FG-Text-SD: Training-Free Controllable Scene Text–Image Generation for Low-Resource Southeast Asian Languages
Applied Sciences · 02.05.2026 · 16 (9) · 4461
DOI: 10.3390/app16094461 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 02.05.2026. Verfasst von Ning Shi und 2 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Shandong Province, National Natural Science Foundation of China, Qingdao Natural Science Foundation.
Abstract (Originalsprache)
Scene text–image generation aims to synthesize natural images containing readable and visually coherent text. Although recent diffusion-based methods have shown promising results, they often struggle with low-resource Southeast Asian languages because of complex glyph structures, limited language resources, and weak alignment between generated text and background carriers. To address this issue, we propose FG-Text-SD, a training-free controllable scene text–image generation framework built on Stable Diffusion. The proposed framework organizes multiple text instances in an instance-level manner, injects rendered glyph structure priors into the denoising process to stabilize complex character shapes, modulates cross-attention with carrier-aware masks to improve text-to-surface alignment, and employs OCR-guided local repainting to correct residual local errors. Experiments are conducted on AnyText-benchmark, CVTG-2K, and a newly constructed evaluation set covering Thai, Lao, Khmer, and Burmese. The proposed method achieves strong performance on both public benchmarks and low-resource language subsets, improving text accuracy, readability, and spatial consistency without additional model retraining. These results demonstrate that FG-Text-SD provides an effective solution for controllable scene text–image generation in low-resource multilingual settings.
Förderung
- Natural Science Foundation of Shandong Province
- National Natural Science Foundation of China
- Qingdao Natural Science Foundation
Zitieren
APA
Shi, N., Wu, C., & Zhang, Y. (2026). FG-Text-SD: Training-Free Controllable Scene Text–Image Generation for Low-Resource Southeast Asian Languages. Applied Sciences, 16(9), 4461. https://doi.org/10.3390/app16094461
Vancouver
Shi N, Wu C, Zhang Y. FG-Text-SD: Training-Free Controllable Scene Text–Image Generation for Low-Resource Southeast Asian Languages. Applied Sciences. 2026;16(9):4461. doi:10.3390/app16094461
BibTeX
@article{Shi2026,
author = {Shi, Ning and Wu, Chunlei and Zhang, Yongzhen},
title = {FG-Text-SD: Training-Free Controllable Scene Text–Image Generation for Low-Resource Southeast Asian Languages},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {9},
pages = {4461},
doi = {10.3390/app16094461}
}
EUVIMED