Boosting Text-To-Image Generation via Multilingual Prompting in Large Multimodal Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909455023603712 |
|---|---|
| author | Mu, Yongyu Li, Hengyu Wang, Junxin Zhou, Xiaoxuan Wang, Chenglong Luo, Yingfeng He, Qiaozhi Xiao, Tong Chen, Guocheng Zhu, Jingbo |
| author_facet | Mu, Yongyu Li, Hengyu Wang, Junxin Zhou, Xiaoxuan Wang, Chenglong Luo, Yingfeng He, Qiaozhi Xiao, Tong Chen, Guocheng Zhu, Jingbo |
| contents | Previous work on augmenting large multimodal models (LMMs) for text-to-image (T2I) generation has focused on enriching the input space of in-context learning (ICL). This includes providing a few demonstrations and optimizing image descriptions to be more detailed and logical. However, as demand for more complex and flexible image descriptions grows, enhancing comprehension of input text within the ICL paradigm remains a critical yet underexplored area. In this work, we extend this line of research by constructing parallel multilingual prompts aimed at harnessing the multilingual capabilities of LMMs. More specifically, we translate the input text into several languages and provide the models with both the original text and the translations. Experiments on two LMMs across 3 benchmarks show that our method, PMT2I, achieves superior performance in general, compositional, and fine-grained assessments, especially in human preference alignment. Additionally, with its advantage of generating more diverse images, PMT2I significantly outperforms baseline prompts when incorporated with reranking methods. Our code and parallel multilingual data can be found at https://github.com/takagi97/PMT2I. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_07086 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Boosting Text-To-Image Generation via Multilingual Prompting in Large Multimodal Models Mu, Yongyu Li, Hengyu Wang, Junxin Zhou, Xiaoxuan Wang, Chenglong Luo, Yingfeng He, Qiaozhi Xiao, Tong Chen, Guocheng Zhu, Jingbo Computation and Language Previous work on augmenting large multimodal models (LMMs) for text-to-image (T2I) generation has focused on enriching the input space of in-context learning (ICL). This includes providing a few demonstrations and optimizing image descriptions to be more detailed and logical. However, as demand for more complex and flexible image descriptions grows, enhancing comprehension of input text within the ICL paradigm remains a critical yet underexplored area. In this work, we extend this line of research by constructing parallel multilingual prompts aimed at harnessing the multilingual capabilities of LMMs. More specifically, we translate the input text into several languages and provide the models with both the original text and the translations. Experiments on two LMMs across 3 benchmarks show that our method, PMT2I, achieves superior performance in general, compositional, and fine-grained assessments, especially in human preference alignment. Additionally, with its advantage of generating more diverse images, PMT2I significantly outperforms baseline prompts when incorporated with reranking methods. Our code and parallel multilingual data can be found at https://github.com/takagi97/PMT2I. |
| title | Boosting Text-To-Image Generation via Multilingual Prompting in Large Multimodal Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2501.07086 |