EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Text-to-Image Generation via Deep Learning: A Comprehensive Review of Models, Architectures, and Future Directions

Abdussalam Elhanashi, Siham Essahraui, Qinghe Zheng, Sergio Saponara

Applied Sciences · 24.07.2026 · 16 (15) · 7430

DOI: 10.3390/app16157430 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 24.07.2026. Verfasst von Abdussalam Elhanashi und 3 weiteren Autor:innen. Die Arbeit nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Text-to-image generation is an increasingly fast-paced field of generative artificial intelligence, consisting of synthesizing images of high quality and semantic consistency based on natural language descriptions. In this paper, we give an extensive overview of the approach to text-to-image generation using deep learning, including the most common core model families, architecture designs, training approaches, and evaluation systems. We discuss the paradigms of the generative adversarial networks (GANs), variational autoencoders (VAEs), transformer-based designs, and diffusion models, with the last one representing the state of the art in image generation models. The review also discusses key aspects of pipelines such as text encoding, cross-modal alignment, mechanisms of attention, and decoding images. Popular datasets, methods, and metrics of evaluation, including Fréchet Inception Distance (FID) and CLIP-based similarity, are discussed. The application domains that involve creative content creation, medical imaging, education and industrial design are critically discussed. Despite significant advances, various issues still exist, such as low stability in training, excessive computational complexity, amplification of bias, generated images, and text–image alignment errors. Moral and social issues, such as misinformation, intellectual property, and equity, are critically examined. Lastly, we present future research directions to more controllable, more efficient and more interpretable text-to-image systems, focusing on multimodal foundation models and human–AI collaborative design.

Zitieren

APA

Elhanashi, A., Essahraui, S., Zheng, Q., & Saponara, S. (2026). Text-to-Image Generation via Deep Learning: A Comprehensive Review of Models, Architectures, and Future Directions. Applied Sciences, 16(15), 7430. https://doi.org/10.3390/app16157430

Vancouver

Elhanashi A, Essahraui S, Zheng Q, Saponara S. Text-to-Image Generation via Deep Learning: A Comprehensive Review of Models, Architectures, and Future Directions. Applied Sciences. 2026;16(15):7430. doi:10.3390/app16157430

BibTeX
@article{Elhanashi2026,
  author = {Elhanashi, Abdussalam and Essahraui, Siham and Zheng, Qinghe and Saponara, Sergio},
  title = {Text-to-Image Generation via Deep Learning: A Comprehensive Review of Models, Architectures, and Future Directions},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {15},
  pages = {7430},
  doi = {10.3390/app16157430}
}
Kostenlos starten →