Movie Weaver: Tuning-Free Multi-Concept Video Personalization with Anchored Prompts

TL;DR

Movie Weaver introduces a tuning-free method for multi-concept video personalization using anchored prompts and concept embeddings, enabling accurate and flexible integration of multiple reference images into personalized videos.

Contribution

It proposes a novel anchored prompt mechanism and concept embeddings to enable multi-concept video personalization without fine-tuning.

Findings

Outperforms existing methods in identity preservation.

Effectively integrates multiple concepts like face, body, and animals.

Maintains high quality in personalized videos.

Abstract

Video personalization, which generates customized videos using reference images, has gained significant attention. However, prior methods typically focus on single-concept personalization, limiting broader applications that require multi-concept integration. Attempts to extend these models to multiple concepts often lead to identity blending, which results in composite characters with fused attributes from multiple sources. This challenge arises due to the lack of a mechanism to link each concept with its specific reference image. We address this with anchored prompts, which embed image anchors as unique tokens within text prompts, guiding accurate referencing during generation. Additionally, we introduce concept embeddings to encode the order of reference images. Our approach, Movie Weaver, seamlessly weaves multiple concepts-including face, body, and animal images-into one video, allowing flexible combinations in a single model. The evaluation shows that Movie Weaver outperforms existing methods for multi-concept video personalization in identity preservation and overall quality.