An AI video prompt describes a moment that changes: who is in the frame, what they do, where the camera is and how it moves, and what the scene sounds like when the model supports audio. The prompts below are written that way, and each page splits the prompt from the settings so you can see what actually drove the result.

Open a video, copy the prompt, then follow the method to recreate it in the same model. Use the filters to narrow by platform, category or difficulty, and start with the beginner prompts if you are new to text-to-video or image-to-video.

Questions about these prompts

What is an AI video prompt?

It is the written instruction you give a video model. A good one names the subject, the action, the setting, the camera and the lighting, and keeps each clip to one main idea.

What is the difference between text-to-video and image-to-video?

Text-to-video builds the whole scene from your words. Image-to-video starts from a picture you supply, so the prompt should describe the motion rather than repeat what is already in the image.

Will these prompts work in any model?

They are written in plain descriptive language that most models understand, but results differ between models and versions. Each page lists the model and settings used, so start there and adjust.

How long are the clips?

It depends on the model and your settings. The duration used is listed on every prompt page, and longer scenes are normally built by joining several short clips.