Cones 2：多主体可定制图像合成
Cones 2: Customizable Image Synthesis with Multiple Subjects
AI总结：
Cones 2 通过文本嵌入残差学习表示主体，并利用布局先验校正交叉注意力图来安排多个主体位置，从而在无需微调的情况下实现高效、可控的多主体图像合成。
摘要：
合成具有用户指定主体的图像因其实际应用而受到越来越多的关注。尽管单主体定制近来取得了成功，但随着主体数量的增加，现有算法面临训练成本高和成功率低的问题。为了实现以多主体为约束的可控图像合成，本工作研究了如何高效地表示特定主体以及如何恰当地组合不同主体。我们发现，关于主体令牌的文本嵌入已经可以作为一种简单而有效的表示，支持任意组合而无需任何模型微调。通过在基础嵌入之上学习残差，我们能够在各种文本条件下稳健地将原始主体转换为定制主体。随后，我们提出采用布局这一非常抽象且易于获取的先验，作为主体排列的空间引导。通过校正交叉注意力图中的激活，布局指定并分离了不同主体在图像中的位置，显著缓解了它们之间的相互干扰。定性和定量实验结果均表明，在多主体定制的各种设置下，我们的方法优于最先进的替代方案。
英文摘要：
Synthesizing images with user-specified subjects has received growing attention due to its practical applications. Despite the recent success in single subject customization, existing algorithms suffer from high training cost and low success rate along with increased number of subjects. Towards controllable image synthesis with multiple subjects as the constraints, this work studies how to efficiently represent a particular subject as well as how to appropriately compose different subjects. We find that the text embedding regarding the subject token already serves as a simple yet effective representation that supports arbitrary combinations without any model tuning. Through learning a residual on top of the base embedding, we manage to robustly shift the raw subject to the customized subject given various text conditions. We then propose to employ layout, a very abstract and easy-to-obtain prior, as the spatial guidance for subject arrangement. By rectifying the activations in the cross-attention map, the layout appoints and separates the location of different subjects in the image, significantly alleviating the interference across them. Both qualitative and quantitative experimental results demonstrate our superiority over state-of-the-art alternatives under a variety of settings for multi-subject customization.
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。
