Wassup in a Minute AI Hillside Video Generator
One photo puts you in the middle of the foggy hillside clip and gives you the close-up. Two more bring friends to your left and right, each in the clothes their photo shows.
Make yours
120 credits
Your photos
1 needed
Photo 1 is required and takes the middle place and the close-up. The other two places are optional friends for the left and the right spots, and a place with no photo goes to someone the model invents. One consenting adult per photo, face lit, wearing what they should wear on screen.
Soundtrack
Keeps the clip’s own audio under your video.
What you get
Fixed
- Length
- 15 s
- Format
- 4:3 landscape
- Sound
- Clip audio
- Ready in
- A few minutes
- Cost
- 120 credits 1 video
Sign in with Google at the next step.
Failed renders are refunded automatically. You can leave the page while it renders.
By making a video, you confirm everyone in the photos agreed to it. Terms
Short answer: Wassup in a Minute AI is the hillside branch of a TikTok trend in which three people saunter at the camera on a wet green hill, clutch their heads with both hands, goof off into the lens and then dance away down the grass, under a sped-up jersey club flip of a 2013 song whose opening greeting lands on most ears as "wassup, been a minute". Genvima films the same 15 seconds again with the people in your photos: the first photo is required and gets the middle place plus the close-up, while the second and third are optional friends for the left and the right spots, 3 photos at most. You end up with a 4:3 MP4 at 480p carrying the trend remix, or silent if you flip the sound off, with no watermark on it, a few minutes after you press the button. One clip costs 120 credits, which the $9.99 credit pack pays for, and the effect has no free version. Genvima has no ties to CapCut, to the account that posted the hillside template, to the actors whose clip it uses or to the musicians behind the song.
How to make a Wassup in a Minute AI video on Genvima
The maker sits at the top of this page. Nothing is typed: the shots, the timing and the hill are already set.
- 1
Put the star in the middle slot
Slot one belongs to whoever should carry the clip. That person walks in the centre of the group and is alone on screen for the long close-up, so pick a lit photo of one adult looking at the camera in the clothes they want on screen.
- 2
Fill the side slots, or leave them
Slot two is the place on the left and slot three the place on the right. Any slot you skip is taken by a person the model dreams up, and skipping one costs no less and no more.
- 3
Decide about the music, then start
Leave the trend sound on or turn it off, then hit Remake this. A first render asks you to sign in with Google, after which your photos come back and the job starts on this page. The price in credits is printed on the button.
- 4
Pick up the file
The 15 second MP4 shows up under the maker and in Assets within a few minutes, and nothing breaks if you close the tab. Switch on the AI label of whichever app you post it to.
What your photos decide, and what the hill keeps
The middle place gets the camera
Photo one leads the group downhill, holds their head with everyone else, and then fills the frame alone from the waist up: grinning, hands rolling around each other, both thumbs swung back at their own chest.
Friends on the left and the right
Photo two walks on the left, a pace behind the leader. Photo three starts nearest the lens on the right. Both dance in the background of the close-up and take the outer spots in the row and the final run.
Everyone wears their own photo
Faces, hair, build and clothing all come out of the pictures you upload, in the same colours, from the first step to the last. Caps, hats and sunglasses appear only if a photo already has them.
Empty places are cast for you
Upload one photo and you still get a trio. The two beside you are invented people who resemble nobody in your pictures and turn up in clothes of their own. One photo is never cloned into three of you.
The weather and the four shots never move
The flat grey daylight, the lake lost in fog below, the second slope with its trees, the phone-video look and the order of the four shots stay the same in every 15 second render.
Trend sound or a silent file
The picture is rendered without audio and the trend remix is laid underneath afterwards, about as long as the clip. Turn the sound off instead and you get a silent MP4 to pair with a track inside the app you post from.
Wassup in a Minute AI with three photos and with one
Two of our own renders, posted here as they came out of the model. Every person in them is a fictional adult.
