Att-Adapter：基于条件变分自编码器的鲁棒、精确的领域特定多属性文生图扩散适配器
Att-Adapter: A Robust and Precise Domain-Specific Multi-Attributes T2I Diffusion Adapter via Conditional Variational Autoencoder
AI总结：
针对扩散模型难以精确控制新领域连续多属性的问题，提出即插即用的 Att-Adapter，通过解耦交叉注意力与 CVAE 实现无需成对数据的鲁棒多属性控制。
摘要：
文生图（T2I）扩散模型在生成高质量图像方面已取得卓越性能。然而，在新领域中仅凭文本引导实现对连续属性的精确控制，尤其是同时控制多个属性（例如眼睛睁开程度或汽车宽度等数值），仍然是一项重大挑战。为解决这一问题，我们提出了 Attribute（Att）Adapter，这是一种新颖的即插即用模块，旨在使预训练扩散模型具备细粒度的多属性控制能力。我们的方法从一组样本图像中学习单一控制适配器，这些图像可以是不成对的，并包含多种视觉属性。Att-Adapter 利用解耦交叉注意力模块，自然地协调多个领域属性与文本条件。我们进一步在 Att-Adapter 中引入条件变分自编码器（CVAE）以缓解过拟合，匹配视觉世界的多样性。在两个公开数据集上的评估表明，Att-Adapter 在控制连续属性方面优于所有基于 LoRA 的基线方法。此外，我们的方法支持更宽的控制范围，并改善了多个属性之间的解耦，超越了基于 StyleGAN 的技术。值得注意的是，Att-Adapter 具有灵活性，训练时不需要成对合成数据，并且能够在单一模型中轻松扩展到多个属性。
英文摘要：
Text-to-Image (T2I) Diffusion Models have achieved remarkable performance in generating high quality images. However, enabling precise control of continuous attributes, especially multiple attributes simultaneously, in a new domain (e.g., numeric values like eye openness or car width) with text-only guidance remains a significant challenge. To address this, we introduce the Attribute (Att) Adapter, a novel plug-and-play module designed to enable fine-grained, multi-attributes control in pretrained diffusion models. Our approach learns a single control adapter from a set of sample images that can be unpaired and contain multiple visual attributes. The Att-Adapter leverages the decoupled cross attention module to naturally harmonize the multiple domain attributes with text conditioning. We further introduce Conditional Variational Autoencoder (CVAE) to the Att-Adapter to mitigate overfitting, matching the diverse nature of the visual world. Evaluations on two public datasets show that Att-Adapter outperforms all LoRA-based baselines in controlling continuous attributes. Additionally, our method enables a broader control range and also improves disentanglement across multiple attributes, surpassing StyleGAN-based techniques. Notably, Att-Adapter is flexible, requiring no paired synthetic data for training, and is easily scalable to multiple attributes within a single model.
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。
