SliderEdit: Continuous Image Editing with Fine-Grained Instruction Control

TL;DR

SliderEdit introduces a novel framework for continuous, fine-grained control in instruction-based image editing, enabling smooth adjustments of individual edits with a single trained model, improving precision and user steerability.

Contribution

It proposes a unified, slider-based control mechanism for image editing instructions that generalizes across diverse edits without requiring separate training for each attribute.

Findings

Enhanced control over individual edit strengths.

Preservation of spatial locality and semantic consistency.

Improved edit controllability and visual coherence.

Abstract

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 image editing models, including FLUX-Kontext and Qwen-Image-Edit, and observe substantial improvements in edit controllability, visual consistency, and user steerability. To the best of our knowledge, we are the first to explore and propose a framework for continuous, fine-grained instruction control in instruction-based image editing models. Our results pave the way for interactive, instruction-driven image manipulation with continuous and compositional control.