Updated
A CapCut template and a photo-to-video creator solve different parts of the job. In an editor, you start with footage or photos you already have and assemble the timing, captions and sound. That makes sense if you can film the check, the wallet close-up and a walk to the kitchen. You get to choose how long the reaction lasts and exactly when the cut happens. Look in CapCut for templates available to your account and region. This page offers an independent browser creator and a workflow for making the scene from a portrait.
If all you have is a still photo, use the workbench to generate a take around that person. You can then bring the video into CapCut or another editor to trim the opening, add a caption or adjust the framing. Check the sponge shot after cropping and keep it visible under any text. Add music in the destination app if the sound is available for your intended use, and label the finished clip as AI-generated when you post.