Original document
GPT Image 2 · mixed
[中文]
でChatGPTで画像を作成してもらって、今日また作成してもらったらGPT image 2かもしれず、出来が変わったように見えるのでメモ
左の水色と黄色のが先週
右の紫のが今日
右のは透明感とか解像度、緻密さが違うような気がする…
プロンプト
曼荼羅の近未来SF版を描いて
[English]
I had ChatGPT create images, and when I had it create them again today, it might be GPT image 2, and it seems like the quality has changed, so I'm making a note of it
The light blue and yellow one on the left is from last week
The purple one on the right is from today
I feel like the transparency, resolution, and fineness are different for the one on the right.
Prompt
Draw a near-future sci-fi version of a mandalaHow to use
- Copy the complete original prompt, including any parameters.
- Replace the subject, text and composition with your own requirements.
- Use a compatible external tool; check its current access conditions and review the result.
Before you start
- Check whether a reference image is required. A compatible model label does not mean this example was generated with that model.
- Keep names, figures and visible text accurate; results can vary between model versions.