AI Video Shot List Template: Plan a 5-Shot Product Video Before You Generate It
Turning a product description into an AI video is easier when you plan the shots before you write the prompt. This five-shot template gives every frame one job: introduce the product, show a detail, show use, explain the benefit, and end with a clear next step.
Quick answer: An AI video shot list is a short production plan that defines what each shot must communicate before generation. For a product video, start with five shots: hero, detail, use, benefit, and CTA. Keep one camera intention and one viewer takeaway per shot.
Table of Contents
- What an AI video shot list is
- Why plan shots before generating
- The five-shot product video template
- A completed example
- Turn the shot list into prompts
- Review checklist and FAQs
What Is an AI Video Shot List?
An AI video shot list is a production outline for a short video. Instead of giving a model one long paragraph and hoping it finds the structure, you decide the sequence first.
Each line answers five practical questions:
| Field | What to decide | Example |
|---|---|---|
| Shot purpose | Why this moment exists | Make the product recognizable |
| Visual subject | What the viewer must see | A cobalt-blue serum bottle |
| Action | What changes on screen | A hand lifts the bottle |
| Camera | How the viewer sees it | Slow push-in |
| Constraint | What must not change | Label, color, and bottle shape stay fixed |
This is not a screenplay. It is a compact brief that makes a first generation easier to review, revise, and reuse.
Why Plan the Shot List Before You Generate?
AI video generation is most reliable when the instruction has a clear visual priority. A shot list prevents three common problems:
- One overloaded prompt: product demo, lifestyle scene, feature list, transition, and CTA all compete for attention.
- Weak continuity: each generation invents a new product angle, setting, or visual style.
- Unclear revisions: when a clip fails, the team does not know whether to change the product reference, action, camera, or timing.
Planning does not make the process slower. It reduces rework because each output can be judged against an approved purpose.
Summary: Use the brief to decide the message, approved assets to protect brand details, the shot list to define sequence, the prompt to direct each shot, and review to decide what changes next.
The 5-Shot AI Product Video Template
Use the following structure for a 10- to 30-second product video. It works for physical products, apps, packaging, food, cosmetics, and many service offers. Adapt the action and setting; keep the storytelling jobs in order.
| Shot | Goal | Recommended visual direction | Camera guidance | What must stay consistent |
|---|---|---|---|---|
| 1. Hero | Establish the product | Clean product reveal in its strongest setting | Static hold or slow push-in | Shape, logo placement, primary color |
| 2. Detail | Prove quality or design | Macro view of material, texture, interface, or mechanism | Controlled close-up | Surface finish, text, proportions |
| 3. Use | Show context | One believable use action | Medium shot or lateral follow | Product identity and user interaction |
| 4. Benefit | Make the value understandable | Visual result, before/after state, or one concise graphic idea | Hold long enough to read | Claim language and brand tone |
| 5. CTA | Give the viewer a next step | Product with clean negative space for end text | Static centered frame | Final product appearance and safe crop |
Shot 1: The hero shot
The hero shot answers, “What is this?” Keep it simple. Use the best approved product image or a clean visual description, one setting, and one camera direction. A slow push-in works when detail matters; a stable hold works when you need room for a title or later edit.
Prompt starter:
Clean studio hero shot of [product], centered on [surface], [one subtle environmental detail], slow push-in, soft directional light, product silhouette and label remain unchanged, premium but natural commercial look.
Shot 2: The detail shot
The detail shot earns attention by showing one thing that supports quality: a material, texture, interface state, ingredient, or mechanism. Do not combine several close-ups in one generation.
Prompt starter:
Macro close-up of [specific detail], [single visible action such as light moving across the surface or a drop landing], shallow depth of field, gentle focus shift, preserve the exact product texture and color.
Shot 3: The use shot
Show a person only when the action helps explain the product. A use shot should communicate one interaction—opening, applying, placing, tapping, pouring, or carrying—not an entire lifestyle story.
Prompt starter:
Medium shot of [person or hand] using [product] for [one action] in [setting], natural movement, camera follows gently from the side, keep the product geometry and visible branding consistent with the reference.
