OpenAI Codex 的 ImageGen 新增 Lightbox 和 Canvas 功能
Codex 的图像生成终于能局部修改了，点一下就能擦除或改标题，不用再写千字提示词。
OpenAI 在 Codex 中为 ImageGen 添加了 Lightbox 和 Canvas 功能，方便用户在工作流中探索和优化视觉元素。
新的图像编辑工作流支持在 ChatGPT 和 Codex 桌面端指向人物、擦除对象、标注标题位置等操作，无需长提示词即可精确修改。该功能提升了图像局部编辑的交互性。
ImageGen in Codex just got a new lightbox and canvas. Now, it’s even easier to explore and refine visuals in your workflow. dominik kundel @dkundel A picture may be worth a thousand words, but editing one shouldn’t take a thousand-word prompt. Point at a character. Erase what should disappear. Comment where the title should change. Here’s the new image editing workflow in ChatGPT and Codex on desktop.
This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Codex, ImageGen, OpenAI, 图像编辑.
Primary source verification: published directly by @OpenAIDevs with first-party authority. Cross-source corroboration: 11 independent sources have covered this development (including IT之家, 歸藏(guizang.ai), OpenAI), confirming industry-wide signal strength.
