AI 修图连改十次不糊了：秘诀是让它自己改自己
现在的 AI 修图，单次效果惊艳，但连续改几次就崩：每改一次，画面就偏离一点原始状态，几轮下来，细节糊、颜色漂、指令也渐渐不听了。这篇把「让模型自己改自己」的训练原则搬进图像编辑：训练时强迫模型在它自己上一轮的输出上继续改，而不是总拿干净原图练手，逼它适应真实的多轮操作。但自己改出来的轨迹没有标准答案，没法直接教，于是他们让一个始终盯着原图的「老师模型」来打分纠偏，学生模型则只看着自己改过的图、听着累积的指令往下走。结果，长序列编辑的退化大幅减少，质量不掉、指令照听。它不是你明天就能用的功能，但这是「AI 修图能陪你改到满意为止」这条路上关键的一步。
📄 原文摘要(英文)
Image editing models produce impressive results for individual edits, but their quality often deteriorates over multiple editing turns. Each editing turn introduces small distribution shifts that accumulate over successive edits, creating a gap between the input distributions encountered during the editor's original training and multi-turn inference. We introduce a training scheme that makes multi-turn image editing stable under this accumulating distribution shift. A key is to force the editor to operate on its own outputs from previous editing turns during training, bringing the principle of Self-Forcing to image editing. The main challenge is that self-generated editing trajectories deviate from ground-truth trajectories, making direct supervision unreliable. We address this challenge through a distillation objective that leverages a teacher image editor to provide a reliable training signal when the model operates on its own previous outputs. We introduce an asymmetric conditioning scheme: while the student performs edits sequentially on its own outputs, the teacher remains anchored to the original clean image and receives a compound editing instruction. Experiments show substantially reduced degradation over long multi-turn sequences while maintaining editing quality and instruction adherence.