{"ID":3004768,"CreatedAt":"2026-06-03T03:09:48.883664427Z","UpdatedAt":"2026-06-05T11:43:53.432517148Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.03746","arxiv_id":"2606.03746","title":"Qwen-Image-Flash: Beyond Objective Design","abstract":"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.","short_abstract":"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 perfor...","url_abs":"https://arxiv.org/abs/2606.03746","url_pdf":"https://arxiv.org/pdf/2606.03746v1","authors":"[\"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\"]","published":"2026-06-02T15:00:22Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.GR\",\"cs.LG\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}