AI video prompts to copy and run
28 AI video prompts, each one a complete shot with its scene, its sound and its music written out. Open one in the generator and it runs exactly as written; change a detail and it becomes yours. All of these AI video prompts were run by us before they went on this page.
AI video prompts by model
Browse AI video prompts by style
Each card names the technique its shot demonstrates. All AI video prompts here load into the generator in one click; the full text is in the guide.
Cinematic AI video prompts
Shot lists, cuts and camera amplitude on a timeline.
IllustrationTextRain, violin, doorwayThe plain three-field shape, with camera motion written as an actionRun this prompt
Illustration
Illustration
Dialogue & voice AI video prompts
Speaker IDs, verbatim lines, voiceover and lines that cross cuts.
Illustration
IllustrationTextVoiceover over a night driveThe exact voiceover phrasing, plus the lips-closed statement it requiresRun this prompt
IllustrationTextA line that survives the cutCarrying one sentence across a shot change with <scenetrans>Run this prompt
Product AI video prompts
Controlled camera, controlled light, and audio you actually chose.
IllustrationImageProduct orbit from a stillA single clean camera idea plus an explicit silence requestRun this prompt
Illustration
Illustration
Animation AI video prompts
Style contracts that hold for the whole clip.
Illustration
Illustration
IllustrationTextWatercolour street in rainStyle plus a transition described as an event, not an effectRun this prompt
Made hereTextPapercraft stop-motion bloomStepped stop-motion cadence carried through picture, paper-friction foley and a matching mallet scoreRun this prompt
Made hereText3D short — robot and puddleA stylised 3D character beat with a timed cut, where servo and water sounds land on the actionsRun this prompt
Audio-led AI video prompts
Soundscape first — the field most prompts leave empty.
Made hereTextForge quenchGiving the picture a countable rhythm so the soundscape and the score have the same beats to land onRun this prompt
IllustrationTextRain on a window, no scoreWriting overall_soundscape as the main event and refusing musicRun this prompt
Illustration
IllustrationTextRehearsal room, diegetic vs scoreKeeping music the characters can hear out of non_diegetic_musicRun this prompt
Made hereTextASMR pour over iceAn audio-led clip where every visible event has a named sound and the music field is explicitly N/ARun this prompt
References AI video prompts
Giving each reference image, clip or voice exactly one job.
IllustrationReferencesCharacter kept across a new sceneNaming each reference and giving it exactly one jobRun this prompt
IllustrationReferencesMotion from a clip, look from stillsSplitting the job between a video reference and image refsRun this prompt
IllustrationReferencesVoice taken from an audio referenceBinding a reference voice to a specific speaker IDRun this prompt
First & last frame AI video prompts
Describing the path between two images, not the images.
IllustrationImagePortrait turn between two framesDescribing only the path, since both frames are givenRun this prompt
IllustrationImageUmbrella opening in the rainNarrowing differences until the last frame is reachedRun this prompt
IllustrationImageLanding on a last frameInferring a plausible earlier state and converging onto itRun this prompt
On-screen text AI video prompts
Quoting strings verbatim so they render as letters, not noise.
Illustration
Illustration
Illustration
Make these AI video prompts your own
Start from the closest one
Among the AI video prompts, pick the one whose camera and sound are nearest to what you want, not the nicest subject.
Swap one block at a time
Change the subject, keep the camera and sound. Then change the sound. AI video prompts teach most when one change per run shows what each part does.
Run it where it fits
Most AI video prompts here are text prompts. Load them into text to video, or adapt the action for an image you already have.
Run these AI video prompts in text to video or start from a picture in image to video. Photo templates such as zombie love story AI and the gangnam style AI video selfie dance load their prompt for you. Every other tool is listed under AI video tools.
AI video prompts FAQ
We wrote them and ran them on MiniMax H3. Each one is a complete shot with scene, sound and music written out. We only publish AI video prompts we have run ourselves.
Yes, but these AI video prompts were written in MiniMax H3's three-block format. The scene block carries the subject, action and camera, which any model reads; results will differ from model to model.
Click Run this prompt on any card. The AI video prompts open in the video console exactly as written, with the right mode selected, and nothing runs until you press Generate.
Length is a setting in the console, not a sentence in the prompt. Our AI video prompts describe one shot; the model fits that action into the length you pick.
The AI video prompts are yours to copy and change. Commercial use of the generated clip follows the terms of the model you run it on and this site's terms.
Related pages
- H3 Video GeneratorCreate an H3 video with native audio and exact per-second credit pricing.
- H3 Max explainedA visual, evidence-led guide to the speed claim, quality rankings, real costs, limits and the Infinite Slop connection.
- Infinite Slop explainedWatch the official channel, understand the public queue and see why endless AI television is an airtime product — not one long video.
- AI Video MakerCreate an H3 video from a prompt, with native audio and the exact credit cost shown before submission.
- Text to videoWrite one shot — subject, action, camera, sound — and render it on the model that fits.
- Image to videoStart from a still you already have and make it move — motion, camera and sound from one prompt.
- Video to promptUpload a clip and get the structured prompt that recreates it — camera, cut timing and soundscape included.
- Zombie love storyTwo photos become a 15-second zombie couple drama — the standoff, the embrace and the memory, with sound.
- Gangnam selfie danceThree photos become the trio selfie dance: center, left, right, then a point at the lens, on the beat.
- All video toolsEvery tool on the site, grouped by what you start from: words, a frame, or a clip.
- BlogEvery article in one place: model explainers, prompt guides and local-setup walkthroughs.
- PricingOne-time credit packs from $9.99 with no subscription or free allowance.