Luma Prompt Generator

About the “Luma Prompt Generator” template

Builds a paste-ready prompt for Luma: subject, action, camera, pace, light and style, adapted to text, start image, start and end or looping, depending on what your version supports, plus variants and iteration tips. It is one of the templates in AI Video.

What it will ask you (16)

1. Working mode
2. Video idea (e.g. a paper boat crosses a puddle and turns into a sailing boat on reaching the sea)
3. Main subject, original and fictional, with 2 or 3 visual traits that stay fixed (e.g. small blue paper boat, sharp folds, white sail)
4. Action that happens during the clip (one clear action)
5. Setting and atmosphere (place, era, weather, background objects)
6. Main framing
7. Camera movement (it is best to ask for just one)
8. Pace of the movement
9. Lighting
10. Visual style (just one: mixing styles tends to fail)
11. Desired length in seconds (check the lengths the tool offers today)
12. Desired aspect ratio (check which ones the tool supports)
13. I want the end to connect with the start (looping clip, if your version allows it)
14. Images or clips you will use and what must be kept from each (e.g. photo 1 = first frame, keep the composition)
15. Things you do NOT want to see, comma-separated (they are rewritten as positives in the prompt)
16. Write the prompt in English (otherwise in Spanish)

Example result

What the AI returned with this prompt and some sample answers.

# Luma prompt · a red tram climbs a cobbled hill at golden hour

SUMMARY AND ASSUMPTIONS
  Text-only mode, one single action and one single camera move.
  No loop: the shot has a clear ending (the tram comes to a stop).

PROMPT FOR LUMA
  A small red tram with cream window frames and a single round headlight climbs a
  steep cobbled street lined with pale houses and hanging laundry. Wide shot, the
  camera tracks smoothly beside the tram at its pace. Natural, unhurried rhythm.
  Golden-hour light, long shadows across the cobbles, photorealistic and cinematic.
  The tram reaches the top of the hill and slows to a stop beside an empty bench.

SETTINGS TO CHECK IN LUMA
  - Model: whichever your account offers (check the current documentation).
  - Input mode: text only (to be checked).
  - Desired duration: 6 s (to be checked).
  - Desired aspect ratio: 16:9 (to be checked).
  - Loop: off. Files to upload: none.

WHAT EACH PART DOES
  - Subject: three fixed traits of the tram so it stays the same.
  - Camera and rhythm: one single move, at the tram's pace.
  - Final state: where and how the shot ends.
…

How to use it

1. Answer the questions in the form above.
2. Generate the prompt and copy it, or open it straight in your AI.
3. Paste it into ChatGPT, Claude or Gemini. If the result doesn't fit, ask the AI to adjust it or generate it again with other answers.

Frequently asked questions

What do I get with “Luma Prompt Generator”?

A complete prompt tailored to your answers, ready to paste into ChatGPT, Claude or Gemini. Builds a paste-ready prompt for Luma: subject, action, camera, pace, light and style, adapted to text, start image, start and end or looping, depending on what your version supports, plus variants and iteration tips.

How long does it take?

You answer 16 guided questions; most have options to pick from, so it usually takes a couple of minutes.

Is it free?

Yes. Fill in the form, sign in with Google and copy the prompt, at no cost.

Do you store what I type?

Yes, in your history: we keep your answers and the generated prompt, linked to your account, for 12 months. You can see and delete them in “My account”. For health, diet, fitness and finance templates we store nothing.