Recent progress in personalized image generation using diffusion models has been significant. However, development in the area of open-domain and non-fine-tuning personalized image generation is proceeding rather slowly. In this paper, we propose Subject-Diffusion, a novel open-domain personalized image generation model that, in addition to not requiring test-time fine-tuning, also only requires a single reference image to support personalized generation of single- or multi-subject in any domain. Firstly, we construct an automatic data labeling tool and use the LAION-Aesthetics dataset to construct a large-scale dataset consisting of 76M images and their corresponding subject detection bounding boxes, segmentation masks and text descriptions. Secondly, we design a new unified framework that combines text and image semantics by incorporating coarse location and fine-grained reference image control to maximize subject fidelity and generalization. Furthermore, we also adopt an attention control mechanism to support multi-subject generation. Extensive qualitative and quantitative results demonstrate that our method outperforms other SOTA frameworks in single, multiple, and human customized image generation. Please refer to our \href{https://oppo-mente-lab.github.io/subject_diffusion/}{project page}

翻译：摘要：最近，利用扩散模型进行个性化图像生成的进展显著。然而，在开放域且无需微调的个性化图像生成领域，其发展相对缓慢。本文提出Subject-Diffusion，一种新颖的开放域个性化图像生成模型。该模型不仅无需测试时微调，而且仅需单张参考图像，即可支持任意域中单个或多个主体的个性化生成。首先，我们构建了一个自动数据标注工具，并利用LAION-Aesthetics数据集构建了一个大规模数据集，包含7600万张图像及其对应的主体检测边界框、分割掩码和文本描述。其次，我们设计了一个新的统一框架，通过结合粗略位置和细粒度参考图像控制来融合文本和图像语义，以最大化主体的保真度和泛化性。此外，我们还采用了一种注意力控制机制来支持多主体生成。大量定性和定量结果表明，我们的方法在单主体、多主体及人类定制图像生成任务上均优于其他SOTA框架。请参阅我们的\href{https://oppo-mente-lab.github.io/subject_diffusion/}{项目页面}。