AI 出图终于能改字了：从像素变成可编辑的图层
现在的 AI 画图，生成的是整张像素图，想改一个字、挪一个元素，基本等于重画。这篇提出一个新路子：让 AI 像设计师一样，先想清楚要什么，再让图像模型生成单个素材，最后用代码（HTML/CSS）把它们拼成一张图。结果就是，你拿到的不再是一张死图，而是分好层的、文字是真的可编辑的，还能用鼠标直接拖拽调整。它把 AI 的审美和代码的精确结合了起来，在海报、信息图等场景上验证了效果。虽然现在还需要在特定工具里用，但这是 AI 出图从“一次性”走向“可修改”的关键一步。
📄 原文摘要(英文)
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.