Cafe Promo Videos With Nano Banana and AI Clone

A cafe promo video can introduce a retail coffee bag, explain takeaway ordering, or direct viewers to brunch booking. Use Nano Banana 2.1 to create the campaign presenter image. Pair it with a separate motion recording in AI Clone.

Choose one visit or purchase task. A coffee-bag message should not turn into a full brunch-menu announcement. The short presenter needs one clear line and a useful next step.

Start with a coffee-retail script

A bag of beans gives the first campaign a defined product and buying route.

Example script: "Want coffee for home? Ask our team about the retail bags and grind options we currently offer."

Use this line only if those options are available. If the cafe sells bags without grinding them, remove the grind reference. Add the exact product size and price in checked caption text.

For brunch, use a different message: "Planning a weekend visit? Check our current brunch menu and booking information before you come."

Record each line as its own performance. One generic motion clip does not automatically carry every new spoken message.

Create a cafe campaign character

Use a clear adult face and clothing that suits the scene without identifying the person as an actual barista.

Prompt: "Create one adult campaign presenter for a cafe promotion. Use a front-facing waist-up composition with a clear face, relaxed expression, and plain neutral clothing. Show a softly lit, simple cafe-inspired background. Keep both eyes and the mouth visible. Leave the hands relaxed and empty. Do not add a staff name, logo, branded cup, food, or text."

Keeping hands empty reduces the number of product details that need to survive motion. Show the actual coffee bag in a separate clip if the campaign requires precise packaging.

Check the face and body proportions. Match the framing to the planned recording. Save the approved image as a campaign reference, separate from real staff photos.

Record the source performance

Film a performer with permission for this use. Use a stable camera and a simple background. Have them say the checked line in one take.

For a retail invitation, use a small gesture and a short pause after the final sentence. Avoid a cup covering the mouth or a large turn away from the camera. Make sure the audio remains clear.

The accepted motion input is an MP4 or MOV between 3 and 20 seconds, up to 1080p and 100 MB. Check those limits before upload.

A spoken line should fit naturally. If it feels rushed, remove secondary details and put them in the caption.

Combine the image and recording

Use the AI Face Swap solution to open the AI Clone workflow. Select the approved presenter image and add the motion clip. Choose the output settings and check the estimate before generating.

A short direction can state: "Preserve the source pacing and keep the presenter front-facing." The direction should support the recorded performance.

Optional voice conversion needs source speech. It changes the voice rather than providing a different script. Listen to the finished audio even when the original recording was clear.

Nano Banana creates the still reference in this process. The video generation comes from the separate AI Clone step.

Check the finished retail message

Play the full clip. Listen for the coffee name, if spoken, and check that the purchase instruction is clear. Inspect the face when the person gestures.

Example caption: "Our current retail coffee bags are available at the counter. Ask about the options we offer. See the bag label for weight and product details."

For a brunch clip, check the menu link and booking wording. Do not claim there are free tables unless that statement has been checked for the publishing time.

Use actual venue footage when the message shows where guests should arrive. A generated cafe background does not provide a record of your seating or entrance.

Pair the opener with actual cafe footage

A presenter can introduce the retail task. A real close-up should show the bag, label, and collection point. For brunch, use the actual dish and serving.

The cafe and brunch UGC video guide includes shot sequences for those campaigns. Use it when you need an assembled video with more than one clip.

For still-image planning, use the coffee and brunch photography guide. Keep product references accurate across the image and video assets.

Reuse the reference with a new performance

A second clip can explain takeaway collection. A third can point to brunch booking. Keep the approved character image fixed while changing the source line and caption.

Name each final clip by its task. A retail opener belongs with product footage. A brunch opener belongs with the current menu campaign. This helps the team avoid an unrelated opening when assembling later videos.

Check time-limited details before reuse. A spoken seasonal special needs a new version when the offer changes.

FAQ

Should I put the coffee bag in the presenter's hands?

Use a separate product clip for the first campaign. Product handling adds packaging and hand details that need extra review.

Can I call the generated presenter our barista?

Use a real staff member for that introduction. A campaign presenter can explain the cafe's offer without claiming a staff identity.

Where can I check the general workflow?

Read the AI Clone input guide and the Nano Banana business guide. Finish one complete message before adding more presenter variants.