用文本快速编辑图像，保持细节且不破坏原图结构。
InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow
- 基于修正流框架，分步编辑同时保留关键内容。
- 在PIE数据集上优于现有方法，生成更清晰、更连贯。
- 适合需要快速精准修改图像的设计师与研究人员。
我们提出一种名为InstantEdit的快速文本引导图像编辑方法，基于修正流（RectifiedFlow）框架，采用多步编辑流程，在遵循文本指令的同时保留关键内容。通过引入专用反演策略PerRFI，利用修正流的直线采样轨迹实现高效反演。为提升生成一致性，提出逆向潜在注入再生方法，有效复用反演阶段获得的潜在信息，增强细节还原能力。进一步设计解耦式提示引导机制，平衡编辑灵活性与细节保持性，并集成边缘条件控制网络（Canny-conditioned ControlNet）以引入结构线索、抑制伪影。在PIE图像编辑数据集上的评估表明，InstantEdit不仅速度更快，且在定性和定量指标上均优于当前最先进的少步编辑方法。
原文摘要 · Abstract (English)
We propose a fast text-guided image editing method called InstantEdit based on the RectifiedFlow framework, which is structured as a few-step editing process that preserves critical content while following closely to textual instructions. Our approach leverages the straight sampling trajectories of RectifiedFlow by introducing a specialized inversion strategy called PerRFI. To maintain consistent while editable results for RectifiedFlow model, we further propose a novel regeneration method, Inversion Latent Injection, which effectively reuses latent information obtained during inversion to facilitate more coherent and detailed regeneration. Additionally, we propose a Disentangled Prompt Guidance technique to balance editability with detail preservation, and integrate a Canny-conditioned ControlNet to incorporate structural cues and suppress artifacts. Evaluation on the PIE image editing dataset demonstrates that InstantEdit is not only fast but also achieves better qualitative and quantitative results compared to state-of-the-art few-step editing methods.
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。