EditThinker：为任意图像编辑器解锁迭代式推理能力

摘要

基于指令的图像编辑已成为一个重要的研究领域，该领域受益于图像生成基础模型，已实现较高的美学质量，使得指令跟随能力成为当前的核心挑战。现有方法通过监督学习或强化学习提升指令遵循度，但由于内在随机性和缺乏深思熟虑，单轮编辑的成功率仍受限。本研究提出一种具备思考能力的编辑框架，通过模拟人类认知循环，迭代执行"边编辑边思考"的流程：批判生成结果并优化指令，随后重复生成直至满意。具体而言，我们训练了单一多模态大语言模型EditThinker作为该框架的推理引擎，联合生成评分、推理过程和优化后的指令。我们采用强化学习将EditThinker的思考过程与编辑行为对齐，从而产生更具针对性的指令改进。在四个基准测试上的大量实验表明，我们的方法能够显著提升任意图像编辑模型的指令跟随能力。我们将公开数据构建框架、数据集和模型，以促进社区发展。

English

Instruction-based image editing has emerged as a prominent research area, which, benefiting from image generation foundation models, have achieved high aesthetic quality, making instruction-following capability the primary challenge. Existing approaches improve instruction adherence via supervised or reinforcement learning, yet single-turn success rates remain limited due to inherent stochasticity and a lack of deliberation. In this work, we propose a deliberative editing framework to 'think' while they edit, which simulates the human cognitive loop by iteratively executing a Think-while-Edit cycle: Critiquing results and Refining instructions , followed by Repeating the generation until satisfactory. Specifically, we train a single MLLM, EditThinker, to act as the reasoning engine of this framework, which jointly produce the critique score, reasoning process, and refined instructions. We employ reinforcement learning to align the EditThinker's thinking with its editing, thereby generating more targeted instruction improvements. Extensive experiments on four benchmarks demonstrate that our approach significantly improves the instruction-following capability of any image editing model by a large margin. We will release our data construction framework, datasets, and models to benefit the community.

EditThinker：为任意图像编辑器解锁迭代式推理能力

EditThinker: Unlocking Iterative Reasoning for Any Image Editor

摘要

Support