TokenDial: 通过时空token偏移实现文本到视频的连续属性控制
TokenDial: Continuous Attribute Control for Text-to-Video Generation in Visual Dial Space
AI总结：
TokenDial通过在中间时空视觉patch-token空间中添加偏移实现文本到视频生成模型的连续属性控制，通过调整偏移量实现外观和运动动态的可预测编辑，优于现有基线。
摘要：
我们提出了TokenDial，一种用于预训练文本到视频生成模型中连续滑动式属性控制的框架。尽管现代生成器能产生高质量的视频，但它们在不导致身份、背景或时间一致性漂移的情况下，对属性变化程度（如效果强度或运动幅度）的控制有限。TokenDial基于观察：中间时空视觉patch-token空间中的加法偏移形成语义控制方向，调整偏移量可产生一致且可预测的编辑。我们通过预训练的理解信号学习属性特定的token偏移，无需重新训练骨干网络：利用语义方向匹配进行外观控制，利用运动幅度缩放进行运动控制。我们在多种属性和提示上展示了TokenDial的有效性，实现了比现有最佳基线更强的可控性和更高的编辑质量，通过广泛的定量评估和人类研究得到支持。
英文摘要：
In video diffusion transformers, visual patch tokens maintain explicit correspondence to space and time. We hypothesize that their channel dimension can serve as a semantic control space, which we call Visual Dial Space V+. In this space, additive directions can be broadcast to the token stream to control appearance or motion attributes, enabling slider-style edits such as making a generated person look older or run faster. To verify the hypothesis, we present TokenDial, a framework for learning attribute directions in the proposed V+ space. TokenDial keeps the pretrained video generator frozen and optimizes only additive directions. Rather than requiring paired edited videos, TokenDial supervises each direction through its induced effect on generated videos: the edited video should move along the desired attribute while the remaining content stays stable. The learned directions become reusable visual dials that support continuous appearance and motion control, explicit spatiotemporal localization, composition, and reuse across prompts, resolutions, and video lengths. Experiments and human studies show that TokenDial achieves stronger slider controllability and better content preservation than prior video editing and slider-based methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
