@inproceedings{jamil-etal-2025-poetry,
title = "Poetry in Pixels: Prompt Tuning for Poem Image Generation via Diffusion Models",
author = "Jamil, Sofia and
Reddy, Bollampalli Areen and
Kumar, Raghvendra and
Saha, Sriparna and
J, Joseph K. and
Goswami, Koustava",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.620/",
pages = "9224--9237",
abstract = "The task of text-to-image generation has encountered significant challenges when applied to literary works, especially poetry. Poems are a distinct form of literature, with meanings that frequently transcend beyond the literal words. To address this shortcoming, we propose a PoemToPixel framework designed to generate images that visually represent the inherent meanings of poems. Our approach incorporates the concept of prompt tuning in our image generation framework to ensure that the resulting images closely align with the poetic content. In addition, we propose the PoeKey algorithm, which extracts three key elements in the form of emotions, visual elements, and themes from poems to form instructions which are subsequently provided to a diffusion model for generating corresponding images. Furthermore, to expand the diversity of the poetry dataset across different genres and ages, we introduce MiniPo, a novel multimodal dataset comprising 1001 children`s poems and images. Leveraging this dataset alongside PoemSum, we conducted both quantitative and qualitative evaluations of image generation using our PoemToPixel framework. This paper demonstrates the effectiveness of our approach and offers a fresh perspective on generating images from literary sources. The code and dataset used in this work are publicly available."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jamil-etal-2025-poetry">
<titleInfo>
<title>Poetry in Pixels: Prompt Tuning for Poem Image Generation via Diffusion Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sofia</namePart>
<namePart type="family">Jamil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bollampalli</namePart>
<namePart type="given">Areen</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raghvendra</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriparna</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="given">K</namePart>
<namePart type="family">J</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koustava</namePart>
<namePart type="family">Goswami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The task of text-to-image generation has encountered significant challenges when applied to literary works, especially poetry. Poems are a distinct form of literature, with meanings that frequently transcend beyond the literal words. To address this shortcoming, we propose a PoemToPixel framework designed to generate images that visually represent the inherent meanings of poems. Our approach incorporates the concept of prompt tuning in our image generation framework to ensure that the resulting images closely align with the poetic content. In addition, we propose the PoeKey algorithm, which extracts three key elements in the form of emotions, visual elements, and themes from poems to form instructions which are subsequently provided to a diffusion model for generating corresponding images. Furthermore, to expand the diversity of the poetry dataset across different genres and ages, we introduce MiniPo, a novel multimodal dataset comprising 1001 children‘s poems and images. Leveraging this dataset alongside PoemSum, we conducted both quantitative and qualitative evaluations of image generation using our PoemToPixel framework. This paper demonstrates the effectiveness of our approach and offers a fresh perspective on generating images from literary sources. The code and dataset used in this work are publicly available.</abstract>
<identifier type="citekey">jamil-etal-2025-poetry</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.620/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>9224</start>
<end>9237</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Poetry in Pixels: Prompt Tuning for Poem Image Generation via Diffusion Models
%A Jamil, Sofia
%A Reddy, Bollampalli Areen
%A Kumar, Raghvendra
%A Saha, Sriparna
%A J, Joseph K.
%A Goswami, Koustava
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F jamil-etal-2025-poetry
%X The task of text-to-image generation has encountered significant challenges when applied to literary works, especially poetry. Poems are a distinct form of literature, with meanings that frequently transcend beyond the literal words. To address this shortcoming, we propose a PoemToPixel framework designed to generate images that visually represent the inherent meanings of poems. Our approach incorporates the concept of prompt tuning in our image generation framework to ensure that the resulting images closely align with the poetic content. In addition, we propose the PoeKey algorithm, which extracts three key elements in the form of emotions, visual elements, and themes from poems to form instructions which are subsequently provided to a diffusion model for generating corresponding images. Furthermore, to expand the diversity of the poetry dataset across different genres and ages, we introduce MiniPo, a novel multimodal dataset comprising 1001 children‘s poems and images. Leveraging this dataset alongside PoemSum, we conducted both quantitative and qualitative evaluations of image generation using our PoemToPixel framework. This paper demonstrates the effectiveness of our approach and offers a fresh perspective on generating images from literary sources. The code and dataset used in this work are publicly available.
%U https://aclanthology.org/2025.coling-main.620/
%P 9224-9237
Markdown (Informal)
[Poetry in Pixels: Prompt Tuning for Poem Image Generation via Diffusion Models](https://aclanthology.org/2025.coling-main.620/) (Jamil et al., COLING 2025)
ACL