Ovis-Image Technical Report
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_ | 1866915643156070400 |
|---|---|
| author | Wang, Guo-Hua Cao, Liangfu Cui, Tianyu Fu, Minghao Chen, Xiaohao Zhan, Pengxin Zhao, Jianshan Li, Lan Fu, Bowen Liu, Jiaqi Chen, Qing-Guo |
| author_facet | Wang, Guo-Hua Cao, Liangfu Cui, Tianyu Fu, Minghao Chen, Xiaohao Zhan, Pengxin Zhao, Jianshan Li, Lan Fu, Bowen Liu, Jiaqi Chen, Qing-Guo |
| contents | We introduce $\textbf{Ovis-Image}$, a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints. Built upon our previous Ovis-U1 framework, Ovis-Image integrates a diffusion-based visual decoder with the stronger Ovis 2.5 multimodal backbone, leveraging a text-centric training pipeline that combines large-scale pre-training with carefully tailored post-training refinements. Despite its compact architecture, Ovis-Image achieves text rendering performance on par with significantly larger open models such as Qwen-Image and approaches closed-source systems like Seedream and GPT4o. Crucially, the model remains deployable on a single high-end GPU with moderate memory, narrowing the gap between frontier-level text rendering and practical deployment. Our results indicate that combining a strong multimodal backbone with a carefully designed, text-focused training recipe is sufficient to achieve reliable bilingual text rendering without resorting to oversized or proprietary models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_22982 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Ovis-Image Technical Report Wang, Guo-Hua Cao, Liangfu Cui, Tianyu Fu, Minghao Chen, Xiaohao Zhan, Pengxin Zhao, Jianshan Li, Lan Fu, Bowen Liu, Jiaqi Chen, Qing-Guo Computer Vision and Pattern Recognition Artificial Intelligence We introduce $\textbf{Ovis-Image}$, a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints. Built upon our previous Ovis-U1 framework, Ovis-Image integrates a diffusion-based visual decoder with the stronger Ovis 2.5 multimodal backbone, leveraging a text-centric training pipeline that combines large-scale pre-training with carefully tailored post-training refinements. Despite its compact architecture, Ovis-Image achieves text rendering performance on par with significantly larger open models such as Qwen-Image and approaches closed-source systems like Seedream and GPT4o. Crucially, the model remains deployable on a single high-end GPU with moderate memory, narrowing the gap between frontier-level text rendering and practical deployment. Our results indicate that combining a strong multimodal backbone with a carefully designed, text-focused training recipe is sufficient to achieve reliable bilingual text rendering without resorting to oversized or proprietary models. |
| title | Ovis-Image Technical Report |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.22982 |