arXiv 2508.023242025-08-04cs.CV

Qwen-Image 技术报告

Qwen-Image Technical Report

Chenfei Wu, Jiahao Li, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kun Yan, Sheng-ming Yin, Shuai Bai, Xiao Xu, Yilei Chen, Yuxiang Chen, Zecheng Tang, Zekai Zhang,… 展开作者

Chenfei Wu, Jiahao Li, Jingren Zhou, Junyang Lin, Kaiyuan Gao, Kun Yan, Sheng-ming Yin, Shuai Bai, Xiao Xu, Yilei Chen, Yuxiang Chen, Zecheng Tang, Zekai Zhang, Zhengyi Wang, An Yang, Bowen Yu, Chen Cheng, Dayiheng Liu, Deqing Li, Hang Zhang, Hao Meng, Hu Wei, Jingyuan Ni, Kai Chen, Kuan Cao, Liang Peng, Lin Qu, Minggang Wu, Peng Wang, Shuting Yu, Tingkun Wen, Wensen Feng, Xiaoxiao Xu, Yi Wang, Yichang Zhang, Yongqiang Zhu, Yujia Wu, Yuxuan Cai, Zenan Liu

备注：: https://github.com/QwenLM/Qwen-Image

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

Qwen-Image 是 Qwen 系列图像生成基础模型，通过全面数据流水线和渐进式训练提升复杂文本渲染，并采用多任务训练与双编码机制增强编辑一致性，在多个基准上达到最先进性能。

摘要：

我们提出了 Qwen-Image，这是 Qwen 系列中的一个图像生成基础模型，在复杂文本渲染和精确图像编辑方面取得了显著进展。为了解决复杂文本渲染的挑战，我们设计了一个全面的数据流水线，包括大规模数据收集、过滤、标注、合成和平衡。此外，我们采用了一种渐进式训练策略，从非文本到文本渲染开始，从简单到复杂的文本输入逐步演进，并逐渐扩展到段落级描述。这种课程学习方法显著增强了模型的原生文本渲染能力。因此，Qwen-Image 不仅在英语等字母语言中表现出色，而且在中文等更具挑战性的表意语言中也取得了显著进展。为了增强图像编辑的一致性，我们引入了一种改进的多任务训练范式，不仅包括传统的文本到图像（T2I）和文本-图像到图像（TI2I）任务，还包括图像到图像（I2I）重建，有效地对齐了 Qwen2.5-VL 和 MMDiT 之间的潜在表示。此外，我们将原始图像分别输入 Qwen2.5-VL 和 VAE 编码器，以获得语义和重建表示。这种双编码机制使编辑模块能够在保持语义一致性和维持视觉保真度之间取得平衡。Qwen-Image 实现了最先进的性能，展示了其在多个基准测试中图像生成和编辑的强大能力。

英文摘要：

We present Qwen-Image, an image generation foundation model in the Qwen series that achieves significant advances in complex text rendering and precise image editing. To address the challenges of complex text rendering, we design a comprehensive data pipeline that includes large-scale data collection, filtering, annotation, synthesis, and balancing. Moreover, we adopt a progressive training strategy that starts with non-text-to-text rendering, evolves from simple to complex textual inputs, and gradually scales up to paragraph-level descriptions. This curriculum learning approach substantially enhances the model's native text rendering capabilities. As a result, Qwen-Image not only performs exceptionally well in alphabetic languages such as English, but also achieves remarkable progress on more challenging logographic languages like Chinese. To enhance image editing consistency, we introduce an improved multi-task training paradigm that incorporates not only traditional text-to-image (T2I) and text-image-to-image (TI2I) tasks but also image-to-image (I2I) reconstruction, effectively aligning the latent representations between Qwen2.5-VL and MMDiT. Furthermore, we separately feed the original image into Qwen2.5-VL and the VAE encoder to obtain semantic and reconstructive representations, respectively. This dual-encoding mechanism enables the editing module to strike a balance between preserving semantic consistency and maintaining visual fidelity. Qwen-Image achieves state-of-the-art performance, demonstrating its strong capabilities in both image generation and editing across multiple benchmarks.

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。