Example portrait of a woman with dark curly hair wearing a white sleeveless top
Photo 1 · Opening foreground
Example portrait of a blond man wearing a black T-shirt in a kitchen
Photo 2 · Opening background
Seedance 2.5

Your photo is where the story starts

EFFECT PREVIEW

This is an effect preview. You can check progress and watch your finished video in My Videos.

Use this template

When Two Legends Try to Make Coffee Video

Restoring draft…

Photos on your phone?
Output quality
Estimated time
5–15 minutes
Credit cost
Loading…

Credits are automatically returned if generation fails due to a technical problem.

Your finished MP4 will be saved in My Videos, where you can play and download it.

Loading…

Use photos and likenesses you have permission to use.

About this effect

What is When Two Legends Try to Make Coffee?

Upload two person photos and cast both sides of a kitchen disaster. Photo 1 becomes the foreground coffee maker who spills grounds and milk; Photo 2 becomes the helper behind and to the left who pours water and reacts. The template guides a 14-second vertical comedy.

What your photos control
Photo 1 controls the foreground person on the right, holding the spoon and coffee jar and pouring milk at the end. Photo 2 controls the helper behind and to the left, holding the kettle. Each photo guides its own character’s appearance and outfit. The preview is a generated example using the two portraits shown here.
Movement and background
AI generates a new clip from the example’s routine and setting. Backgrounds, camera movement, expressions and occlusion may vary; frame-for-frame matching is not guaranteed.
Kitchen comedyTwo photos, two rolesCoffee and milk mishaps

Photo to video: a paired example

Compare the input photos with their corresponding video to assess the subject’s appearance and movement.

Example portrait of a woman with dark curly hair wearing a white sleeveless top
Photo 1 · Opening foreground
Example portrait of a blond man wearing a black T-shirt in a kitchen
Photo 2 · Opening background
Corresponding video

What happens in this video?

Three frames from this template’s showcase explain the scene and performance.

  1. Woman in white holds a spoon by a red mug with her coffee partner behind
    01 · Opening

    The coffee misses the mug

    The foreground character carefully scoops coffee grounds onto the counter while the partner brings over the kettle.

  2. Coffee maker examines a spoon above the counter beside spilled grounds and a red mug
    02 · Middle

    A second try, the same mistake

    The partner pours water into the red mug. Another spoonful lands on the counter, followed by a confused exchange of looks.

  3. Coffee partner tips a white carton while the woman holds a spoon beside the mug
    03 · Later

    Milk makes the mess bigger

    The foreground character pours milk across the counter, then checks the spoon and mug as the partner reacts.

How to get a better result

Recommended photos

  • Use two sharp, well-lit portraits, with one person in each photo and both faces clearly visible.
  • Keep each person’s shoulders, arms and desired outfit visible. Distinct hairstyles and clothing can help keep the two roles apart.
  • Even lighting and clear detail
  • A subject outline distinct from the background

Try to avoid

  • Collages, chat interfaces or watermarked screenshots
  • Avoid group photos, covered faces, strong filters and photos with a phone blocking the torso.
  • Avoid tight face-only crops and large objects covering the arms. The kitchen props come from the template, not from your photo.
  • Blur, darkness or heavy filters

If the result needs improvement

The appearance looks different
Use sharp single-person portraits with unobstructed faces and visible outfits. If one character changes while turning, replace the photo in that character’s slot. The prompt keeps the two identities separate, but exact likeness is not guaranteed.
Limbs or props connect awkwardly
Keep both people’s shoulders and arms visible in their respective photos. The spoon, jar, kettle and milk jug are template props; AI may still distort grips or splashes when the hands overlap.
Roles or positions get mixed up
Check the upload order: Photo 1 is the foreground spoon-and-jar character; Photo 2 is the helper with the kettle behind and to the left. Use one person per photo, not a group shot or collage. Select each portrait in its intended slot before generating.
The movement or performance differs
The AI generates a new scene rather than editing the original frames. Faces, hands, liquid splashes and the timing of small props can vary, so an exact match to the reference is not guaranteed.
The task reports a generation failure
Check the task status in My Videos first. Technical failures return deducted credits automatically; a successful video that does not meet personal expectations is a different situation. Each new generation costs credits, so review the refund policy before retrying.
View refund policy ↗
Use this template

How to Make a When Two Legends Try to Make Coffee Video

  1. Step 01

    Upload your photos

    Upload two separate person photos, following the role order.

  2. Step 02

    Generate your video

    Choose 480p / 720p / 1080p, confirm the credits, and submit. The current output is 14 seconds in 9:16. You can leave the page while it processes, then check My Videos when ready.

  3. Step 03

    Download and share

    When ready, play and download the MP4 from My Videos and save a copy to your device.

    My Videos

FAQ

How many photos do I need, and what kind works best?

Upload two separate single-person photos, one for each role. Use clear faces in even light, with the upper body and outfit visible. Avoid group photos, strong filters and objects covering the arms.

How are the two photos assigned to the characters?

Photo 1 is the foreground person on the right who holds the spoon and coffee jar and pours milk at the end. Photo 2 is the helper behind and to the left who uses the kettle. Choose the person for each slot before generating.

Will both people keep the clothes from their photos?

The prompt asks each character to keep the hairstyle, body shape, visible outfit and accessories from their own photo throughout the scene. It does not force the original white printed shirt or gray tank top. AI-generated details can still vary.

Does the video include the original sound?

Yes. The platform combines the generated picture with this template’s original audio at its original speed. It does not clone your voice, add new lines or offer a different song in this effect.

Is it free, and how many credits does it cost?

Watching the reference is free. A 14-second generation costs 50 credits at 480p, 100 at 720p, or 240 at 1080p. The selected quality and credit cost are shown before submission.Pricing ↗

How long is the clip, and when can I download it?

The current output is an MP4 lasting 14 seconds in 9:16, with 480p / 720p / 1080p quality options. Check the current credit quote before generating.

What if the hands, spoon or milk look wrong?

Try clearer portraits with each person’s shoulders and arms visible and no large objects blocking the body. Small utensils and liquid motion can be imperfect. Generating another version is a new paid task; technical failures automatically return the deducted credits.View refund policy ↗

Can I download and share the finished coffee video?

The completed MP4 appears in My Videos for preview and download. The site adds no extra watermark. Before sharing, make sure you have permission to use the uploaded likeness and the included audio.View refund policy ↗