Abstract
In this paper, we present MoMA: an open-vocabulary, training-free personalized image model that boasts flexible zero-shot capabilities. As foundational text-to-image models rapidly evolve, the demand for robust image-to-image translation grows. Addressing this need, MoMA specializes in subject-driven personalized image generation. Utilizing an open-source, Multimodal Large Language Model (MLLM), we train MoMA to serve a dual role as both a feature extractor and a generator. This approach effectively synergizes reference image and text prompt information to produce valuable image features, facilitating an image diffusion model. To better leverage the generated features, we further introduce a novel self-attention shortcut method that efficiently transfers image features to an image diffusion model, improving the resemblance of the target object in generated images. Remarkably, as a tuning-free plug-and-play module, our model requires only a single reference image and outperforms existing methods in generating images with high detail fidelity, enhanced identity-preservation and prompt faithfulness. Our work is open-source, thereby providing universal access to these advancements.
Abstract (translated)
在本文中，我们提出了MoMA：一个开放词汇、无需训练的个性化图像模型，具有灵活的零样本能力。随着基础文本到图像模型的快速演变，对稳健图像到图像转换的需求不断增加。为满足这一需求，MoMA专注于主题驱动的个性化图像生成。利用一个开源的Multimodal Large Language Model（MLLM），我们训练MoMA既作为特征提取器又作为生成器。这种方法有效地将参考图像和文本提示信息协同作用，产生有价值的图像特征，促进图像扩散模型。为了更好地利用生成的特征，我们进一步引入了一种新颖的自注意短路方法，该方法有效地将图像特征转移到图像扩散模型中，提高了生成图像中目标对象的相似度。值得注意的是，作为无需调度的插件和播放模块，我们的模型只需要一个参考图像，并且在生成具有高细节保真度、增强身份保留和提示信仰的图像方面优于现有方法。我们的工作是开源的，从而为这些创新提供了统一的访问。
URL
https://arxiv.org/abs/2404.05674
