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.

翻译：[Chinese abstract] 少步蒸馏已成为加速先进视觉生成模型的有效策略，但先前的工作主要集中在蒸馏目标上。在本工作中，我们从互补视角重新审视少步蒸馏，重点关注对模型性能有重要影响的训练方案。以Qwen-Image-2.0作为代表性案例，我们系统性地研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、教师引导与任务混合。我们的实证分析揭示出若干非直观行为，这些发现推动了Qwen-Image-Flash的发展。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优化目标，还需要对整个训练流程进行原则性组织。