Instruction-based image editing enables natural-language control over visual modifications, yet existing models falter under Instruction-Visual Complexity (IV-Complexity), where intricate instructions meet cluttered or ambiguous scenes. We introduce RePlan (Region-aligned Planning), a plan-then-execute framework that couples a vision-language planner with a diffusion editor. The planner decomposes instructions via step-by-step reasoning and explicitly grounds them to target regions; the editor then applies changes using a training-free attention-region injection mechanism, enabling precise, parallel multi-region edits without iterative inpainting. To strengthen planning, we apply GRPO-based reinforcement learning using 1K instruction-only examples, yielding substantial gains in reasoning fidelity and format reliability. We further present IV-Edit, a benchmark focused on fine-grained grounding and knowledge-intensive edits. Across IV-Complex settings, RePlan consistently outperforms strong baselines trained on far larger datasets, improving regional precision and overall fidelity. Our project page: https://replan-iv-edit.github.io
@article{arxiv.2512.16864,
title = {RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing},
author = {Tianyuan Qu and Lei Ke and Xiaohang Zhan and Longxiang Tang and Yuqi Liu and Bohao Peng and Bei Yu and Dong Yu and Jiaya Jia},
journal= {arXiv preprint arXiv:2512.16864},
year = {2025}
}
Comments
Precise region control and planning for instruction-based image editing. Our project page: https://replan-iv-edit.github.io