可编辑可视化设计

摘要

尽管GPT-Image-2、Nano-Banana这类扩散基础模型展现出卓越的视觉表现力，但其端到端生成本质上产出的只是极易出现文本错误的扁平化位图，无法进行图层级后期编辑。相比之下，借助编码智能体实现的基于代码的视觉生成虽能提供精确的布局控制和图层解耦，却仍受限于全局审美直觉的缺失以及复杂视觉素材的编码困难。针对上述问题，我们提出一种由编码智能体驱动的新范式——可编辑视觉设计（Editable Visual Design）。我们将视觉语言模型（VLM）定位为“创意大脑”，负责需求理解、任务规划与审美判断；同时，将图像生成模型作为按需的“视觉世界模拟器”，用于合成独立的视觉素材。智能体遵循“先想象、再行动”的闭环工作流：先生成相互独立的素材，再编写原生HTML/CSS，并根据视觉渲染反馈对设计进行迭代优化。此外，智能体设计回放（Agent Design Replay）能够忠实再现与人类专业设计师相似的创意与推理轨迹。最终，系统交付具有解耦图层与真实文本的可编辑产物，使用户能够在图形用户界面上通过直观的鼠标拖拽调整布局。在海报、信息图等场景上的验证表明，该范式成功兼顾了精良的美学效果与生产级的可编辑性。

English

While diffusion base models such as GPT-Image-2 and Nano-Banana exhibit remarkable visual expressiveness, their end-to-end generation inherently yields flattened bitmaps with error-prone text, precluding layer-wise post-editing. Conversely, code-based visual generation via Coding Agents provides precise layout control and decoupled layers, yet remains constrained by a lack of global aesthetic intuition and the difficulty of coding complex visual assets. To address this, we propose Editable Visual Design, a new paradigm driven by a Coding Agent. We designate the VLM as the ``creative brain'' for requirement comprehension, task planning, and aesthetic judgment, while utilizing the image generation model as an on-demand ``visual world simulator'' to synthesize standalone visual assets. Operating under an ``imagine first, then act'' closed-loop workflow, the agent generates isolated assets, writes native HTML/CSS, and iteratively refines the design against visual rendering feedback. Furthermore, Agent Design Replay faithfully reproduces the creative and reasoning trajectory akin to that of professional human designers. Ultimately, the system delivers editable artifacts with decoupled layers and real text, enabling users to perform intuitive mouse dragging and layout adjustments on a graphical user interface. Validations on posters, infographics, and other scenarios show that this paradigm successfully achieves both refined aesthetics and production-grade editability.