让图像编辑模型像人一样思考，自动修正错误并决定何时停止。
ReasonEdit: Towards Reasoning-Enhanced Image Editing Models
- 引入思维与反思机制，让模型在编辑中主动理解指令
- 在ImgEdit、GEdit、Kris三个评测上分别提升4.3%、4.7%、8.2%
- 适用于需要高精度和逻辑一致性的图像编辑场景
近期图像编辑模型进展显著，主流架构将多模态大语言模型（MLLM）编码器与扩散解码器结合，如Step1X-Edit和Qwen-Image-Edit，其中MLLM负责编码参考图和指令，且训练中保持冻结。本文证明，激活MLLM的推理能力可进一步提升编辑性能。我们探索了两种推理机制：思维（thinking）与反思（reflection），前者利用MLLM的世界知识解析抽象指令，后者评估编辑结果，自动修正意外修改并判断停止时机。基于此，提出一个思考-编辑-反思循环框架。大量实验表明，从Step1X-Edit初始化的ReasonEdit-S在ImgEdit、GEdit、Kris上分别提升4.3%、4.7%、8.2%；集成Qwen-Image-Edit的ReasonEdit-Q在GEdit和Kris上也优于现有开源方法。
原文摘要 · Abstract (English)
Recent advances in image editing models have shown remarkable progress. A common architectural design couples a multimodal large language model (MLLM) encoder with a diffusion decoder, as seen in systems such as Step1X-Edit and Qwen-Image-Edit, where the MLLM encodes both the reference image and the instruction but remains frozen during training. In this work, we demonstrate that unlocking the reasoning capabilities of MLLM can further push the boundaries of editing models. Specifically, we explore two reasoning mechanisms, thinking and reflection, which enhance instruction understanding and editing accuracy. Based on that, our proposed framework enables image editing in a thinking-editing-reflection loop: the thinking mechanism leverages the world knowledge of MLLM to interpret abstract instructions, while the reflection reviews editing results, automatically corrects unintended manipulations, and identifies the stopping round. Extensive experiments demonstrate that our reasoning approach achieves significant performance gains, with improvements of ImgEdit (+4.3%), GEdit (+4.7%), and Kris (+8.2%) when initializing our DiT from the Step1X-Edit (ReasonEdit-S), and also outperforms previous open-source methods on both GEdit and Kris when integrated with Qwen-Image-Edit (ReasonEdit-Q).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。