Can open-sora model be utilized to predict or generate the next frame of a video based on preceding frames?

[xuhyun11]

Can open-sora model be utilized to predict or generate the next frame of a video based on preceding frames?
If so, could you please provide guidance on how to implement this in programming?

If direct prediction and generation of the subsequent video frame are not feasible, I would like to know how to craft cue words or prompts to assist in predicting and generating the next frame of the video.