Three photos: all three places cast
One photo: two friends made up for her
Wassup in a Minute AI at a glance
- Photos
- 1 to 3, one adult in each
- Places
- Middle with the close-up, a friend left, a friend right
- Empty places
- Filled by invented friends
- Clothes
- Whatever each photo shows
- Clip
- 15 seconds, 4:3, 480p, MP4
- Sound
- The trend remix, or silent
- Setting
- A green hill over a foggy lake, then a slope with trees
- Trend
- On TikTok since November 12, 2026
- Price
- 120 credits a clip; the $9.99 pack covers one
- Render time
- A few minutes
- Watermark
- None
- Made with
- Seedance 2.0 Mini
Who makes a Wassup in a Minute AI video
The group chat that went quiet
That is the joke the sound carries: three friends who have not spoken in months strolling back in as if nothing happened. One photo each and the reunion is on everyone’s timeline the same evening.
Reunions and homecomings
Classmates meeting after years, a sibling back from abroad, a friend home on leave. The shrug at the end does the talking better than a caption can.
Teams announcing they are back
A band off tour, a club before the new season, a shop reopening. Three staff photos, work clothes kept, and the grey sky makes it funnier than a polished advert.
Couples with one spare friend
Two photos put the two of you in the middle and on a side, and the model supplies the third body so the row still works.
Solo posters
One picture is plenty. You keep the middle and the close-up, two invented friends mirror your moves, and nobody has to send you a photo first.
Family group videos
Parents, cousins and in-laws read as a trio easily, because the clip needs no rehearsal and no dancing skill at all: a walk, hands on heads and a shrug.
Where the Wassup in a Minute AI trend comes from
The name comes from the first words of a jersey club remix, sped up, of a 2013 Drake and Jhené Aiko track called "From Time". The greeting is slurred enough that people write it down as both "wassup in a minute" and "wassup, been a minute", and the remix itself has been circulating since January 2026.
It became a trend in late October 2026 with anime edits, one drawn character swaying in after another. Then on November 12, 2026 the TikTok account @dancevault14 published a CapCut template that moved the joke outdoors. The footage is three actors on a grassy hill above a fogged-in lake, walking at the camera in casual shirts, grabbing their heads, mugging in close-up and skipping off down a slope. By November 14 the post had been played roughly 3.8 million times, and the template is what most of the remakes you see were built in.
Genvima rebuilds those 15 seconds from nothing with the people you upload. No actor, no frame and no still from the original post ends up in your file, and the page shows none of it either. The site is independent of CapCut, of @dancevault14, of the actors in that clip and of the musicians whose song the remix is built on.
The fifteen seconds, shot by shot
Four shots, cut in the same order every time. Knowing them helps you work out who should go in which slot.
- 0 to 3.6 s, the walk in. The three come down a green hillside toward the lens, the lake grey and foggy behind them. The middle one leads, the left one trails half a step, the right one is closest to the camera. Near the end of the shot all three take their heads in both hands and shake them.
- 3.6 to 7.25 s, the close-up. The person from photo one fills the frame from the waist up, right at the glass, grinning, hands rolling over each other, then both thumbs jabbed back at their own chest. The other two keep dancing far behind, small and out of focus.
- 7.25 to 10.75 s, the row. All three walk in a line at the camera, the left friend, then the middle, then the right friend. They open their palms in a long shrug and bounce at the knees on the beat.
- 10.75 to 15 s, down the slope. A wide shot on a second slope with trees. The three spread out and skip, hop and flap their way down the grass until the clip ends.
Small gestures land differently from one render to the next, but the shots, their order and the 15 seconds do not change.
Who ends up where
- Photo one, the middle. Required. Leads the walk, is in the middle of the row and is the only person in the close-up. Roughly four of the fifteen seconds belong to this face alone, so give it your sharpest picture.
- Photo two, the left. Optional. Walks a step behind at the start, dances in the background of the close-up, holds the left end of the row and the left side of the run downhill.
