Grease dance AI turns one photo of you and your partner into a 15-second vertical dance clip. MiniMax H3 follows the reference video’s moves, camera and timing, with instrumental sound and no voice.
1Добавьте своё фото
2Качество и длина480p · 15s · 9:16120 credits
Без подписки · Готово примерно за 3 минуты · При ошибке деньги не списываются
Upload a photo of yourself or adults who have agreed to appear in an AI video.
From the Feed
These four examples show the reference scenes available on this page: a night parking lot duet, a couple turning at home, an indoor duo in shiny pants, and a solo in red heels. Each case describes only what appears in its clip. Grease dance AI uses the selected reference for the movement, camera and timing, then places the people from your uploaded photo into the result.
Make Our Dance ClipThree Steps
Look through the four examples and choose a reference to guide the action, camera and timing. The doorway reference shows one dancer performing solo, and the result for a couple photo with that reference is unspecified.
Add one clear photo that shows the adults you want in the clip. Make sure everyone has agreed to this use. The page does not take a second image or let you set a custom scene.
Press Make Our Dance Clip to start the 15-second 9:16 generation. The video has instrumental sound and no voice. Download it when it is ready, then decide where and how you want to share it.
Example 01 · Parking Lot Duet
Two kicks, joined hands, one spin.
This example shows a man in a leather jacket and a woman in a black top kicking side by side in a parking lot at night. They take hands and spin together. A couple photo dance video uses the reference for the routine and camera, while your uploaded photo provides the people in the new clip.
Example 02 · Living Room Turn
A jacket, fitted pants and a joined turn.
In this example, a couple dances at home. One wears a black off-the-shoulder top and fitted pants; the other wears a leather jacket. They take hands and turn. This Grease dance AI reference keeps the movement recognizable while the photo you upload determines who appears in your result. The example shows how a couple photo dance video can carry a reference routine into a different setting, while the selected clip still controls the action and camera.
Example 03 · Shiny Pants Duo
Glossy trousers meet a plain black shirt.
This indoor example pairs a black off-the-shoulder top and shiny fitted pants with a plain black tee. The couple performs the duo routine together. The visual contrast comes from the clothes shown in the clip; the generator follows the reference action, while the people in your generated video come from your one-photo upload.
Example 04 · Doorway Solo
One dancer poses, then moves alone.
This example is a solo performance in a doorway, with a black off-the-shoulder top, shiny fitted pants and red heels. The dancer poses and moves alone. The Grease dance AI page also follows this displayed reference when generating, so choose a couple photo only if you want the clip to use the people in that upload within the reference action.
Straight Answers
Grease dance AI makes the reference routine clear before you upload: one photo in, one short vertical clip out. The routine guides the result, so the tool has defined limits as well as a simple workflow.
The Trend Explained
Grease dance AI creates a short video from one couple photo and a reference dance clip. MiniMax H3 uses the reference as a guide for the movement, camera and timing, then generates a 15-second vertical result with instrumental sound and no voice. The reference determines what happens in the scene; this page does not offer custom choreography or scene writing. Upload a photo only when everyone shown has agreed to appear. The generated clip can be shared after you download it, subject to your own choice of platform and audience settings.
Upload one image with the adults you want to appear. A clear, forward-facing photo makes it easier to identify who is in the frame. This is a photo-to-video workflow, not a multi-photo editor: the page accepts one photo for each generated clip.
The four references are a parking lot duet, living room turn, shiny pants duo, and doorway solo. The selected reference guides the action, which may be a solo or a duet, along with the camera and pacing. This page does not let you type a new location or request different choreography.
The result is 15 seconds in a 9:16 frame. It includes instrumental sound without a voice, and the tool does not accept a song upload. Add a track separately through the platform where you share the clip, if desired.
Answers about the reference routine, photo upload, sound, clip length and sharing.
Make Our Dance ClipGrease dance AI uses one couple photo to create a 15-second vertical dance video. MiniMax H3 follows the reference clip’s movements, camera and timing, with instrumental sound and no voice. The reference guides the action; the uploaded photo supplies the people.
Choose one displayed reference clip, upload one photo of the consenting adults who should appear, and generate the video. The reference determines the dance and camera, so you cannot specify a different routine or custom location. The result is a 15-second 9:16 clip. Grease dance AI uses the selected reference to guide the movement while the uploaded photo supplies the people.
You need one photo for each clip. Include both adults in the same image if you want a couple result, and choose a clear photo where they are visible. The page does not accept separate images for each person.
The clip includes instrumental sound but no voice. You cannot upload your own song to this tool. If you want a particular track with your post, add it separately using the sharing platform’s available audio options.
No. The selected reference sets the movement, camera and timing, and the page does not let you enter a custom scene. The four examples are a parking lot duet, living room turn, shiny pants duo, and doorway solo; the solo reference shows one dancer, and the result for a couple photo is not specified.
Each result is 15 seconds in a vertical 9:16 format. That gives you a short clip built around the reference routine, rather than a longer performance or an editable sequence of separate shots.
Use only a photo of yourself or adults who have agreed to appear in an AI video. Ask your partner before uploading their image, and consider who may see the result before sharing it publicly.
Clips made without a subscription can appear in the public Explore feed on Ricebowl AI. Do not upload a photo if you or the other adults would not be comfortable with that possibility. Check the current account and privacy information before generating.
One 15-second clip costs {credits:768p-15} credits. You can also buy a one-time pack or review the available plans and current prices on the pricing page before choosing how to pay.
Select a reference that shows the kind of movement you want, upload one clear photo of the consenting adults, then generate and download the 15-second vertical clip. The reference supplies the movement, camera and timing; the output has instrumental sound and no voice. For a walkthrough of the broader process, read the [guide to making an AI trend video](/hub/how-to-do-the-ai-trend).
Explore More
Grease Dance AI Clip
Choose a reference, upload one consenting couple photo, and generate a 15-second vertical routine with instrumental sound.
Make Our Dance ClipOne photo • 15 seconds • 9:16 vertical
Put Your Couple Photo Into a
Make Our Dance Clip