arXiv 2605.107302026-05-11cs.CV

Qwen-Image-2.0 技术报告

Qwen-Image-2.0 Technical Report

Qwen Team（通义实验室）

Bing Zhao, Chenfei Wu, Deqing Li, Hao Meng, Jiahao Li, Jie Zhang, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kuan Cao, Kun Yan, Liang Peng, Lihan Jiang, Niantong L… 展开作者

Bing Zhao, Chenfei Wu, Deqing Li, Hao Meng, Jiahao Li, Jie Zhang, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kuan Cao, Kun Yan, Liang Peng, Lihan Jiang, Niantong Li, Ningyuan Tang, Shengming Yin, Tianhe Wu, Xiao Xu, Xiaoyue Chen, Xihua Wang, Yan Shu, Yanran Zhang, Yi Wang, Yilei Chen, Ying Ba, Yixian Xu, Yujia Wu, Yuxiang Chen, Zecheng Tang, Zekai Zhang, Zhendong Wang, Zihao Liu, Zikai Zhou, An Yang, Chen Cheng, Chenxu Lv, Dayiheng Liu, Fan Zhou, Hantian Xiong, Hongzhu Shi, Hu Wei, Huihong Zhao, Ivy Liu, Jianwei Zhang, Jiawei Zhang, Kai Chen, Kang He, Levon Xue, Lin Qu, Linhan Tang, Luwen Feng, Minggang Wu, Minmin Sun, Na Ni, Rui Men, Shuai Bai, Sishou Zheng, Tao Lan, Tianqi Zhang, Tingkun Wen, Wei Wang, Weixu Qiao, Weiyi Lu, Wenmeng Zhou, Xiaodong Deng, Xiaoxiao Xu, Xinlei Fang, Xionghui Chen, Yanan Wang, Yang Fan, Yichang Zhang, Yixuan Xu, Yu Wu, Zhiyuan Ma, Zhizhi Cai

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

Qwen-Image-2.0 通过多模态扩散变换器和定制化训练流程，统一高保真生成与精确图像编辑，提升多语言文本精度、高分辨率逼真度及复杂指令遵循能力。

摘要：

我们介绍了Qwen-Image-2.0，一个具备多方面能力的图像生成基础模型，该模型在一个框架内统一了高保真生成和精确图像编辑。尽管已有进展，现有模型仍难以处理超长文本渲染、多语言字体、高分辨率逼真度、稳健的指令遵循和高效的部署，尤其是在文本丰富和结构复杂的场景中。Qwen-Image-2.0通过将Qwen3-VL作为条件编码器与多模态扩散变换器结合，实现条件-目标联合建模，依托大规模数据整理和定制化的多阶段训练流程。这使得模型在多模态理解方面表现出色，同时保留了灵活的生成和编辑能力。该模型支持生成文本丰富的内容，如幻灯片、海报、信息图和漫画，指令长度可达1K个token。同时显著提升了多语言文本的保真度和字体质量。它还通过更丰富的细节、更真实的纹理和一致的光照增强了逼真生成，并在多样化的风格中更可靠地遵循复杂提示。大量的人类评估显示，Qwen-Image-2.0在生成和编辑方面均显著优于之前的Qwen-Image模型，标志着向更通用、可靠和实用的图像生成基础模型迈出一步。

英文摘要：

We present Qwen-Image-2.0, an omni-capable image generation foundation model that unifies high-fidelity generation and precise image editing within a single framework. Despite recent progress, existing models still struggle with ultra-long text rendering, multilingual typography, high-resolution photorealism, robust instruction following, and efficient deployment, especially in text-rich and compositionally complex scenarios. Qwen-Image-2.0 addresses these challenges by coupling Qwen3-VL as the condition encoder with a Multimodal Diffusion Transformer for joint condition-target modeling, supported by large-scale data curation and a customized multi-stage training pipeline. This enables strong multimodal understanding while preserving flexible generation and editing capabilities. The model supports instructions of up to 1K tokens for generating text-rich content such as slides, posters, infographics, and comics, while significantly improving multilingual text fidelity and typography. It also enhances photorealistic generation with richer details, more realistic textures, and coherent lighting, and follows complex prompts more reliably across diverse styles. Extensive human evaluations show that Qwen-Image-2.0 substantially outperforms previous Qwen-Image models in both generation and editing, marking a step toward more general, reliable, and practical image generation foundation models.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。