- Photo three, the right. Optional. Starts nearest the lens, which makes this the second most visible place, and then holds the right end of the row.
Slots are not swapped around by the model, so whoever should get the spotlight goes in slot one. The price is identical whether you fill one slot or all three.
What to upload, and what you will be wearing
- The clothes in the photo are the costume. Pick each picture for the outfit as much as for the face. Something with colour reads well against a grey sky and wet grass.
- Waist up or knees up is enough. When the legs are outside the frame, the render adds plain trousers and shoes that suit the top half.
- One adult, face lit and unobscured. No sunglasses, no mask, no heavy filter, nobody else in the shot. Crop a group picture into separate photos before you upload.
- Make the three distinguishable. Different hair and different colours help, because the first shot is quick and the three of you are side by side.
Every face in your photos has to belong to a consenting adult. Public figures and children are not accepted, and the effect is built for people, not for pets, drawings or game characters.
One photo, two or three
- One photo. You take the middle and the close-up, and two friends are invented for your sides. They look like nobody you uploaded, and your face is not duplicated onto their bodies.
- Two photos. You and one real friend, in whichever of the two side places you filled; the other place is an invented friend.
- Three photos. Everyone on screen is someone you uploaded. This is the version most posts use, and the one in the clip at the top of this page.
Those three cost the same. For a band of five there is Tiny Desk AI, for a trio in a glossy music video there is No Scrubs AI, and every video model we run is listed on the AI video maker page.
How close your clip stays to the hillside post
Kept: the four shots and their order, the timing, the green hill above the fogged lake, the second slope with trees, the flat overcast light, the hands on the heads, the thumbs in the close-up, the shrug and the skip down the grass.
Changed on purpose: the people, who come from your photos and keep their own clothes; the friends in places you left empty, who are invented; and the length, which is the full fifteen seconds rather than the post’s fourteen and a bit.
Changed because a model is not a copier: how far the background dancers are from the camera moves around a little, the fog over the lake is thicker in some renders than others, and the last shot can wander off the exact line down the slope.
Never included: the three actors from the template, their show, and any footage, audio stem or still lifted out of the original post. The remix under your file is the trend sound, laid on after the picture is finished.
Why the clip is 4:3, and how to post it
The hillside template is 4:3, so the remakes are too, and a vertical crop would shove the two friends at the sides out of the row. We keep the shape the trend is recognised by.
On TikTok, Reels and Shorts a squarish clip plays in the middle of the screen with a dark band above and below it, which is exactly how the posts in this trend look. Plenty of people write their caption into that band and say who is who. If an app mutes the audio you uploaded, render with the sound switched off and add the trend remix from the library inside the app.
Price, render time and the file you get
A Wassup in a Minute AI clip is 120 credits, with one photo or with three. The $9.99 credit pack buys exactly one, and the plans and bigger packs on the pricing page bring the cost of a clip down. There is no free version of the effect, because every render is paid compute working on your pictures.
Seedance 2.0 Mini does the filming and takes a few minutes. What lands in Assets is a 15 second 4:3 MP4 at 480p, free of watermarks and logos, yours to download as often as you want. If a model fails or refuses the request, the credits for that clip go back to your balance automatically.
The same model is also open as a plain generator, prompt and all, on the Seedance 2.0 page, if you want to try a scene of your own instead of this one.
FAQ
What is Wassup in a Minute AI?
A TikTok trend from November 2026, in its hillside form: three people walk at the camera on a foggy green hill, hold their heads, one of them goofs around in close-up with both thumbs pointed at himself, and all three skip off down a slope. Genvima’s effect films that 15 second scene again with the faces in your photos.
What does "wassup in a minute" mean, and where is the sound from?
It is how people hear the opening greeting of a sped-up jersey club remix of a 2013 Drake and Jhené Aiko song. Some write it "wassup, been a minute", which is why both spellings are searched. The sound became a trend in late October 2026 with anime edits, and the hillside version followed on November 12.
