Controllable Generation With Text-to-Image Diffusion Models: A Survey
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-04 · 48 (4) · 4771-4791
DOI: 10.1109/tpami.2025.3646548 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-04. Verfasst von Pu Cao und 3 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 336 Literaturangaben. Gefördert von: Young Scientists Fund of NSFC.
Abstract (Originalsprache)
In the rapidly advancing realm of visual generation, diffusion models have revolutionized the landscape, marking a significant shift in capabilities with their impressive text-guided generative functions. However, relying solely on text for conditioning these models does not fully cater to the varied and complex requirements of different applications and scenarios. Acknowledging this shortfall, a variety of studies aim to control pre-trained text-to-image (T2I) models to support novel conditions. In this survey, we undertake a thorough review of the literature on controllable generation with T2I diffusion models, covering both the theoretical foundations and practical advancements in this domain. Our review begins with a brief introduction to the basics of denoising diffusion probabilistic models (DDPMs) and widely used T2I diffusion models. Additionally, we provide a detailed overview of research in this area, categorizing it from the condition perspective into three directions: generation with specific conditions, generation with multiple conditions, and universal controllable generation. For each category, we analyze the underlying control mechanisms and review representative methods based on their core techniques.
Förderung
- Young Scientists Fund of NSFC
Zitieren
APA
Cao, P., Zhou, F., Song, Q., & Yang, L. (2026). Controllable Generation With Text-to-Image Diffusion Models: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(4), 4771-4791. https://doi.org/10.1109/tpami.2025.3646548
Vancouver
Cao P, Zhou F, Song Q, Yang L. Controllable Generation With Text-to-Image Diffusion Models: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(4):4771-4791. doi:10.1109/tpami.2025.3646548
BibTeX
@article{Cao2026,
author = {Cao, Pu and Zhou, Feng and Song, Qing and Yang, Lu},
title = {Controllable Generation With Text-to-Image Diffusion Models: A Survey},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {4},
pages = {4771--4791},
doi = {10.1109/tpami.2025.3646548}
}
EUVIMED