How to Make a Wassup in a Minute AI Video From 3 Photos
What’s new on this page
- — Published with our first tested three-person run: settings, frame breakdown, photo placement and the full prompt.
We made our Wassup in a Minute AI video with three costumed characters: a red-haired girl, a blonde girl and a dark-haired boy in a long red robe. One run, about five minutes, and all three kept their own faces and robes from the head grab at the start to the wide freestyle at the end.
Wassup in a Minute trend hillside trio dance
Wassup in a Minute AI video result
What Happens in a Wassup in a Minute AI Video?
A Wassup in a Minute AI video is the real-people version of the trend: three dancers on a misty lakeside hill, cut into four shots on the beat of the Jersey club remix of Drake and Jhené Aiko’s “From Time.” It is not the anime edit, where a cartoon of you sways on a white background.

| Time | What happens | Who to watch |
|---|---|---|
| 0–4s | All three grab their heads on the beat | The right dancer is closest to the camera |
| 4–7s | Close-up while the other two dance behind | The middle dancer |
| 7–11s | The trio walks toward the camera side by side | Everyone, full body |
| 11–15s | Wide freestyle across the hill | Small figures, so faces need to be sharp |
How Do I Make a Wassup in a Minute AI Video? (4 Steps)
- Open the template. Go to the Wassup in a Minute AI trend page and play the example once with sound so you know where the close-up lands.
- Add three photos. Dancer 1 opens on the left, Dancer 2 is in the middle and gets the close-up, Dancer 3 opens on the right. One person per photo, knees up or full body.
- Check the cost and tap Generate. The button shows 385 credits. Our run finished in about 5 minutes; you can leave the page and come back.
- Download from My Videos. Watch it through the walk-up and the wide shot, then download the watermark-free MP4.

Who Goes Where in the Wassup in a Minute Dance?
In the Wassup in a Minute dance, the middle slot is the lead: Dancer 2 gets the only close-up, about three seconds where their face fills a third of the frame. Give it to whoever started the group chat, the birthday person, or the friend with the sharpest photo.

- Dancer 1 (left): starts at the back of the first shot and ends on the left of the walk-up.
- Dancer 2 (middle): the close-up, then the center of the walk-up.
- Dancer 3 (right): the biggest figure in the opening shot, closest to the lens.
The three positions don’t change identity during the video. In our run, nobody ended up in someone else’s robe, even when the dancers spread out across the hill in the last shot.
Which Photos Work for a Wassup in a Minute AI Video?
Sharp, front-facing photos of one person each work best for a Wassup in a Minute AI video, because two of the four shots are wide and every face is small. Each dancer wears what they wear in their photo, so the outfit in the picture is the outfit in the dance.
- Knees up or full body, so the walk-up and freestyle have a body and outfit to work with.
- Three people who look different: different hair or clothing colors make the trio easier to tell apart.
- No sunglasses, hats over the eyes or hands on the face.
- Crop group shots into three single photos, and skip faces that blur after cropping.
Short a dancer? All three slots need a photo, and we only tested three different people. For two of you, the Ice Ice Baby duo dance or the Iconic By Mistake duet take two photos.
The Exact Settings and Prompt We Used
Behind the one-tap template is a video-to-video run on Wan 3.0: the hillside clip sets the moves, cuts and camera, and the three photos set who is dancing. These were the settings on November 15, 2026.
| Setting | Value |
|---|---|
| Model | Wan 3.0 |
| Resolution and length | 480p · 15 seconds · 3:2 wide (784 × 522) |
| Inputs | 3 reference photos + the trio dance clip |
| Audio | On, the trend remix |
| Cost and time | 385 credits · about 5 minutes · 1 run, no retries |

This is the prompt we used. It points at each dancer by the clothes they wear in the dance clip, not by where they stand, so identities hold when the trio moves. It never describes the people in the photos, so it works for any three photos.
Replace the three people in the source video with the characters from the reference images: - the person in light gray coat becomes the character from image 1; - the person in blue outfit becomes the character from image 2; - the person in dark clothes becomes the character from image 3. Track them through the whole video: when they move or swap positions, the same character stays on the same person and identities never switch. Each character's face, hairstyle and outfit come entirely from their reference image; the source clothing is only used to identify who is who and must not appear in the result. Keep everything else from the source unchanged: the exact movements, position changes, poses, timing, camera motion, framing, background and lighting. Faces stay consistent and recognizable in every frame, with realistic skin, natural fabric movement, and no extra people or objects.
You don’t need any of this to make one: the Wassup in a Minute AI template already has the clip, the prompt and the settings.
Wassup in a Minute AI Video FAQ
What is the Wassup in a Minute trend?
The Wassup in a Minute trend is a TikTok trend set to a Jersey club remix of “From Time” by Drake and Jhené Aiko. It started on October 23, 2026 with a Blue Lock anime edit by @ristyisvalid (2.6 million+ views in about a week, per Know Your Meme), then spread to real people dancing it in groups.
How much does a Wassup in a Minute AI video cost? Is it free?
A Wassup in a Minute AI video costs 385 credits, about $4.27 from the $5.99 starter pack of 540 credits, with no subscription. The 75 free signup credits aren’t enough for it. See pricing for larger packs; failed runs are refunded automatically.
Can I make it with only one or two photos?
No. All three dancer slots need a photo, and we only tested three different people. With two people, use a duo template such as the Ice Ice Baby duo dance.
Is the Wassup in a Minute AI video vertical?
No. The export is a wide 3:2 frame at 480p, 15 seconds. Post it as is on YouTube or a feed, or crop to the middle dancer for TikTok and Reels.
Does the video have the song?
Yes. The video comes with the Jersey club remix of “From Time” already on it, so you don’t need to add the sound in CapCut or TikTok.
Why don’t the dancers look like our photos?
Usually the faces are too small or blurry, often from a cropped group shot. Use a sharp, front-facing photo for each person, especially the middle dancer, and run the template again.