Qwen-Image-Flash: Rethinking the Training Recipe for Few-Step Distillation

תקציר מקורי באנגליתarXiv:2606.03746v3 Announce Type: replace-cross Abstract: Few-step distillation has emerged as a critical component in the development of advanced visual generative foundation models, substantially reducing inference overhead while enabling real-time generation and cost-efficient deployment across a broad range of practical scenarios. However, prior work has predominantly focused on advancing training objectives, while comparatively overlooking the training recipe, which has become increasingly critical in the era of large-scale foundation models. In this work, we systematically revisit the training recipe under the well-established distribution matching distillation (DMD) framework for both text-to-image generation and image editing, focusing on three key dimensions: training data composi