This exercise is about morning coffee. Prepare four clips and arrange them into an opening, explanation, experience, and ending. Move from simply joining generated footage to designing how your message comes across through editing.

Choose a model that supports 15-second generation. If a model's maximum length is five or 10 seconds, combine shorter clips to create each 15-second section. Four full clips add up to 60 seconds, but removing failed sections and unnecessary pauses shortens the finished video.

What to prepare first

  • Prepare all four clips in vertical 9:16, using the same mug, color palette, and time of day. Use a shared reference image if the model supports one.
  • Name the files 01_hook.mp4, 02_detail.mp4, 03_feeling.mp4, and 04_ending.mp4, and save them so their order is clear.
  • Choose a common frame rate. For example, if the footage is 30 fps, use 30 fps as the basis for editing and export too.
  • Prepare a script with short lines and background music licensed for your intended social platform and use.

Your production exercise

01 · 15s

Opening: one shot that makes people want to watch

Show a close-up of the mug by the window. Make the topic clear in the first one or two seconds.

01_hook.mp4
02 · 15s

Explanation: show actions and details

Show coffee being poured. Reject sections where the liquid or hands look unnatural.

02_detail.mp4
03 · 15s

Experience: a scene that conveys a feeling

Show steam and soft light. Match the color palette and mug shape to the previous shot.

03_feeling.mp4
04 · 15s

Ending: a final impression and message

Show a wider shot of the mug and add the text “Make your morning minute a little richer” during editing.

04_ending.mp4
Example timeline structure

An example with four 15-second clips. After removing unwanted sections, the finished video will be around 45–60 seconds.

Video
0115s0215s0315s0415s
Captions and titles
Captions and titles
Narration
Narration
Background music
Background music

Toggle the layers to see the roles of video, voice, and captions.

  • First keep only the good sections of each clip and arrange the story in order. Add captions and decoration afterward.
  • Use hard cuts as the default. Try a short transition only where you want to connect similar compositions smoothly.
  • Keeping voice or background music continuous across cuts can help bring separately generated clips into one flow.
  • Limit captions to one point at a time, aiming for around two short lines. Avoid the top and bottom edges where social media interface elements appear.

Choose an editor

Combine 15-second clips in CapCut on a smartphone

Edit the four clips saved on your device in a new project. Decide the order and length of the visuals first, then add voice, captions, and background music.

Production steps

Combine 15-second clips in Premiere on a PC

Place four clips in a vertical sequence and build the edit with separate tracks for video, ambient sound, narration, and background music.

Production steps

Check the result

  • The topic is clear in the first one or two seconds.
  • No distorted frames or unnatural movement remain.
  • The mug, color palette, and brightness do not change drastically between shots.
  • The voice is intelligible, with no abrupt changes in music or ambient sound.
  • Captions and the final message are not hidden by the posting interface.
  • You have played the exported video from beginning to end and checked its finished length.