Latest Research Papers
2025-01-21
arXiv
TokenVerse: Versatile Multi-concept Personalization in Token Modulation Space
TokenVerse is a method for multi-concept personalization using a pre-trained text-to-image diffusion model, capable of disentangling and combining complex visual elements from multiple images. It leverages the semantic modulation space to enable localized control over various concepts, including objects, accessories, materials, pose, and lighting. The effectiveness of TokenVerse is demonstrated in challenging personalization settings, outperforming existing methods.
We present TokenVerse -- a method for multi-concept personalization,
leveraging a pre-trained text-to-image diffusion model. Our framework can
disentangle complex visual elements and attributes from as little as a single
image, while enabling seamless plug-and-play generation of combinations of
concepts extracted from multiple images. As opposed to existing works,
TokenVerse can handle multiple images with multiple concepts each, and supports
a wide-range of concepts, including objects, accessories, materials, pose, and
lighting. Our work exploits a DiT-based text-to-image model, in which the input
text affects the generation through both attention and modulation (shift and
scale). We observe that the modulation space is semantic and enables localized
control over complex concepts. Building on this insight, we devise an
optimization-based framework that takes as input an image and a text
description, and finds for each word a distinct direction in the modulation
space. These directions can then be used to generate new images that combine
the learned concepts in a desired configuration. We demonstrate the
effectiveness of TokenVerse in challenging personalization settings, and
showcase its advantages over existing methods. project's webpage in
https://token-verse.github.io/