NumeriKontrol: Adding Numeric Control to Diffusion Transformers for Instruction-based Image Editing
By: Zhenyu Xu , Xiaoqi Shen , Haotian Nan and more
Potential Business Impact:
Control image changes with exact numbers.
Instruction-based image editing enables intuitive manipulation through natural language commands. However, text instructions alone often lack the precision required for fine-grained control over edit intensity. We introduce NumeriKontrol, a framework that allows users to precisely adjust image attributes using continuous scalar values with common units. NumeriKontrol encodes numeric editing scales via an effective Numeric Adapter and injects them into diffusion models in a plug-and-play manner. Thanks to a task-separated design, our approach supports zero-shot multi-condition editing, allowing users to specify multiple instructions in any order. To provide high-quality supervision, we synthesize precise training data from reliable sources, including high-fidelity rendering engines and DSLR cameras. Our Common Attribute Transform (CAT) dataset covers diverse attribute manipulations with accurate ground-truth scales, enabling NumeriKontrol to function as a simple yet powerful interactive editing studio. Extensive experiments show that NumeriKontrol delivers accurate, continuous, and stable scale control across a wide range of attribute editing scenarios. These contributions advance instruction-based image editing by enabling precise, scalable, and user-controllable image manipulation.
Similar Papers
Kontinuous Kontext: Continuous Strength Control for Instruction-based Image Editing
CV and Pattern Recognition
Adjusts picture edits from slight to strong.
SliderEdit: Continuous Image Editing with Fine-Grained Instruction Control
CV and Pattern Recognition
Lets you smoothly change picture edits, one by one.
AttriCtrl: Fine-Grained Control of Aesthetic Attribute Intensity in Diffusion Models
CV and Pattern Recognition
Controls how pretty pictures look, exactly how you want.