Slideredit++ enables smooth control for better image editing sliders
SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing
Computer Vision and Pattern RecognitionGraphics
Summary
Sliders let people change how much an image edit affects a photo, but current sliders can jump suddenly or mess up when used together. The authors created a set of tests called SlideBench to measure these problems and then improved the sliders with a method called SliderEdit++. This new approach makes slider movements smoother and more predictable, preventing edits from interfering with each other. Their technique also runs much faster than older methods, making image editing more responsive.
What this means in practice
- •For graphic designers: Use smoother, more predictable sliders for adjusting image edits interactively without abrupt changes or conflicting effects.
- •For mobile app developers: Build faster, more responsive photo editing apps by integrating improved slider controls that reduce lag and unintended visual jumps.
Authors
Arman Zarei, Sayan Nag, Bryan Wang, Franck Dernoncourt, Varun Manjunatha, Nedim Lipka, Soheil Feizi, Samyadeep Basu
Abstract
Slider-based control aims to give users continuous, fine-grained control over the intensity of individual edits in instruction-based image editing. However, existing approaches fail to deliver reliable continuous controllability: traversing a slider can produce abrupt visual jumps and non-monotonic changes, while jointly controlled sliders can interfere with one another. To systematically study these limitations, we introduce SlideBench, a comprehensive benchmark for continuous image editing spanning diverse editing categories and equipped with a unified suite of metrics quantifying monotonic progression, perceptual continuity, and inter-slider disentanglement. Building on these observations, we propose SliderEdit++, which explicitly regularizes the intermediate editing trajectory rather than supervising only its endpoints. Our method combines velocity- and semantic-space trajectory regularization with spectral control to encourage smooth, predictable slider traversal, together with a disentanglement objective that reduces interference between independently controlled edits. On SlideBench, SliderEdit++ achieves state-of-the-art performance, improving the overall score by 18.5% relative to the strongest baseline. At the same time, using a few-step editing backbone makes our method approximately 3x to 20x faster than existing slider-based approaches, enabling substantially more responsive interactive editing.