
Prepare the photo
Use one clear adult portrait, preferably showing the upper body.
Photo + motion reference · AI video template

An adult holds a coffee cup while perched on what appears to be a high cafe seat. Another customer arrives and sits beside them, revealing the first adult has mistaken the little table for a seat. They climb down and settle onto the lower seat. This continuous reference is sped up to fit the input limit.
Make my versionChoose a scene, describe it or add a photo, and review the current cost before generating. The videos shown here are samples. · Source: @kkubi99
An adult holds a coffee cup while perched on what appears to be a high cafe seat. Another customer arrives and sits beside them, revealing the first adult has mistaken the little table for a seat. They climb down and settle onto the lower seat. This continuous reference is sped up to fit the input limit.

An adult holds a coffee cup while perched on what appears to be a high cafe seat. Another customer arrives and sits beside them, revealing the first adult has mistaken the little table for a seat. They climb down and settle onto the lower seat. This continuous reference is sped up to fit the input limit.
An adult holds a coffee cup while perched on what appears to be a high cafe seat. Another customer arrives and sits beside them, revealing the first adult has mistaken the little table for a seat. They climb down and settle onto the lower seat. This continuous reference is sped up to fit the input limit.
Replace only the first seated adult with the uploaded adult; preserve the second customer and furniture.
Related searches: Your First Time in a Fancy Cafe AI · First Time Fancy Cafe capcut
Try the generatorThis template sends the selected video as a motion reference. Your photo supplies the replacement identity. AI interpretation can vary; the reference is not a guarantee of the final result.

Use one clear adult portrait, preferably showing the upper body.

An adult holds a coffee cup while perched on what appears to be a high cafe seat. Another customer arrives and sits beside them, revealing the first adult has mistaken the little table for a seat. They climb down and settle onto the lower seat. This continuous reference is sped up to fit the input limit.
Replace only the first seated adult with the uploaded adult; preserve the second customer and furniture.

Use one clear adult portrait, preferably showing the upper body.

Choose a supported duration, ratio and resolution. Estimates update with every selection and include this reference video; actual inputs receive a fresh quote.

Track the task and download its finished video. The reference sample stays separate from your result.
Keep the recognizable action while changing the lead.

Replace only the first seated adult with the uploaded adult; preserve the second customer and furniture.

Add captions after downloading so spelling and timing remain under your control.
Use credits across supported image and video tools.
Payments are processed securely by Stripe. Available methods depend on your country, device and checkout eligibility.
Use one clear adult portrait, preferably showing the upper body.
Make my version