Tools
The I Love The Smiths CapCut template
CapCut is the default editing app for trend videos. It can cut, caption, and sync the sound, but it cannot replace two people inside the elevator scene.
What CapCut templates do
CapCut templates package cuts, transitions, text, and music. You drop your clips into the slots and the template assembles the edit. They are great for matching a rhythm or a caption style.
Where CapCut stops
A CapCut template does not generate new footage. If you have the original clip, you can cut it, but you cannot put your own faces into the elevator. That requires a video model, not an editor.
The two-photo AI workflow
The AI template does the part CapCut cannot: it casts you and the other person into the scene, then returns a finished 18-second clip. You can still bring that clip into CapCut for captions or a vertical crop.
The practical workflow
Generate the scene here, download the 16:9 MP4, then edit in CapCut if you want a 9:16 crop, captions, or a hook. The AI handles the casting; the editor handles the packaging.
Generate the scene first
Two photos, 18 seconds, about 30 minutes. Failed runs are refunded.
Generate the scene firstFAQ
Is there a CapCut template for this trend?
There are CapCut edits that use the sound, but not a character-swap template. The swap is an AI video task.
Can CapCut swap faces?
CapCut has some AI tools, but it is not a reference-to-video model for a full scene replacement.
What should I use?
Use the AI generator for the scene, then CapCut for captions and the vertical crop.
Keep reading
- The I Love The Smiths Kling templateHow the I Love The Smiths Kling template works, what creators use it for, and where a dedicated two-photo generator is simpler.
- The I Love The Smiths templateHow the I Love The Smiths template works: which photo is the headphone wearer, which one says the line, and what the finished 18-second video keeps.
- How to make an I Love The Smiths videoA step-by-step guide to the I Love The Smiths video: choose two photos, upload them in the right order, generate, and post the 18-second scene.