Sign up for new-member prices on your first plan

Prompt library

AI Video Prompts That Were Actually Tested

Every guide here collects AI video prompts we ran ourselves on Buble. Each prompt comes with the model, the settings and the clip it produced, so you can judge a prompt by its result instead of by its promise, then copy it into the generator in one click.

Prompt guides

Our method

How we test AI video prompts

A list of prompts is only useful if you can see what they do. These rules apply to every guide in the library.

Run on Buble, not copied

We write each prompt ourselves and run it on the model it is listed under. The video on the card is that run, not a hand-picked clip from somewhere else.

Model and settings on every card

Resolution, length, aspect ratio and audio are listed with the prompt, because the same words behave differently at other settings.

Cheapest settings that still show the point

Most examples run at 480p and five seconds. When a higher tier changes the outcome, the guide shows the same prompt on that model too.

Fictional people only

Characters in these AI video prompts are invented, and products have no logos, so every example is safe to adapt.

Anatomy

What strong AI video prompts have in common

Different models have their own habits, but good AI video prompts share the same skeleton. Each model guide then adds that model's specific wording.

Step 01

A specific subject

Two or three visible details instead of a category: a red vintage tram, a fox made of orange clay.

Step 02

One action that fits the length

A five-second clip carries one clear action. Longer clips or numbered shots carry more.

Step 03

A place, a time and light

Setting and light source decide color and mood more than any style adjective.

Step 04

One camera instruction

Shot size, angle and a single move, written in plain film terms.

Step 05

Sound, when audio is on

Two or three concrete sounds, or a short spoken line in quotes.

Make it yours

Turn an example into your own video

The fastest way to a good clip is to start from a prompt that already works and change it in small steps. This keeps what made the example succeed and lets you see what each change does.

Step 01

Pick the closest example

Match the shot type first, not the topic. A product orbit prompt adapts to any object; a talking-head prompt adapts to any speaker.

Step 02

Swap the subject

Replace the subject sentence and keep the rest. Describe your subject with the same level of detail as the original.

Step 03

Keep the settings

Run it once with the card's resolution, length and aspect ratio, so any difference comes from your words.

Step 04

Change one sentence per run

Adjust the camera, then the light, then the sound. One change at a time shows you what works.

Step 05

Scale up at the end

When the draft is right, rerun it at a higher resolution or on a stronger model for the final version.

By input

AI video prompts for each way of starting a video

What the prompt needs to say depends on what you give the model besides text. The guides label every example with the mode it used.

Text to video

The prompt carries everything: subject, action, place, camera, light and sound. These AI video prompts are the longest and the most detailed.

Start frame

Your image is the opening shot, so the prompt only describes the motion and the camera. Describing the scene again can fight the picture.

Reference images

Several uploads supply a face, an outfit or a place. Refer to them by their order, such as Image 1 and Image 2, and say what to keep from each.

Video to video

A source clip gives the motion. The prompt says what changes, such as the person or the style, and what must stay the same.

Wording

Words that change the result

A few kinds of words do most of the work in a video prompt. Learning them is quicker than collecting long lists of adjectives.

Light sources

Golden hour, neon signs, soft window light, a single desk lamp. A named source gives the model direction, color and shadows at once.

Pace

Slow motion, a slow push-in, a quick whip pan. Pace words control how much happens in the few seconds you have.

Texture and style

Claymation, watercolor, 16mm film grain, glossy product render. One clear style beats a stack of competing ones.

Exclusions

Short notes such as no text, no logos or exactly two people help when a model keeps adding things you did not ask for.

Who uses them

Who these prompts are for

The examples are chosen to cover the clips people make most often, so there is usually one close to what you need.

Social creators

Vertical clips with sound, quick reveals and talking characters for Reels, TikTok and Shorts.

Marketers and shops

Product orbits, clean studio light and short ad scenes without logos you would need to clear.

Filmmakers and storytellers

Multi-shot sequences, consistent characters and camera language for previsualization and short films.

Anyone learning to prompt

Side-by-side examples of a vague and a structured prompt show faster than any tutorial why AI video prompts need specific choices.

Using the library

Free to read, one click to try

Part of each guide is open to everyone. Sign in to Buble, which is free, and every prompt in every guide becomes readable and copyable.

Copy the prompt

Take the exact text into your own workflow or another tool.

Use this prompt

Open the model with the prompt and its settings filled in, change a detail and generate.

Bring your own media

Cards marked with a photo or video icon need your upload; the card explains what to add.

FAQ

AI video prompts FAQ

Access, cost, models and reuse.







Start

Start from a prompt that already works

Open a guide, pick the closest example and make it yours.