FilmotionA product photo of a ceramic mug is a useful starting point for a short video. “Make this feel premium and calming” is not much of a shot brief.
That sentence describes a reaction you want from the viewer. It does not say where the camera sits, what moves or where the light comes from. Those decisions are still wide open.
When I write a product video prompt, I translate the idea into things a camera could record. For a mug on a desk, that means a particular crop, a controlled movement and light that reveals the glaze. Here is how to build that brief without burying it in adjectives.
Start with a frame you can point to
Use one product photo as the visual anchor. For this example, imagine an upright ceramic mug photographed from a front three-quarter angle, with its handle on the right and a plain desk behind it.
Before describing motion, describe the opening frame. Name the product, its position and how much of it should be visible.
“Close shot of the reference mug, fully visible, placed slightly left of centre on the desk, with the handle on the right” is more useful than “beautiful product composition”.
For a vertical video, specify a 9:16 frame. If you intend to add a headline later, describe the empty area as part of the composition: “Leave uncluttered space above the mug.” Do not ask the video generation step to create the headline itself.
The opening frame should already work as a still image. Movement is not a substitute for composition.
Turn mood words into physical choices
Words such as cosy, polished and dramatic can remain as secondary guidance, but they should not carry the prompt.
For a quiet desk scene, translate “calming” into a locked camera, a simple background and soft light from a large window. Translate “premium” into a close view of the ceramic surface, restrained props and a clean separation between the mug and the background.
These are creative choices, not universal definitions. A bright, playful mug might need a different treatment. The useful habit is to explain what your chosen mood looks like in this particular shot.
Compare “cinematic lighting” with “soft window light from frame left, creating a broad highlight on the glaze and a gentle shadow to the right”. The second version gives the light a source, direction and visible effect.
Give each shot one main movement
Camera movement and object movement are separate instructions. “Move closer to the mug” is ambiguous. Does the camera approach it, or does the mug slide across the desk?
Write the subject behaviour explicitly: “The mug remains stationary.” Then describe the camera: “The camera makes a slow, straight push towards the mug.”
A push changes the camera position. A zoom changes the framing without moving the camera. An orbit moves around the subject and reveals different sides. Choose the movement for what it shows, not because the term sounds impressive.
With a single product photo, I favour restrained movement near the supplied viewpoint. A wide orbit asks for surfaces the photo may not show. If the purpose is to reveal the texture of the visible glaze, a modest push is a better brief.
Avoid combining a rotating mug, moving camera, shifting focus and sweeping light in one short shot. You lose a clear visual priority.
Build a three-shot desk sequence
A simple product sequence can move from context to detail to a settled final view. Each shot needs a different job, rather than a different collection of effects.
The opening shot establishes the mug on the desk. Use a medium close view, keep the entire mug visible and hold the camera still. Let the placement and lighting introduce the object.
The detail shot brings attention to the glaze. Use a closer crop from the same side and a slow push towards the visible ceramic surface. Keep the highlight broad enough that the surface remains readable rather than turning into a bright white patch.
The final shot returns to the whole mug with open space above it for text added during editing. A static ending gives the viewer a clear final view and avoids cutting off a movement halfway through.
Generate these as separate shots. That makes the brief for each one simpler and lets you choose their lengths in the edit.
Write the prompt in a consistent order
I use this order: reference subject, framing, subject movement, camera movement, lighting and ending. Here is the detail shot written out:
“Use the supplied ceramic mug photo as the visual reference. Create a vertical 9:16 close shot from the same front three-quarter viewpoint, with the handle on the right. The mug stays stationary on the desk. The camera makes a slow, shallow push towards the visible glazed surface, without orbiting. Soft window light enters from frame left, producing a broad highlight and a gentle shadow on the desk. Keep the background quiet and softly out of focus. Ease the movement to a stop before the shot ends.”
Each sentence controls something visible. There is no need to add “stunning”, “award-winning” or a string of competing style labels.
Revise the instruction that caused the problem
If the result feels too busy, identify what moved unnecessarily. Replace a vague request for “less energy” with “keep the camera locked and the lighting constant”.
If the mug feels flat, revise the light direction rather than asking for “more depth”. If the detail disappears, widen the crop or reduce the push.
The practical test is simple: could someone sketch the frame and draw an arrow showing the movement from your words? If so, you have described a shot, not just an idea.