Small Shop Walkthrough | Follow-Along Exercise

できあがるもの

A storyboard or production plan, an asset list and a check log; you'll need to produce the final video yourself.

必要なもの

• A chat, image or video tool suited to the task (PromptKite does not provide model credits)
• Your own input materials and a folder for saving results

手順

1. Define the inputs for this exercise

   The demo inputs for this exercise are: Topic: an independent coffee shop; Duration: 30 seconds. First confirm whether these conditions fit your situation; replace “paste your material” in the example with real material. Write the goal as a deliverable you can check against.

2. Run it once for your scenario

   First give the example prompt to a chat tool to get a storyboard or production plan. After checking the timing, mark each shot as live footage, still-image editing or video generation, then prepare assets; copying once won't produce a finished video. Focus of this task: design five shots with a clear spatial direction, from entering the door to the seating, the counter, the products and leaving, without arbitrarily mirroring the space.

3. Check against the criteria and revise

   Check each shot against “Spatial direction, accurate information and permission from people on camera; check whether the duration and shots are achievable.” If a movement is hard to achieve, drop secondary camera moves first and keep one main action; if the timing is off, fix the schedule before making assets, rather than padding with unrelated shots.

4. Save and review

   Save the final result, the prompt, the source of your input material and one reason for a change. Name files with the date plus the task name; save reusable versions to your PromptKite Prompt Pocket. Next time, change one condition and try again, noting whether the result still holds.

よくある失敗

• The input is still placeholder text, so the output looks empty — Replace placeholders such as “paste your material” in the example with real material; state clearly that missing facts are unknown instead of asking the model to fill them in.
• The result doesn't meet the standard for this scenario — Check each shot against “Spatial direction, accurate information and permission from people on camera; check whether the duration and shots are achievable.” If a movement is hard to achieve, drop secondary camera moves first and keep one main action; if the timing is off, fix the schedule before making assets, rather than padding with unrelated shots.

練習用テンプレート

Create a video plan around {subject}, with a duration of 30 seconds. Design five shots with a clear spatial direction, from entering the door to the seating, the counter, the products and leaving, without arbitrarily mirroring the space. Use only the address and opening hours provided, avoid close-ups of customers without permission, and list suggestions for on-site audio and stable shooting. Output an actionable table with shot number, timing, shot size, main action, camera movement, captions or sound, and assets to prepare; for a shoot plan, distinguish shooting time from final video length. Keep only one main motion per generated shot, and describe its start and end states. Don't invent actual shooting or generation results; clearly list any missing reference assets. Finally, provide a pre-publication checklist and a simplified fallback if it doesn't work.