Control Color:

Multimodal Diffusion-Based Interactive Image Colorization

Zhexin Liang, Zhaochen Li, Shangchen Zhou, Chongyi Li, Chen Change Loy
S-Lab, Nanyang Technological University


In this work, we successfully achieve highly controllable multi-modal image colorization. Our method is built on Stable Diffusion with new designs such as stroke control and content-guided deformable autoencoder. These designs offer our method realistic outputs along with various applications, including text/stroke/exemplar-based colorization, hybrid control colorization, recolorization, iterative editing and the pioneering implementation of local region colorization. Our approach provides a more diverse range of colors and high user interactivity.

Our Various Applications

Unconditional Colorization

Colorize images into various colors without conditions.

Multi-control Colorization

Colorize images according to user needs
(text prompts, strokes and exemplar).

Iterative Editing

Our method allows user to edit images freely and iteratively.

Region colorization

Our method supports colorization for specific regions in images.


Recolorize colorful images or old photos.

Demo Video

(Download: full video)