ChatGPT Sketch 可将随手涂鸦变成细节丰富的 AI 图像

OpenAI 于周二发布了 ChatGPT Images 2.5，并新增了一种告诉 ChatGPT 你希望它生成什么图像的方式：画一张涂鸦。借助名为 Sketch 的新功能，你可以直接在 ChatGPT 内绘图，再告诉 ChatGPT 希望它如何基于这张草图生成图像。

你可以在聊天框中输入 @Sketch 来启用 Sketch 功能，随后会弹出一个窗口供你绘制图案。我进行了简短测试：按照我的指令，它成功将我用电脑鼠标画出的粗糙猫咪涂鸦转换成了一张逼真的照片。现在，你还可以直接在希望修改的图像局部添加评论；我利用这一功能将猫的眼睛从蓝色改成了绿色。

至于 ChatGPT Images 2.5，OpenAI 表示，它生成的图像拥有“更自然的光照和更丰富的纹理”，能够在“多轮”交互中更好地遵循编辑指令，而且图像生成延迟较 Images 2.0“最多降低 50%”。OpenAI 称，ChatGPT Images 2.5 现已面向桌面端、移动端和网页版的 ChatGPT、ChatGPT Work 与 Codex 用户推出。

OpenAI announced ChatGPT Images 2.5 on Tuesday and is adding a new way to tell ChatGPT what you want it to make an image of: by drawing a doodle. With a new feature called Sketch, you can just draw something right inside ChatGPT and then tell ChatGPT how you want it to make an image based on that sketch.

You can activate the Sketch feature by typing @Sketch into your chat box, and a window will pop up where you can make your drawing. I briefly tested it, and it successfully turned my bad doodle of a cat that I drew with my computer mouse into a realistic photo, per my instructions. You can also now leave comments directly on parts of images that you want changed, which I used to make the cat’s eyes green instead of blue.

As for ChatGPT Images 2.5, OpenAI says that it makes images with “more natural lighting and richer textures,” is better at following your editing instructions “across multiple turns,” and that image generation latency has been reduced by “up to 50% compared with Images 2.0.” ChatGPT Images 2.5 is out now for ChatGPT, ChatGPT Work, and Codex users on desktop, mobile, and web, according to OpenAI.