AlcheMinT：面向多参考一致视频生成的细粒度时序控制
AlcheMinT: Fine-grained Temporal Control for Multi-Reference Consistent Video Generation
提出一种可插拔的时间区间位置编码，把主体身份与显式时间戳绑定，并通过 token 级拼接注入预训练视频扩散模型，无需额外交叉注意力即可实现多主体出现/消失的精细时序控制，可直接复用于可控视频合成与故事板生成。
原文依据 a novel positional encoding mechanism that unlocks the encoding of temporal intervals, associated in our case with subject identities
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期，基于大型扩散模型的主体驱动视频生成技术已实现以用户提供的主体为条件的个性化内容合成。然而，现有方法缺乏对主体出现与消失的细粒度时序控制，而这对于组合式视频合成、故事板制作和可控动画等应用至关重要。我们提出 AlcheMinT，一个统一的框架，为主体驱动视频生成引入显式时间戳条件。我们的方法提出一种新颖的位置编码机制，能够对时间区间进行编码（在本工作中该区间与主体身份相关联），同时与预训练视频生成模型的位置嵌入无缝集成。此外，我们引入描述主体的文本 token，以增强视觉身份与视频字幕之间的绑定，缓解生成过程中的歧义。通过 token 级拼接，AlcheMinT 避免了任何额外的交叉注意力模块，且带来的参数开销可忽略不计。我们建立了一个基准，用于评估多主体身份保持、视频保真度和时序遵循性。实验结果表明，AlcheMinT 的视觉质量可与最优的视频个性化方法相匹配，同时首次实现了视频内多主体生成的精确时序控制。
英文原文摘要 1416 字符
Recent advances in subject-driven video generation with large diffusion models have enabled personalized content synthesis conditioned on user-provided subjects. However, existing methods lack fine-grained temporal control over subject appearance and disappearance, which are essential for applications such as compositional video synthesis, storyboarding, and controllable animation. We propose AlcheMinT, a unified framework that introduces explicit timestamps conditioning for subject-driven video generation. Our approach introduces a novel positional encoding mechanism that unlocks the encoding of temporal intervals, associated in our case with subject identities, while seamlessly integrating with the pretrained video generation model positional embeddings. Additionally, we incorporate subject-descriptive text tokens to strengthen binding between visual identity and video captions, mitigating ambiguity during generation. Through token-wise concatenation, AlcheMinT avoids any additional cross-attention modules and incurs negligible parameter overhead. We establish a benchmark evaluating multiple subject identity preservation, video fidelity, and temporal adherence. Experimental results demonstrate that AlcheMinT achieves visual quality matching state-of-the-art video personalization methods, while, for the first time, enabling precise temporal control over multi-subject generation within videos.