Abstract
Instruction-based image editing offers a powerful and intuitive way to manipulate images through natural language. Yet, relying solely on text instructions limits fine-grained control over the extent of edits. We introduce Kontinuous Kontext, an instruction-driven editing model that provides a new dimension of control over edit strength, enabling users to adjust edits gradually from no change to a fully realized result in a smooth and continuous manner. Kontinuous Kontext extends a state-of-the-art image editing model to accept an additional input, a scalar edit strength which is then paired with the edit instruction, enabling explicit control over the extent of the edit. To inject this scalar information, we train a lightweight projector network that maps the input scalar and the edit instruction to coefficients in the model's modulation space. For training our model, we synthesize a diverse dataset of image-edit-instruction-strength quadruplets using existing generative models, followed by a filtering stage to ensure quality and consistency. Kontinuous Kontext provides a unified approach for fine-grained control over edit strength for instruction driven editing from subtle to strong across diverse operations such as stylization, attribute, material, background, and shape changes, without requiring attribute-specific training.
Abstract (translated)
指令驱动的图像编辑提供了一种通过自然语言强大且直观地操纵图像的方法。然而，仅依赖文本指令限制了对编辑程度进行精细控制的能力。我们引入了Kontinuous Kontext（连续上下文），这是一种指令驱动的编辑模型，它提供了对编辑强度的新维度的控制，使用户能够从不做任何更改到完全实现结果之间平滑且连续地调整编辑。 Kontinuous Kontext 扩展了一种最先进的图像编辑模型以接受额外输入——一个标量编辑强度值，并将其与编辑指令配对，从而明确控制了编辑的程度。为了注入这个标量信息，我们训练了一个轻量级投影网络，将输入的标量和编辑指令映射到模型调制空间中的系数。 在训练我们的模型时，我们使用现有的生成模型综合了一组多样化的图像-编辑-指令-强度四元数据集，并经过筛选阶段以确保质量和一致性。Kontinuous Kontext 为各种操作（如风格化、属性、材质、背景和形状变化）提供了从细微到强烈调整的统一方法，而无需特定属性的训练。
URL
https://arxiv.org/abs/2510.08532
