融合GAN与扩散模型，实现真实图像的精细可控编辑。
Beyond Sliders: Mastering the Art of Diffusion-based Image Manipulation
- 用文本与视觉双重引导，对抗性优化图像细节。
- 在真实场景图像上表现优于传统概念滑块方法。
- 适合需要高保真图像编辑的设计师与研究人员。
在图像生成领域，对真实感与定制化的需求日益迫切。尽管现有方法如概念滑块已取得进展，但在无AIGC的真实图像（尤其是现实场景拍摄）上表现不佳。为此，我们提出Beyond Sliders，一种融合GAN与扩散模型的创新框架，支持跨多种图像类别的复杂编辑。该方法在对抗性机制下，通过细粒度的文本与视觉双重引导，显著提升图像质量与真实感。大量实验证明，Beyond Sliders在多种应用场景中具备卓越的鲁棒性与通用性。
原文摘要 · Abstract (English)
In the realm of image generation, the quest for realism and customization has never been more pressing. While existing methods like concept sliders have made strides, they often falter when it comes to no-AIGC images, particularly images captured in real world settings. To bridge this gap, we introduce Beyond Sliders, an innovative framework that integrates GANs and diffusion models to facilitate sophisticated image manipulation across diverse image categories. Improved upon concept sliders, our method refines the image through fine grained guidance both textual and visual in an adversarial manner, leading to a marked enhancement in image quality and realism. Extensive experimental validation confirms the robustness and versatility of Beyond Sliders across a spectrum of applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。