InstantFamily: Masked Attention for Zero-shot Multi-ID Image Generation

TL;DR

InstantFamily introduces a novel masked cross-attention mechanism and multimodal embedding stack for zero-shot multi-ID image generation, effectively preserving identities and enabling controlled, cohesive multi-concept image synthesis.

Contribution

The paper presents a new masked cross-attention approach combined with multimodal embeddings for zero-shot multi-ID image generation, improving identity preservation and compositional control.

Findings

Outperforms existing methods in multi-ID image generation

Achieves state-of-the-art results in identity preservation

Scales effectively with more identities than trained on

Abstract

In the field of personalized image generation, the ability to create images preserving concepts has significantly improved. Creating an image that naturally integrates multiple concepts in a cohesive and visually appealing composition can indeed be challenging. This paper introduces "InstantFamily," an approach that employs a novel masked cross-attention mechanism and a multimodal embedding stack to achieve zero-shot multi-ID image generation. Our method effectively preserves ID as it utilizes global and local features from a pre-trained face recognition model integrated with text conditions. Additionally, our masked cross-attention mechanism enables the precise control of multi-ID and composition in the generated images. We demonstrate the effectiveness of InstantFamily through experiments showing its dominance in generating images with multi-ID, while resolving well-known multi-ID generation problems. Additionally, our model achieves state-of-the-art performance in both single-ID and multi-ID preservation. Furthermore, our model exhibits remarkable scalability with a greater number of ID preservation than it was originally trained with.