FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918210846064640 |
|---|---|
| author | Lan, Rui Bai, Yancheng Duan, Xu Li, Mingxing Jin, Dongyang Xu, Ryan Nie, Dong Sun, Lei Chu, Xiangxiang |
| author_facet | Lan, Rui Bai, Yancheng Duan, Xu Li, Mingxing Jin, Dongyang Xu, Ryan Nie, Dong Sun, Lei Chu, Xiangxiang |
| contents | Scene text editing aims to modify or add texts on images while ensuring text fidelity and overall visual quality consistent with the background. Recent methods are primarily built on UNet-based diffusion models, which have improved scene text editing results, but still struggle with complex glyph structures, especially for non-Latin ones (\eg, Chinese, Korean, Japanese). To address these issues, we present \textbf{FLUX-Text}, a simple and advanced multilingual scene text editing DiT method. Specifically, our FLUX-Text enhances glyph understanding and generation through lightweight Visual and Text Embedding Modules, while preserving the original generative capability of FLUX. We further propose a Regional Text Perceptual Loss tailored for text regions, along with a matching two-stage training strategy to better balance text editing and overall image quality. Benefiting from the DiT-based architecture and lightweight feature injection modules, FLUX-Text can be trained with only $0.1$M training examples, a \textbf{97\%} reduction compared to $2.9$M required by popular methods. Extensive experiments on multiple public datasets, including English and Chinese benchmarks, demonstrate that our method surpasses other methods in visual quality and text fidelity. All the code is available at https://github.com/AMAP-ML/FluxText. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_03329 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing Lan, Rui Bai, Yancheng Duan, Xu Li, Mingxing Jin, Dongyang Xu, Ryan Nie, Dong Sun, Lei Chu, Xiangxiang Computer Vision and Pattern Recognition Scene text editing aims to modify or add texts on images while ensuring text fidelity and overall visual quality consistent with the background. Recent methods are primarily built on UNet-based diffusion models, which have improved scene text editing results, but still struggle with complex glyph structures, especially for non-Latin ones (\eg, Chinese, Korean, Japanese). To address these issues, we present \textbf{FLUX-Text}, a simple and advanced multilingual scene text editing DiT method. Specifically, our FLUX-Text enhances glyph understanding and generation through lightweight Visual and Text Embedding Modules, while preserving the original generative capability of FLUX. We further propose a Regional Text Perceptual Loss tailored for text regions, along with a matching two-stage training strategy to better balance text editing and overall image quality. Benefiting from the DiT-based architecture and lightweight feature injection modules, FLUX-Text can be trained with only $0.1$M training examples, a \textbf{97\%} reduction compared to $2.9$M required by popular methods. Extensive experiments on multiple public datasets, including English and Chinese benchmarks, demonstrate that our method surpasses other methods in visual quality and text fidelity. All the code is available at https://github.com/AMAP-ML/FluxText. |
| title | FLUX-Text: A Simple and Advanced Diffusion Transformer Baseline for Scene Text Editing |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.03329 |