How many photos does it take?
One is enough. The middle place is required; the left and the right are optional, and any place you leave open is taken by a friend the model invents. You can upload up to 3.
Which photo gets which place?
Photo one is in the middle, leads the walk and is the only one in the close-up with the thumbs. Photo two is on the left, half a step back at the start. Photo three stands on the right and begins closest to the lens. The model does not shuffle them.
Can I make it with only my own photo?
Yes, and it is the most common way people use this effect. You keep the middle place and the close-up, and two invented friends walk and dance beside you.
Will everyone keep their own clothes?
Yes. Each person appears in the outfit from their own photo, in the same colours. Nothing is restyled to match the actors in the template, and hats or sunglasses show up only if a photo has them.
Are the actors from the original clip in my video?
No. The scene is generated from scratch with your people, so nobody from the template post appears and no frame of it is used. Photos of famous people are not accepted either.
Is the song on the video?
With the trend sound on, the remix from the post is laid under the picture for about 15 seconds. Switch it off and the MP4 is silent, so you can attach the audio inside TikTok or Instagram instead.
Why is it 4:3 instead of a vertical clip?
Because the template this version grew out of is, and a vertical crop would cut the friends at the sides out of the row. On a phone it plays in the middle of the screen with a dark band top and bottom, which is how the trend posts look.
How much does a Wassup in a Minute AI video cost?
120 credits, no matter how many photos you upload. The $9.99 credit pack covers one clip, and the [pricing](/pricing) page lists the plans and the larger packs.
How long does the render take?
A few minutes for 15 seconds of video. Leaving the page is fine: the finished clip waits for you in Assets.
Does the MP4 have a watermark?
No. There is no logo, no badge and no text burnt into the picture. Do switch on the AI label of the app you post it to.
Why was my Wassup in a Minute AI video not made?
Usually the model’s safety check refused one of the photos before filming started. It sometimes decides a picture is a well-known real person when it is not, and then nothing is rendered. The 120 credits land back in your balance by themselves. Upload a different picture of that person for the place that failed: another angle, even light, one person in frame.
Can I make the anime version of the trend?
Not with this effect. It builds the live-action hillside clip with real-looking adults from photos. An anime edit of the same sound is a different job, which you would prompt yourself on a general model.
Can I use a cartoon, a game character or my dog?
No. The effect is made to carry real adults from their photos through the hillside walk. Drawings, game characters and animals are outside what it does, and well-known characters belong to their owners, so upload a photo of a consenting adult. Pictures of children or of famous people are refused.
How is this different from the CapCut template?
A CapCut template runs inside the CapCut app and drops your pictures into the existing footage. Here the browser does the work and the scene is filmed again, so each person keeps their face, hair, build and clothes, the three places come from three separate photos, and what you download is a plain MP4 you can post anywhere.
Which AI model makes the video?
Seedance 2.0 Mini re-films the hillside scene with your faces. The same model is open as a general video generator on the [Seedance 2.0](/video/seedance-2-0) page.
Is Wassup in a Minute AI free on Genvima?
No. There is no free version of the Wassup in a Minute AI effect: it works from your photos on a paid model. Genvima's free Basic engine (one free video and three free images a day) makes clips and pictures from a written prompt only, so it cannot use your photos. One clip is 120 credits.
What happens if the render fails?
If a model fails or refuses the request, the credits for that clip go back to your balance automatically.
Keep exploring
- No Scrubs AIYou and up to two friends in the silver-room music video, each in your own clothes.Open
- Tiny Desk AIYou on lead vocals in the viral desk concert, your friends as the band.Open
- AI Video MakerEvery way to make a video and all 13 video models.Open
- Seedance 2.0ByteDance’s video model with sound: multi-shot clips up to 15 seconds, from text, a photo or reference images.Open
- PricingPlans and credit packs. One balance pays for every video and image model.Open