Ovis-U1 Technical Report

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Guo-Hua, Zhao, Shanshan, Zhang, Xinjie, Cao, Liangfu, Zhan, Pengxin, Duan, Lunhao, Lu, Shiyin, Fu, Minghao, Chen, Xiaohao, Zhao, Jianshan, Li, Yang, Chen, Qing-Guo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913920815464448
author Wang, Guo-Hua
Zhao, Shanshan
Zhang, Xinjie
Cao, Liangfu
Zhan, Pengxin
Duan, Lunhao
Lu, Shiyin
Fu, Minghao
Chen, Xiaohao
Zhao, Jianshan
Li, Yang
Chen, Qing-Guo
author_facet Wang, Guo-Hua
Zhao, Shanshan
Zhang, Xinjie
Cao, Liangfu
Zhan, Pengxin
Duan, Lunhao
Lu, Shiyin
Fu, Minghao
Chen, Xiaohao
Zhao, Jianshan
Li, Yang
Chen, Qing-Guo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23044
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Ovis-U1 Technical Report
Wang, Guo-Hua
Zhao, Shanshan
Zhang, Xinjie
Cao, Liangfu
Zhan, Pengxin
Duan, Lunhao
Lu, Shiyin
Fu, Minghao
Chen, Xiaohao
Zhao, Jianshan
Li, Yang
Chen, Qing-Guo
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title Ovis-U1 Technical Report
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2506.23044