ScribbleEdit: Synthetic Data for Image Editing with Scribbles and Text

ArXi:2605.01135v1 Announce Type: new Recent progress in generative models has significantly advanced image editing capabilities, yet precise and intuitive user control remains difficult. Specifically, users often struggle to communicate both exact spatial layouts and specific semantic details simultaneously. While natural language instructions effectively convey high-level semantics like texture and color, they lack spatial specificity. Conversely, freehand scribbles provide rough spatial boundaries but cannot express detailed visual attributes.