DanceOPD：策略内生成式字段蒸馏
DanceOPD: On-Policy Generative Field Distillation
摘要
现代图像生成技术需要一种能够整合多种功能的模型，这些功能包括文本到图像生成、局部编辑和全局编辑。然而，这些功能往往无法自然地协同工作，常常产生冲突。例如，局部编辑往往会降低文本到图像生成的性能，而全局编辑与局部编辑则相互干扰。因此，如何有效整合这些功能成为图像生成模型训练中的关键挑战。为了解决这一问题，我们提出了DanceOPD框架——这是一种基于策略的生成域蒸馏方法，它会将每个样本分配到特定的功能域中，然后利用低噪声状态进行训练，同时采用简单的速度MSE作为损失函数。由于每个功能域都被视为共享流状态空间上的速度场，因此模型可以从自身生成的样本中学习到各种功能，从而整合出专业的功能能力。这种方法还能够纳入由操作器定义的各种功能，比如无分类器引导机制。针对文本到图像生成、编辑、真实感功能整合以及CFG功能的实验表明，我们的方法能够改善多功能整合效果，既增强了目标功能的能力，又保持了锚点生成的质量。我们认为，这项工作为流匹配模型中的生成域蒸馏提供了实用的解决方案。
English Abstract
Modern image generation demands a single model that unifies diverse capabilities, including text-to-image (T2I), local editing, and global editing. However, these capabilities are rarely naturally aligned and often conflict. For instance, editing tends to degrade T2I performance, while global and local editing interfere with each other. Consequently, effectively composing these capabilities has become a central challenge for image generation model training. To tackle this, we introduce DanceOPD, an on-policy generative field distillation framework for flow-matching models that routes each sample to one capability field, queries one low-noise student-induced state, and trains with a simple velocity MSE objective. With each capability source defined as a velocity field over the shared flow state space, the student learns from fields queried on its own rollout states to compose expert capabilities. This formulation also absorbs operator-defined fields such as classifier-free guidance. Comprehensive experiments on T2I, editing, realism-field absorption, and CFG absorption show that our approach improves multi-capability composition, strengthening target capabilities while preserving anchor generation quality. We believe this work establishes a practical route for generative field distillation in flow-matching models.