Text-conditioned image editing is a recently emerged and highly practical
task, and its potential is immeasurable. However, most of the concurrent
methods are unable to perform action editing, i.e. they can not produce results
that conform to the action semantics of the editing prompt and preserve the
content of the original image. To solve the problem of action editing, we
propose KV Inversion, a method that can achieve satisfactory reconstruction
performance and action editing, which can solve two major problems: 1) the
edited result can match the corresponding action, and 2) the edited object can
retain the texture and identity of the original real image. In addition, our
method does not require training the Stable Diffusion model itself, nor does it
require scanning a large-scale dataset to perform time-consuming training.

文本条件图像编辑是一个新出现的高度实用的任务，其潜力是无法衡量的。然而，大多数现有方法无法进行动作编辑，即它们无法产生与编辑提示的动作语义相符合且保留原始图像内容的结果。为了解决动作编辑问题，我们提出了 KV Inversion 方法，它可以实现令人满意的重建性能和动作编辑，可以解决两个重要问题：1）编辑结果能够匹配相应的动作，2）编辑对象能够保留原始真实图像的纹理和身份。此外，我们的方法不需要训练稳定弥散模型本身，也不需要扫描大规模数据集进行耗时的训练。