Shot 4: The benefit shot
The benefit shot translates feature into a visible outcome. For example, show an organized desk after a product is placed, a clean skin-care texture spreading, or an app screen moving from an empty state to a completed task. Do not ask the model to render dense marketing copy; add final legal or promotional text in post-production.
Shot 5: The CTA shot
End on a frame that can carry a clear call to action. Reserve clean space and keep the product large enough for mobile viewers. The job of this shot is not to add a new idea—it is to make the next step obvious.
Completed Example: A 15-Second Skincare Product Video
Here is a compact example for an unbranded facial serum. The same structure can be used for a coffee machine, a shoe, a software feature, or a delivery service.
| Time | Shot | Brief | Prompt focus |
|---|---|---|---|
| 0–3s | Hero | Bottle on a bright stone surface; make the packaging recognizable | Slow push-in; preserve bottle, cap, and label area |
| 3–6s | Detail | A drop of serum reveals the lightweight texture | Macro texture; one drop; no product redesign |
| 6–10s | Use | A hand applies a small amount in a calm bathroom setting | One natural hand action; stable skin tone and bottle |
| 10–13s | Benefit | Fresh, hydrated visual finish without exaggerated claims | Clean result; restrained lighting; no on-screen copy required |
| 13–15s | CTA | Bottle centered with open space beside it | Static end frame; safe crop for a CTA added later |
Notice that each shot has a different storytelling job. The product remains the same, but the camera, action, and viewer takeaway change deliberately.
Turn the Shot List Into an AI Video Prompt
Write one prompt per shot when you need high control. If you are generating a connected sequence, still keep the shot boundaries explicit and test the highest-risk moment first—usually the product detail or human interaction.
Use this simple formula:
[shot purpose] + [subject] + [one visible action] + [setting] + [camera move] + [lighting] + [continuity instruction]
Before generating, prepare an asset pack containing the approved product image, logo treatment, color reference, legal claim guidance, and the final CTA. Teams can move from an approved shot list into a repeatable Seedance 2.5 video workflow for generation, review, and controlled revisions.
If you are starting from a still image, use the source image to lock identity and composition, then let the prompt describe only motion and camera intent. See our guide to turning an image into a video with AI for a fuller image-to-video process.
How to Review the First Generation
Review one shot at a time before assembling the sequence. The most useful question is not “Is this perfect?” It is “Did this shot complete its assigned job without changing something approved?”
AI product video review checklist
- [ ] The product silhouette, colors, packaging, and readable details match the approved asset.
- [ ] Each shot has one clear purpose and no competing action.
- [ ] The camera motion supports the product rather than distracting from it.
- [ ] Human hands, use actions, and physical interactions look believable enough for the intended channel.
- [ ] The benefit is shown visually without unsupported or misleading claims.
- [ ] The CTA frame has enough open space and is safe for mobile crops.
- [ ] Only one variable changes in the next revision: reference, action, camera, lighting, or duration.
For camera-specific wording, use these AI video camera movement examples. When a nearly correct clip needs one controlled change rather than a full restart, review the AI video editing workflow.
FAQ
How many shots should an AI product video have?
Five shots are enough for most short product videos: hero, detail, use, benefit, and CTA. Start there, then add a shot only if it has a distinct communication job.
Should I use one long prompt or a separate prompt for each shot?
Use a separate prompt for each shot when product accuracy, camera control, or revisions matter. A short structured sequence can work for early exploration, but individual shots are easier to diagnose and improve.
What is the best first shot for a product video?
Start with a clean hero shot that makes the product recognizable immediately. Keep the camera movement restrained and protect the details that must remain fixed.
Can this template work for software or service videos?
Yes. Replace the physical product detail with an interface state, result, or interaction. The five storytelling jobs stay the same: introduce, focus, demonstrate, prove value, and invite action.
Build the First Version, Then Improve One Variable
A good shot list gives you a repeatable way to make AI product videos without asking a single generation to solve the entire commercial. Build the simplest version first, compare every shot with the approved brief, and revise only the variable that failed.
Ready to turn a concept into a clip? Start with the text-to-video workspace, or use the shot list above as your production brief before generating.
