发表机构
GSIS Tohoku University; RIKEN AIP JAPAN（东北大学全球信息社会研究院; 日本理化学研究所先进智能项目中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究在图像编辑中，高CFG轨迹生成的目标图像何时能被反演。通过对照实验，用现有基准的提示生成图像并反演，揭示提示重建行为类型，定义提示压力分析生成，文本分析表明主体和措辞影响反演，评估干预措施支持局部轨迹感知分析。
AI 中文摘要
文本引导的扩散反演是图像编辑的核心，实践中反演常采用比生成或编辑更低的无分类器引导（CFG）尺度。本文在已知真实初始潜在和去噪轨迹的对照设置中研究该问题，结果揭示三种提示级重建行为，定义提示压力分析生成，文本分析表明主体和措辞影响反演，评估干预措施支持局部轨迹感知分析。
英文摘要
Text-guided diffusion inversion is central to image editing, where an image is mapped to an initial latent and then edited by replaying the denoising process under a modified prompt. In practice, however, inversion is often performed with a lower classifier-free guidance(CFG) scale than the one used for generation or editing. This mismatch is empirically useful but leaves a basic question unresolved: when a target image is generated by a high-CFG trajectory, when can that trajectory actually be inverted? We study this question in a controlled generation--inversion--reconstruction setting, where the true initial latent and denoising trajectory are known. Using prompts taken from an existing diffusion-editing benchmark, we generate images under high CFG and reconstruct them with fixed-point inversion using the same prompt and guidance setting. The results reveal three types of prompt-level reconstruction behavior: easy prompts that reconstruct for most initial latents, hard prompts that fail for most initial latents, and intermediate prompts whose success depends on the prompt--latent pairing. To analyze the generation side, we define prompt pressure, a step-wise measure of how strongly CFG moves the denoising update away from the unconditional trajectory. Total pressure correlates with reconstruction quality and separates easy from hard prompts, but it does not explain the success or failure of intermediate prompt--latent pairs. Text-side analyses further show that the main visual subject and wording can change inversion difficulty. Finally, we evaluate a compact trajectory-consistency intervention that relaxes guidance only at locally unstable inverse steps. This diagnostic check improves reconstruction and Prompt-to-Prompt editing in our controlled setting, supporting the view that high-CFG inversion failure requires local, trajectory-aware analysis.
