MultiBooth: Towards Generating All Your Concepts in an Image from Text

TL;DR

MultiBooth is a new method for multi-concept image generation from text that improves fidelity and efficiency by dividing the process into learning individual concepts and integrating them with bounding boxes.

Contribution

It introduces a two-phase approach with a multi-modal encoder and bounding box guidance, enhancing multi-concept image generation in diffusion models.

Findings

Outperforms baselines in qualitative evaluations

Achieves higher concept fidelity

Reduces inference cost

Abstract

This paper introduces MultiBooth, a novel and efficient technique for multi-concept customization in image generation from text. Despite the significant advancements in customized generation methods, particularly with the success of diffusion models, existing methods often struggle with multi-concept scenarios due to low concept fidelity and high inference cost. MultiBooth addresses these issues by dividing the multi-concept generation process into two phases: a single-concept learning phase and a multi-concept integration phase. During the single-concept learning phase, we employ a multi-modal image encoder and an efficient concept encoding technique to learn a concise and discriminative representation for each concept. In the multi-concept integration phase, we use bounding boxes to define the generation area for each concept within the cross-attention map. This method enables the creation of individual concepts within their specified regions, thereby facilitating the formation of multi-concept images. This strategy not only improves concept fidelity but also reduces additional inference cost. MultiBooth surpasses various baselines in both qualitative and quantitative evaluations, showcasing its superior performance and computational efficiency. Project Page: https://multibooth.github.io/