从单个视觉示例出发的无语言生成式编辑
Language-Free Generative Editing from One Visual Example
提出从成对视觉示例中直接提取条件信号、无需文本与训练即可驱动扩散模型编辑的范式，其 condition-steering 机制与 inversion-correction 步骤可迁移到任何基于 DDIM 反演的编辑流程中，用于缓解反演重建误差并实现语言难以描述的变换（如雨、模糊）。
原文依据 a training-free framework that learns conditioning signals directly from visual examples for precise, language-free image editing
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论文本引导的扩散模型通过语言实现直观控制，推动了图像编辑的发展。然而，尽管这些方法能力强大，我们却意外地发现，当前最先进的方法在雨、模糊等简单的日常变换上表现不佳。我们将这一局限归因于训练过程中文本监督信号微弱且不一致，导致语言与视觉之间的对齐较差。现有解决方案往往依赖额外的微调或更强的文本条件，但需要高昂的数据与计算开销。我们认为，基于扩散模型的编辑能力并未丢失，只是被文本所遮蔽。通往低成本视觉编辑的大门依然敞开，关键在于一种以视觉为中心的范式，像人类一样超越语言去感知和推理视觉变化。受此启发，我们提出视觉扩散条件（Visual Diffusion Conditioning, VDC），这是一个无需训练的框架，可直接从视觉示例中学习条件信号，实现精确、无语言的图像编辑。给定一对示例——一张带有目标效果、一张不带——VDC 推导出刻画该变换的视觉条件，并通过一种新颖的条件引导机制来操控生成过程。配套的反演校正步骤可缓解 DDIM 反演过程中的重建误差，保留细节与真实感。在多种任务上，VDC 均优于无需训练以及完全微调的基于文本的编辑方法。代码与模型已开源于 https://omaralezaby.github.io/vdc/
英文原文摘要 1533 字符
Text-guided diffusion models have advanced image editing by enabling intuitive control through language. However, despite their strong capabilities, we surprisingly find that SOTA methods struggle with simple, everyday transformations such as rain or blur. We attribute this limitation to weak and inconsistent textual supervision during training, which leads to poor alignment between language and vision. Existing solutions often rely on extra finetuning or stronger text conditioning, but suffer from high data and computational requirements. We argue that diffusion-based editing capabilities aren't lost but merely hidden from text. The door to cost-efficient visual editing remains open, and the key lies in a vision-centric paradigm that perceives and reasons about visual change as humans do, beyond words. Inspired by this, we introduce Visual Diffusion Conditioning (VDC), a training-free framework that learns conditioning signals directly from visual examples for precise, language-free image editing. Given a paired example--one image with and one without the target effect--VDC derives a visual condition that captures the transformation and steers generation through a novel condition-steering mechanism. An accompanying inversion-correction step mitigates reconstruction errors during DDIM inversion, preserving fine detail and realism. Across diverse tasks, VDC outperforms both training-free and fully fine-tuned text-based editing methods. The code and models are open-sourced at https://omaralezaby.github.io/vdc/