Qwen-Image-Flash: 超越目標設計

Qwen-Image-Flash: Beyond Objective Design

June 2, 2026

作者: Tianhe Wu, Kun Yan, Zikai Zhou, Lihan Jiang, Jiahao Li, Jie Zhang, Kaiyuan Gao, Ningyuan Tang, Shengming Yin, Xiaoyue Chen, Xiao Xu, Yilei Chen, Yuxiang Chen, Yan Shu, Yixian Xu, Yanran Zhang, Zihao Liu, Zhendong Wang, Zekai Zhang, Deqing Li, Liang Peng, Yi Wang, Jingren Zhou, Chenfei Wu

cs.AI

摘要

少步蒸馏已成为加速先进视觉生成模型的有效策略，然而先前的工作主要聚焦于蒸馏目标。本研究从互补视角重新审视少步蒸馏，重点关注决定学生模型性能的关键训练方案。以Qwen-Image-2.0作为典型实例，我们系统探究了统一文本到图像生成与指令引导图像编辑蒸馏中的三个因素：数据组成、教师引导及任务混合。实证分析揭示了若干非直观行为，这些发现推动了Qwen-Image-Flash的研发。总体而言，我们的结果表明，有效的少步蒸馏不仅需要精心设计的目标函数，更离不开对整个训练流程的原则性组织。

English

Few-step distillation has become an effective strategy for accelerating advanced visual generative models, yet prior work has largely focused on distillation objectives. In this work, we revisit few-step distillation from a complementary perspective, focusing on the training recipe that critically shapes student performance. Using Qwen-Image-2.0 as a representative case, we systematically investigate three factors in unified text-to-image generation and instruction-guided image editing distillation: data composition, teacher guidance, and task mixture. Our empirical analysis reveals several non-obvious behaviors, which motivate the development of Qwen-Image-Flash. Overall, our results suggest that effective few-step distillation requires not only carefully designed objectives, but also principled organization of the broader training pipeline.