AI绘画的「负向提示」正在悄悄拖后腿
扩散模型生成图片时常用「无分类器引导」(CFG)来平衡创意与忠实度，但训练时若直接让学生的CFG输出模仿老师，会陷入一个陷阱：学生可能在「正向」和「负向」分支上犯方向相反的错，两者互相抵消，看似整体对了，实则负向分支越学越歪。研究者发现，当老师模型保留了一些学生无法获取的「特权信息」(比如更精细的负向条件)时，这种矛盾会加剧，导致生成质量不稳定。他们提出「正向方向匹配」(PDM)，把正向预测和CFG方向分开约束，在视频控制任务上，新方法对推理时的引导强度不再敏感，知识迁移更稳健。这不是你明天能直接用的工具，但它解释了为什么有些AI绘画模型在调高「负向提示」权重时容易崩——问题可能出在训练阶段，而非推理参数。
📄 原文摘要(英文)
On-policy distillation (OPD) adapts diffusion models by querying a teacher along trajectories generated by the current student, but how it should behave under classifier-free guidance (CFG), a default component of modern diffusion systems, remains poorly understood. Existing OPD methods naturally extend velocity matching to the CFG-composed prediction, directly matching teacher and student guided velocities. We show that this objective is under-identified at the branch level: positive- and negative-branch errors can compensate in the guided prediction. Through two contrasting cases, we find that naive matching remains effective under shared negative conditioning, where both branch errors decrease jointly. When the model's native CFG schema retains privileged information in the teacher's negative branch that is unavailable to the student, however, this joint reduction breaks down and the composed objective induces antagonistic branch-error dynamics, reducing the positive-branch error while increasing the negative-branch error. We term this failure mode Negative Branch Asymmetry (NBA). To address NBA, we introduce Positive--Direction Matching (PDM), a branch-aware OPD objective that separately constrains the positive prediction and the CFG conditional direction. We apply PDM to dense-to-sparse video control, where naive guided matching is highly sensitive to inference guidance scales, while branch-aware supervision enables more robust and effective knowledge transfer.