In this report, we introduce Ovis-U1, a 3-billion-parameter unified model that integrates multimodal understanding, text-to-image generation, and image editing capabilities. Building on the foundation of the Ovis series, Ovis-U1 incorporates a diffusion-based visual decoder paired with a bidirectional token refiner, enabling image generation tasks comparable to leading models like GPT-4o. Unlike some previous models that use a frozen MLLM for generation tasks, Ovis-U1 utilizes a new unified training approach starting from a language model. Compared to training solely on understanding or generation tasks, unified training yields better performance, demonstrating the enhancement achieved by integrating these two tasks. Ovis-U1 achieves a score of 69.6 on the OpenCompass Multi-modal Academic Benchmark, surpassing recent state-of-the-art models such as Ristretto-3B and SAIL-VL-1.5-2B. In text-to-image generation, it excels with scores of 83.72 and 0.89 on the DPG-Bench and GenEval benchmarks, respectively. For image editing, it achieves 4.00 and 6.42 on the ImgEdit-Bench and GEdit-Bench-EN, respectively. As the initial version of the Ovis unified model series, Ovis-U1 pushes the boundaries of multimodal understanding, generation, and editing.
@article{arxiv.2506.23044,
title = {Ovis-U1 Technical Report},
author = {Guo-Hua Wang and Shanshan Zhao and Xinjie Zhang and Liangfu Cao and Pengxin Zhan and Lunhao Duan and Shiyin Lu and Minghao Fu and Xiaohao Chen and Jianshan Zhao and Yang Li and Qing-Guo Chen},
journal= {arXiv preprint arXiv:2506.23044},
year = {2025}
}
Comments
An unified model for multimodal understanding, text-to-image generation, and image editing. GitHub: https://github.com/AIDC-AI/Ovis-U1