@inproceedings{jiang-etal-2025-controltext,
title = "{C}ontrol{T}ext: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations",
author = "Jiang, Bowen and
Yuan, Yuan and
Bai, Xinyi and
Hao, Zhuoqun and
Yin, Alyson and
Hu, Yaojie and
Liao, Wenyu and
Ungar, Lyle and
Taylor, Camillo Jose",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-emnlp.1385/",
doi = "10.18653/v1/2025.findings-emnlp.1385",
pages = "25414--25425",
ISBN = "979-8-89176-335-7",
abstract = "This work demonstrates that diffusion models can achieve font-controllable multilingual text rendering using just raw images without font label annotations. Visual text rendering remains a significant challenge. While recent methods condition diffusion on glyphs, it is impossible to retrieve exact font annotations from large-scale, real-world datasets, which prevents user-specified font control. To address this, we propose a data-driven solution that integrates the conditional diffusion model with a text segmentation model, utilizing segmentation masks to capture and represent fonts in pixel space in a self-supervised manner, thereby eliminating the need for any ground-truth labels and enabling users to customize text rendering with any multilingual font of their choice. The experiment provides a proof of concept of our algorithm in zero-shot text and font editing across diverse fonts and languages, providing valuable insights for the community and industry toward achieving generalized visual text rendering."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2025-controltext">
<titleInfo>
<title>ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuan</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinyi</namePart>
<namePart type="family">Bai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuoqun</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alyson</namePart>
<namePart type="family">Yin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaojie</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenyu</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lyle</namePart>
<namePart type="family">Ungar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Camillo</namePart>
<namePart type="given">Jose</namePart>
<namePart type="family">Taylor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-335-7</identifier>
</relatedItem>
<abstract>This work demonstrates that diffusion models can achieve font-controllable multilingual text rendering using just raw images without font label annotations. Visual text rendering remains a significant challenge. While recent methods condition diffusion on glyphs, it is impossible to retrieve exact font annotations from large-scale, real-world datasets, which prevents user-specified font control. To address this, we propose a data-driven solution that integrates the conditional diffusion model with a text segmentation model, utilizing segmentation masks to capture and represent fonts in pixel space in a self-supervised manner, thereby eliminating the need for any ground-truth labels and enabling users to customize text rendering with any multilingual font of their choice. The experiment provides a proof of concept of our algorithm in zero-shot text and font editing across diverse fonts and languages, providing valuable insights for the community and industry toward achieving generalized visual text rendering.</abstract>
<identifier type="citekey">jiang-etal-2025-controltext</identifier>
<identifier type="doi">10.18653/v1/2025.findings-emnlp.1385</identifier>
<location>
<url>https://aclanthology.org/2025.findings-emnlp.1385/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>25414</start>
<end>25425</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations
%A Jiang, Bowen
%A Yuan, Yuan
%A Bai, Xinyi
%A Hao, Zhuoqun
%A Yin, Alyson
%A Hu, Yaojie
%A Liao, Wenyu
%A Ungar, Lyle
%A Taylor, Camillo Jose
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Findings of the Association for Computational Linguistics: EMNLP 2025
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-335-7
%F jiang-etal-2025-controltext
%X This work demonstrates that diffusion models can achieve font-controllable multilingual text rendering using just raw images without font label annotations. Visual text rendering remains a significant challenge. While recent methods condition diffusion on glyphs, it is impossible to retrieve exact font annotations from large-scale, real-world datasets, which prevents user-specified font control. To address this, we propose a data-driven solution that integrates the conditional diffusion model with a text segmentation model, utilizing segmentation masks to capture and represent fonts in pixel space in a self-supervised manner, thereby eliminating the need for any ground-truth labels and enabling users to customize text rendering with any multilingual font of their choice. The experiment provides a proof of concept of our algorithm in zero-shot text and font editing across diverse fonts and languages, providing valuable insights for the community and industry toward achieving generalized visual text rendering.
%R 10.18653/v1/2025.findings-emnlp.1385
%U https://aclanthology.org/2025.findings-emnlp.1385/
%U https://doi.org/10.18653/v1/2025.findings-emnlp.1385
%P 25414-25425
Markdown (Informal)
[ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations](https://aclanthology.org/2025.findings-emnlp.1385/) (Jiang et al., Findings 2025)
ACL
- Bowen Jiang, Yuan Yuan, Xinyi Bai, Zhuoqun Hao, Alyson Yin, Yaojie Hu, Wenyu Liao, Lyle Ungar, and Camillo Jose Taylor. 2025. ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 25414–25425, Suzhou, China. Association for Computational Linguistics.