MC$^2$：面向定制化多概念生成的多概念引导
MC$^2$: Multi-concept Guidance for Customized Multi-concept Generation
AI总结：
针对多概念定制生成中的模型整合与概念混淆问题，本文提出推理时优化方法 MC$^2$，通过自适应注意力细化整合异构单概念模型，并发布 MC++ 基准。
摘要：
定制化文本到图像生成根据用户指定的概念合成图像，在处理单个概念方面已取得显著进展。然而，当扩展到多个概念时，现有方法往往难以妥善整合不同模型，并避免不同概念的特征发生意外混合。本文提出 MC$^2$，这是一种用于多概念定制的新方法，通过推理时优化提升灵活性与保真度。MC$^2$ 能够整合具有异构架构的多个单概念模型。通过自适应地细化视觉 token 与文本 token 之间的注意力权重，该方法确保图像区域准确对应其关联概念，同时最大限度减少概念间干扰。大量实验表明，MC$^2$ 在提示-参考对齐方面优于基于训练的方法。此外，MC$^2$ 可无缝应用于文本到图像生成，提供稳健的组合能力。为促进多概念定制评估，我们还引入了一个新基准 MC++。代码将在 https://github.com/JIANGJiaXiu/MC-2 公开发布。
英文摘要：
Customized text-to-image generation, which synthesizes images based on user-specified concepts, has made significant progress in handling individual concepts. However, when extended to multiple concepts, existing methods often struggle with properly integrating different models and avoiding the unintended blending of characteristics from distinct concepts. In this paper, we propose MC$^2$, a novel approach for multi-concept customization that enhances flexibility and fidelity through inference-time optimization. MC$^2$ enables the integration of multiple single-concept models with heterogeneous architectures. By adaptively refining attention weights between visual and textual tokens, our method ensures that image regions accurately correspond to their associated concepts while minimizing interference between concepts. Extensive experiments demonstrate that MC$^2$ outperforms training-based methods in terms of prompt-reference alignment. Furthermore, MC$^2$ can be seamlessly applied to text-to-image generation, providing robust compositional capabilities. To facilitate the evaluation of multi-concept customization, we also introduce a new benchmark, MC++. The code will be publicly available at https://github.com/JIANGJiaXiu/MC-2.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
