Product hero shot: a 5-second generated clip for an ad or a listing
Prompt for a clean product shot with one motion and one light change, the kind that sits at the top of a listing or opens a 15-second ad.
A {product, with material and colour} on a {surface: matte black stone / pale oak / wet concrete}, centred, {background: seamless studio grey / soft out-of-focus kitchen}. {One motion: slow 45-degree turntable rotation / camera slow dolly in / a drop of water landing on it}. Studio lighting with a soft key from the upper left and a thin rim light tracing the edge; the rim light slowly sweeps across the surface. 100mm macro look, shallow depth of field, product tack sharp. Clean commercial style, true-to-life colours, no reflections of people, no hands. No on-screen text, no logo overlays. 5 seconds, 9:16.
Paste into the video model as one paragraph; remove the labels once you are happy with the content.
Steps
- Start from a real photo of the product as the first frame if you have one; the model will keep the label and proportions.
- Generate 4 takes; choose by whether the label stays readable through the motion.
- Add text and price in the editor, never in the prompt.
Tips
- Text on packaging is where models still fail. Keep the label small in frame or add it in post.
- One light event (the rim sweep) reads as 'premium' more than any adjective.
| works with | Veo: Google text-to-video / image-to-video prompts. · Kling: Kling text/image-to-video prompts. · Runway: Runway Gen prompts and camera controls. · Image models: Midjourney, Flux, Imagen: keyframes and style boards for image-to-video. |
| cost | Free. The video or image model you paste it into has its own pricing. |
| status | Unverified: written from the technique, not yet run end to end by us. |
| license | CC BY 4.0 for the text here; skills are MIT. |
| updated | 2026-11-01 |
| for agents | product-hero-shot-generation.md |
Related
Camera movement vocabulary that video models understand
The 14 camera moves that generation models respond to reliably, with the phrasing that works and the phrasing that produces a wobbling mess.
Keep the same character across clips: the reference sheet prompt
A character description block you reuse verbatim in every prompt, plus a generated reference sheet, so a face, outfit and build stay the same from shot to shot.
Image-to-video: generate the first frame, then animate it
Make a still with an image model first, fix the composition there, and only then ask the video model to animate it. Cheaper iterations and the look you chose, not the one the video model guessed.
Fashion lookbook: a model walks in a studio at 24 fps
A filled 7-part prompt for a lookbook clip: seamless backdrop, one walk toward the camera, cinema frame rate so the fabric moves like fabric, and the faces, feet and prints that need extra care.
The 7-part prompt structure for text-to-video
A fill-in template that gives any video model the seven things it needs: subject, action, setting, camera, light, style and sound. Fewer vague words, fewer wasted generations.
Anime style: 2D cel look, limited animation, clean line weight
A filled 7-part prompt for a hand-drawn anime shot: flat cel shading, animation on twos, a held painted background, and the three things the style breaks in current video models.