The tweet mentions that the video was created by sequencing four images generated by Nano Banana Pro, using a common prompt for both image and video generation that was devised by GPT-5.
Nano Banana Proで生成した4枚の画像をプロンプトで指定して順番に切り替わるようにして動画化していますCC BY 4.0. Prompt pages keep the original attribution and source links from the upstream gallery records stored in the database.


