced by human prompt engineers. This approach enables higher-quality text-to-image generations and provides user control over stylistic features via constraint set specification. We demonstrate the utility of our framework by creating an interactive application for prompt enhancement and image generation using Stable Diffusion. Additionally, we conduct experiments utilizing a large dataset of human-engineered prompts for text-to-image generation and show that our approach automatically produces enhanced prompts that result in superior image quality. We make our code, a screencast video demo and a live demo instance of NeuroPrompts publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rosenman-etal-2024-neuroprompts">
<titleInfo>
<title>NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shachar</namePart>
<namePart type="family">Rosenman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasudev</namePart>
<namePart type="family">Lal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Phillip</namePart>
<namePart type="family">Howard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orphee</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julians, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite impressive recent advances in text-to-image diffusion models, obtaining high-quality images often requires prompt engineering by humans who have developed expertise in using them. In this work, we present NeuroPrompts, an adaptive framework that automatically enhances a user’s prompt to improve the quality of generations produced by text-to-image models. Our framework utilizes constrained text decoding with a pre-trained language model that has been adapted to generate prompts similar to those produced by human prompt engineers. This approach enables higher-quality text-to-image generations and provides user control over stylistic features via constraint set specification. We demonstrate the utility of our framework by creating an interactive application for prompt enhancement and image generation using Stable Diffusion. Additionally, we conduct experiments utilizing a large dataset of human-engineered prompts for text-to-image generation and show that our approach automatically produces enhanced prompts that result in superior image quality. We make our code, a screencast video demo and a live demo instance of NeuroPrompts publicly available.</abstract>
<identifier type="citekey">rosenman-etal-2024-neuroprompts</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-demo.17</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>159</start>
<end>167</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation
%A Rosenman, Shachar
%A Lal, Vasudev
%A Howard, Phillip
%Y Aletras, Nikolaos
%Y De Clercq, Orphee
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julians, Malta
%F rosenman-etal-2024-neuroprompts
%X Despite impressive recent advances in text-to-image diffusion models, obtaining high-quality images often requires prompt engineering by humans who have developed expertise in using them. In this work, we present NeuroPrompts, an adaptive framework that automatically enhances a user’s prompt to improve the quality of generations produced by text-to-image models. Our framework utilizes constrained text decoding with a pre-trained language model that has been adapted to generate prompts similar to those produced by human prompt engineers. This approach enables higher-quality text-to-image generations and provides user control over stylistic features via constraint set specification. We demonstrate the utility of our framework by creating an interactive application for prompt enhancement and image generation using Stable Diffusion. Additionally, we conduct experiments utilizing a large dataset of human-engineered prompts for text-to-image generation and show that our approach automatically produces enhanced prompts that result in superior image quality. We make our code, a screencast video demo and a live demo instance of NeuroPrompts publicly available.
%U https://aclanthology.org/2024.eacl-demo.17
%P 159-167
Markdown (Informal)
[NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation](https://aclanthology.org/2024.eacl-demo.17) (Rosenman et al., EACL 2024)
ACL