Although large-scale text-to-image generative models have shown promising
performance in synthesizing high-quality images, directly applying these models
to image editing remains a significant challenge. This challenge is further
amplified in video editing due to the additional dimension of time. Especially
for editing real videos as it necessitates maintaining a stable semantic layout
across the frames while executing localized edits precisely without disrupting
the existing backgrounds. In this paper, we propose \textit{RealCraft}, an
attention-control-based method for zero-shot editing in real videos. By
employing the object-centric manipulation of cross-attention between prompts
and frames and spatial-temporal attention within the frames, we achieve precise
shape-wise editing along with enhanced consistency. Our model can be used
directly with Stable Diffusion and operates without the need for additional
localized information. We showcase our zero-shot attention-control-based method
across a range of videos, demonstrating localized, high-fidelity, shape-precise
and time-consistent editing in videos of various lengths, up to 64 frames.

在这篇论文中，我们提出了一种基于注意力控制的方法，名为 RealCraft，用于零样本编辑实际视频。通过在提示和帧之间进行对象为中心的处理，并在帧内使用时空注意力，我们实现了精确的形状编辑以及增强的一致性。我们的模型可以直接与稳定的扩散一起使用，并且不需要额外的局部信息。我们展示了我们的零样本注意控制方法在各种长度的视频中进行定位、高保真度、形状精确和时间一致的编辑。