The 7-slot prompt formula I use for AI product ad shots (bad vs good examples)
Description and use
A seven‑slot prompt formula standardizes AI product ad creation, improving quality and consistency by specifying product details, action, camera move, lens & light, location, realism & style, and duration.
Problem
Clients need high‑quality AI‑generated product ad shots but current prompts produce low‑quality results.
Outcome
Ad shots improved in clarity, realism, and consistency; each shot can be regenerated independently.
Workflow
- 1. Write a 7‑slot prompt: [Subject + product detail] + [one action] + [one camera move] + [lens & light] + [location] + [realism & style] + [duration]
- 2. Keep product details, lens, light, location, realism & style identical across shots; vary only action and camera move
- 3. Avoid copy, prices, logos, multiple actions, and vague adjectives
- 4. For image‑to‑video, describe only motion, not product
- 5. Assemble shots into a full ad (e.g., 15‑second with hook, hero, CTA)
- 6. Leave empty space for text in CTA shot
- 7. Export and edit text in post‑production
Evidence
I make short product ads with AI video generators for small clients.
The single biggest quality jump didn’t come from a better model. It came from writing prompts like a shot list instead of a mood board.
[Subject + product detail] + [one action] + [one camera move] + [lens & light] + [location] + [realism & style] + [duration]
Keep the product’s fixed information identical across shots. Change only the action and framing.
Copy, prices, logos. Models misspell and distort letters. Leave empty space in the frame and add exact text in editing.
If you start from an existing product photo (image-to-video), don’t re-describe the product at all. The photo already holds product, light and set. Describe only the motion: The camera slowly moves closer. The bottle remains still.
The CTA shot deliberately leaves empty space; the button text goes on in the editor.
- Record date: 2026-10-03T02:41:07.950Z