Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation

TL;DR

Stand-In is a lightweight, plug-and-play framework that enhances identity preservation in video generation with minimal additional parameters, outperforming existing methods and supporting diverse applications.

Contribution

It introduces a novel, efficient identity control method using restricted self-attentions and conditional position mapping in pre-trained models.

Findings

Outperforms full-parameter training methods in video quality and identity preservation.

Uses only ~1% additional parameters and 2000 training pairs.

Supports multiple tasks like subject-driven generation, stylization, and face swapping.

Abstract

Generating high-fidelity human videos that match user-specified identities is important yet challenging in the field of generative AI. Existing methods often rely on an excessive number of training parameters and lack compatibility with other AIGC tools. In this paper, we propose Stand-In, a lightweight and plug-and-play framework for identity preservation in video generation. Specifically, we introduce a conditional image branch into the pre-trained video generation model. Identity control is achieved through restricted self-attentions with conditional position mapping. Thanks to these designs, which greatly preserve the pre-trained prior of the video generation model, our approach is able to outperform other full-parameter training methods in video quality and identity preservation, even with just $\sim$1% additional parameters and only 2000 training pairs. Moreover, our framework can be seamlessly integrated for other tasks, such as subject-driven video generation, pose-referenced video generation, stylization, and face swapping.