PreciseControl：通过细粒度属性控制增强文本到图像扩散模型
PreciseControl: Enhancing Text-To-Image Diffusion Models with Fine-Grained Attribute Control
AI总结：
本文提出PreciseControl，利用StyleGAN解耦的$\mathcal{W+}$空间并训练潜映射器条件化T2I扩散模型，从而在保留文本控制和身份属性的同时实现人脸细粒度连续编辑及多人组合生成。
摘要：
最近，我们看到用于文本到图像（T2I）扩散模型的个性化方法大量涌现，这些方法利用少量图像学习一个概念。现有方法在用于人脸个性化时，难以在保持身份的同时实现令人信服的反演，并且依赖于对生成人脸进行基于语义文本的编辑。然而，面部属性编辑需要更细粒度的控制，而仅靠文本提示很难实现这一点。相比之下，StyleGAN模型学习了丰富的人脸先验，并能够通过潜空间操纵实现对细粒度属性编辑的平滑控制。本工作使用StyleGAN解耦的$\mathcal{W+}$空间来条件化T2I模型。该方法使我们能够精确操纵面部属性，例如自然地引入微笑，同时保留T2I模型固有的现有粗粒度文本控制。为了使T2I模型能够以$\mathcal{W+}$空间为条件，我们训练了一个潜映射器，将潜码从$\mathcal{W+}$转换到T2I模型的token嵌入空间。所提出的方法在保持属性的人脸图像精确反演方面表现出色，并促进了细粒度属性编辑的连续控制。此外，我们的方法可以很容易地扩展到生成涉及多个人的组合。我们进行了大量实验，以验证我们的方法在人脸个性化和细粒度属性编辑方面的有效性。
英文摘要：
Recently, we have seen a surge of personalization methods for text-to-image (T2I) diffusion models to learn a concept using a few images. Existing approaches, when used for face personalization, suffer to achieve convincing inversion with identity preservation and rely on semantic text-based editing of the generated face. However, a more fine-grained control is desired for facial attribute editing, which is challenging to achieve solely with text prompts. In contrast, StyleGAN models learn a rich face prior and enable smooth control towards fine-grained attribute editing by latent manipulation. This work uses the disentangled $\mathcal{W+}$ space of StyleGANs to condition the T2I model. This approach allows us to precisely manipulate facial attributes, such as smoothly introducing a smile, while preserving the existing coarse text-based control inherent in T2I models. To enable conditioning of the T2I model on the $\mathcal{W+}$ space, we train a latent mapper to translate latent codes from $\mathcal{W+}$ to the token embedding space of the T2I model. The proposed approach excels in the precise inversion of face images with attribute preservation and facilitates continuous control for fine-grained attribute editing. Furthermore, our approach can be readily extended to generate compositions involving multiple individuals. We perform extensive experiments to validate our method for face personalization and fine-grained attribute editing.
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。
