{"ID":2835403,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.22982","arxiv_id":"2511.22982","title":"Ovis-Image Technical Report","abstract":"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.","short_abstract":"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 mul...","url_abs":"https://arxiv.org/abs/2511.22982","url_pdf":"https://arxiv.org/pdf/2511.22982v1","authors":"[\"Guo-Hua Wang\",\"Liangfu Cao\",\"Tianyu Cui\",\"Minghao Fu\",\"Xiaohao Chen\",\"Pengxin Zhan\",\"Jianshan Zhao\",\"Lan Li\",\"Bowen Fu\",\"Jiaqi Liu\",\"Qing-Guo Chen\"]","published":"2025-11-28T08:42:31Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Diffusion Model\"]","has_code":false}