Make your quiet on the creek dance video from one photo. MiniMax H3 follows the reference clip’s moves, camera and timing to put you in its 15-second vertical performance.
1Add your photo
2Quality & length480p · 15s · 9:16120 credits
No subscription · Ready in about 3 minutes · Not charged if it fails
Upload a photo of yourself or an adult who has agreed to its use.
From the Feed
These four clips show distinct ways to perform the dance: a close selfie with a shush, a seated car take, a waist-up bounce in a pink top and a full-body denim look. Each example is a reference for the generated movement and camera. Select the composition that suits your photo, then let the clip guide the performance.
Make My Dance ClipThree Steps
Pick the selfie, car-seat, pink-top or full-body denim example. The selected clip determines the movement, camera framing and timing, so choose the composition closest to the performance you want.
Add one clear photo of yourself or a consenting adult. Use a visible face and good light. This page accepts one photo for the person; it does not take a separate dance video or a custom scene prompt.
Start generation to create a 15-second vertical 9:16 video with instrumental sound and no voice. Review the result, then download it and add any permitted audio in your posting app if desired.
Reference 01 · Shush Selfie
A head tilt leads into the sway.
This reference shows a woman with glasses and curly hair filming a close selfie. She puts a finger to her lips, tilts her head and sways. Choose this framing when you want the face and shush gesture close to the lens; the generated performance follows the clip’s movement and camera.
Reference 02 · Car Seat
Half-body framing with a hand over the mouth.
The reference shows a woman with long straight hair seated in a car. The view includes her upper body as she covers her mouth with one hand and sways. The car setting and camera position come from this clip, so the result follows its contained, seated performance rather than a scene you describe yourself.
Reference 03 · Pink Top
Dark curls move with the bounce.
This reference frames a woman with dark curly hair from the waist up in a pink crop top. She bounces toward the camera. Use it for a direct, half-body dance take; the original clip guides the action, framing and rhythm in the generated video. This quiet on the creek dance example keeps the person and the forward bounce within the same waist-up composition.
Reference 04 · Denim Set
The backwards cap stays in frame.
The reference shows a man in a denim set and backwards cap, framed full body. He begins with the shush and then moves into the bounce. This quiet on the creek dance example keeps the head-to-toe composition and its gesture-to-bounce sequence in view, so choose it when you want both movements visible. The reference clip determines the camera and performance.
Straight Answers
The reference clip gives the result a specific performance, while the photo supplies the person. Here are the limits to know before you generate.
The Trend Explained
This page turns one person photo into a 15-second vertical video guided by a reference clip. MiniMax H3 uses the selected performance to follow its action, camera framing and timing, while the uploaded person takes the lead role. The examples include a finger-to-lips selfie, a hand-over-mouth car-seat sway, a waist-up bounce and a full-body shush followed by a bounce. The output includes instrumental sound, not vocals. You do not upload a song, choose a custom location or type in new choreography; the reference sets those parts of the result.
Upload one clear photo of yourself or an adult who has agreed. The photo identifies the person for the generated performance, while the source clip supplies the motion. A face that is visible and well lit gives the model useful visual detail to work from.
Choose among four examples: the shush selfie, the car-seat sway, the pink-top half-body bounce or the full-body denim sequence. Each reference has its own framing and movement, and the video follows the one you select.
The 15-second result includes instrumental sound without human vocals. You cannot provide your own track in this tool. If you want a particular song on a post, add audio through the publishing app and check its music-use terms.
Same vibe
Turn one group photo into a crew that steps in sync in 9:16 vertical video.
Same vibe
Turn your photo into the viral lean, swing and low bounce, friend watching.
Answers about the reference, photo, sound, length and sharing your generated clip.
Make My Dance ClipChoose one of the four reference clips, upload a clear photo of yourself or a consenting adult, then start generation. MiniMax H3 uses the reference for the dance, camera and timing, and returns a 15-second vertical clip with instrumental sound and no voice.
The reference controls the actions, camera framing and timing in the generated performance. For example, the selfie reference shows a close shush and sway, while the denim reference shows a full-body shush followed by a bounce. This quiet on the creek dance follows the selected clip; you cannot replace its moves with a custom scene request.
No. This page does not accept a song upload, and the generated video has instrumental sound without human vocals. If you want a particular track on your post, add it separately in the app where you publish and follow that app’s audio rules.
Every result is 15 seconds in a vertical 9:16 format. The reference clip sets the camera framing and performance within that video, so a close selfie and a full-body example produce different compositions.
No. The chosen reference determines the visible setting, camera and dance movements. You can choose among the four examples on this page, but you cannot type a custom location, add your own choreography or select another duration.
Use one clear, well-lit photo with the person’s face visible and facing the camera. A simple portrait gives the model a clear person to place into the reference performance, whose movements, framing and timing guide the generated clip. Upload only your own image or a photo of an adult who has agreed to participate. Review the result before sharing to check the face and hands in motion.
The reference guides the movement, camera and timing, but generated details can vary from frame to frame. Review the finished clip for face and hand details before sharing, and try a clearer photo if the person is difficult to see in the input.
Yes, if the person is an adult and has agreed to the photo being used for this video. Tell them what the generated clip will show before uploading. This page is designed for one person photo, not a group image or multiple subjects.
This page does not provide information about whether generated videos are public or how visibility is controlled. Check the service’s current privacy information before uploading a photo.
You need one photo for each generated clip. The reference is a separate source clip provided on the page; you do not upload a second person photo or your own dance footage.
Read the [AI trend creation guide](/hub/how-to-do-the-ai-trend) for general advice on preparing and sharing AI trend videos. This page’s specific setup uses one person photo and one of its four dance references.
Explore More
Quiet On The Creek Dance
Choose a reference, upload one consenting adult’s photo and generate a 15-second vertical performance with instrumental sound.
Make My Dance ClipOne photo • 15 seconds • 9:16 vertical
Put Your Photo Into the Quiet on the Creek Dance
Make My Dance Clip