Derived from diffusion models, MangaNinjia specializes in the task of reference-guided line art colorization. We incorporate two thoughtful designs to ensure precise character detail transcription, including a patch shuffling module to facilitate correspondence learning between the reference color image and the target line art, and a point-driven control scheme to enable fine-grained color matching. Experiments on a self-collected benchmark demonstrate the superiority of our model over current solutions in terms of precise colorization. We further showcase the potential of the proposed interactive point control in handling challenging cases, cross-character colorization, multi-reference harmonization, beyond the reach of existing algorithms.
Cite
@article{arxiv.2501.08332,
title = {MangaNinja: Line Art Colorization with Precise Reference Following},
author = {Zhiheng Liu and Ka Leong Cheng and Xi Chen and Jie Xiao and Hao Ouyang and Kai Zhu and Yu Liu and Yujun Shen and Qifeng Chen and Ping Luo},
journal= {arXiv preprint arXiv:2501.08332},
year = {2025}
}
Comments
Project page and code: https://johanan528.github.io/MangaNinjia/