AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
Published in CVPR 2025, 2025
Instruction-based image editing aims to modify specific image elements with natural language instructions. However, current models in this domain often struggle to accurately execute complex user instructions, as they are trained on low-quality data with limited editing types. We present Logo AnyEdit, a comprehensive multi-modal instruction editing dataset, comprising 2.5 million high-quality editing pairs spanning over 20 editing types and five domains. Click here to visit our website.
Recommended citation: Q. Yu, W. Chow, Z. Yue, K. Pan, Y. Wu, X. Wan, J. Li, S. Tang, H. Zhang, and Y. Zhuang, “AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), 2025.
Download Paper