SliderEdit：基于细粒度指令控制的连续图像编辑
SliderEdit: Continuous Image Editing with Fine-Grained Instruction Control
把多段编辑指令解耦成可连续调节的滑块，用一组共享的低秩适配矩阵实现强度插值，可直接套用到 FLUX-Kontext、Qwen-Image-Edit 等指令编辑模型上，为交互式编辑提供细粒度控制手段。
原文依据 our method learns a single set of low-rank adaptation matrices that generalize across diverse edits, attributes, and compositional instructions
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于指令的图像编辑模型近期取得了令人瞩目的性能，能够依据多指令提示词对输入图像执行复杂编辑。然而，这些模型以固定强度施加提示词中的每一条指令，限制了用户精确且连续地控制单条编辑强度的能力。我们提出 SliderEdit，一个面向连续图像编辑、具备细粒度且可解释指令控制的框架。给定由多部分组成的编辑指令，SliderEdit 将各条指令解耦，并把每一条呈现为一个全局训练的滑块，从而可平滑调节其强度。与此前在文本到图像生成中引入基于滑块的属性控制、且通常需要为每个属性或概念单独训练或微调的工作不同，我们的方法学习一组单一的低秩适配矩阵，可泛化到多样的编辑、属性与组合指令之上。这使得沿单条编辑维度进行连续插值成为可能，同时保持空间局部性与全局语义一致性。我们将 SliderEdit 应用于最优的编辑模型，包括 FLUX-Kontext 与 Qwen-Image-Edit，并在编辑可控性、视觉一致性与用户可操控性方面观察到显著提升。我们是首个探索并提出面向图像编辑模型的连续细粒度指令控制框架的工作。我们的结果为具有连续与组合控制的交互式、指令驱动图像操作开辟了道路。
英文原文摘要 1564 字符
Instruction-based image editing models have recently achieved impressive performance, enabling complex edits to an input image from a multi-instruction prompt. However, these models apply each instruction in the prompt with a fixed strength, limiting the user's ability to precisely and continuously control the intensity of individual edits. We introduce SliderEdit, a framework for continuous image editing with fine-grained, interpretable instruction control. Given a multi-part edit instruction, SliderEdit disentangles the individual instructions and exposes each as a globally trained slider, allowing smooth adjustment of its strength. Unlike prior works that introduced slider-based attribute controls in text-to-image generation, typically requiring separate training or fine-tuning for each attribute or concept, our method learns a single set of low-rank adaptation matrices that generalize across diverse edits, attributes, and compositional instructions. This enables continuous interpolation along individual edit dimensions while preserving both spatial locality and global semantic consistency. We apply SliderEdit to state-of-the-art editing models, including FLUX-Kontext and Qwen-Image-Edit, and observe substantial improvements in edit controllability, visual consistency, and user steerability. We are the first to explore and propose a framework for continuous, fine-grained instruction control in image editing models. Our results pave the way for interactive, instruction-driven image manipulation with continuous and compositional control.