Image editing has advanced significantly with the development of diffusion models using both inversion-based and instruction-based methods. However, current inversion-based approaches struggle with big modifications (e.g., adding or removing objects) due to the structured nature of inversion noise, which hinders substantial changes. Meanwhile, instruction-based methods often constrain users to black-box operations, limiting direct interaction for specifying editing regions and intensity. To address these limitations, we propose BrushEdit, a novel inpainting-based instruction-guided image editing paradigm, which leverages multimodal large language models (MLLMs) and image inpainting models to enable autonomous, user-friendly, and interactive free-form instruction editing. Specifically, we devise a system enabling free-form instruction editing by integrating MLLMs and a dual-branch image inpainting model in an agent-cooperative framework to perform editing category classification, main object identification, mask acquisition, and editing area inpainting. Extensive experiments show that our framework effectively combines MLLMs and inpainting models, achieving superior performance across seven metrics including mask region preservation and editing effect coherence.

翻译：随着基于反演和基于指令的扩散模型的发展，图像编辑技术已取得显著进步。然而，当前基于反演的方法由于反演噪声的结构化特性，在进行大幅修改（如添加或移除物体）时面临困难，这阻碍了实质性改变。同时，基于指令的方法通常将用户限制在黑箱操作中，难以直接交互指定编辑区域和强度。为克服这些局限，我们提出BrushEdit——一种基于修复的指令引导图像编辑新范式，它利用多模态大语言模型（MLLMs）和图像修复模型，实现自主、用户友好且交互式的自由形式指令编辑。具体而言，我们设计了一个通过集成MLLMs与双分支图像修复模型的智能体协作系统，在代理协作框架中执行编辑类别分类、主体对象识别、掩码获取及编辑区域修复。大量实验表明，我们的框架有效结合了MLLMs与修复模型，在掩码区域保持度和编辑效果连贯性等七项指标上均取得优异性能。