One photo · One dance reference

iPhone Kupi Dance AI Video Generator

Put your portrait into the 15-second foldable-phone dance. Watch the built-in reference and create your version with Wan 3.0.

THE DANCE STUDIO

Create your iPhone Kupi dance.

Upload one clear photo. The built-in reference guides the movements, setting, and timing.

Ready when you are
Input
1 photo
Duration
15 seconds
Resolution
720p
Framing
Adaptive to reference
Generation
Wan 3.0
Watch the format

The reference and the result

See the built-in movement reference alongside an example video. Results from your photo can vary.

Browse videos ↗
Reference clip · 15 seconds

Built-in dance reference

The movement reference supplied with every generation. Your portrait replaces the performer in the request.

Create your video ↗
Example clip · 15 seconds

Example video

An example of the iPhone Kupi Dance format. Your result may differ in appearance, motion, props and sound.

Create your video ↗
Behind the clip

What is the iPhone Kupi dance?

Win William's “iPhone 5555” TikTok pairs a foldable-phone reveal with an expressive hotel-room dance. The close-up device handling, step back and energetic finish make it recognizable even without the sound. A Coco Vex AI remake followed the original post; that 15-second remake is the built-in reference used here.

“Айфон купи” means “buy an iPhone” in Russian. The hook comes from “Базовый минимум” (“Bare Minimum”) by SABI and MIA BOYKA. The song predates the dance; the video made this particular phone-and-dance sequence familiar online.

The generator uses the reference video for movement guidance and your photo for the requested performer. It does not provide a license to the song or guarantee that the original audio appears in the result.

Explore the song and trend ↗
Song to short video

How this version emerged

Selected public posts show the sequence. They do not establish the first use of the sound or every remake.

August 2025

The song comes first

SABI and MIA BOYKA release 'Базовый минимум,' containing the 'айфон купи' hook. Apple Music ↗

September 2026

The sound circulates

Win William posts an earlier hotel-room dance using the same song, before the phone reveal that defines this template. Earlier TikTok ↗

October 23, 2026

The phone dance takes shape

His 'iPhone 5555' post combines the close-up foldable reveal, step back and dance in one recognizable sequence. Original TikTok ↗

Later that day

An AI remake follows

Coco Vex posts a 15-second AI lookalike. This is the video used as the built-in movement reference here. AI remake ↗

September 2026The sound circulatesOpen Earlier TikTok on TikTok ↗
October 23, 2026The phone dance takes shapeOpen Original TikTok on TikTok ↗
Later that dayAn AI remake followsOpen AI remake on TikTok ↗
Inside the 15-second reference

The dance, moment by moment

Approximate moments in the built-in clip. The generated video may change the timing, movements or objects.

00:00-00:02

The phone reveal

The performer starts close to the lens with a folded device, then opens and presents it to the camera.

00:02-00:04

The close-up performance

Facial expressions, small head movements and a lean toward the lens keep the opening intimate.

00:04-00:06

The larger foldable

A larger, tablet-sized foldable is raised and opened before the performer begins moving away.

00:06-00:10

Step back and dance

The room and outfit come into view as the performer dances and moves the device to the rhythm.

00:10-00:12

The toss

The device goes upward during the performance, one of the hardest prop interactions for a video model to reproduce.

00:12-00:15

The finish

The movement grows more energetic before the performer turns and moves toward the edge of the frame.

From photo to dance

Three steps to your video

Full guide ↗
01 / PREPARE

Upload one portrait

Choose a clear, permitted photo of one person. The dance video is already attached, so you do not need to find a reference clip.

02 / GENERATE

Submit your photo

Sign in and use one video credit to submit a 15-second, 720p Wan 3.0 task. Framing follows the built-in vertical reference.

03 / REVIEW

Check the finished clip

Open My Creations to watch and download it. Review the face, hands, phone and sound before sharing; a recorded technical failure returns its credit.

Before using a credit

Choose a photo the model can work with

The uploaded image supplies the new performer's appearance. More visible detail gives the model a better starting point for a moving shot.

Photo guide ↗

Use a photo with

  • One person, with the face visible and in focus.
  • Even light and enough resolution to see facial details.
  • Hair, shoulders and some outfit visible, especially for the step-back sequence.
  • Permission to use the image and depict the person.

Watch out for

  • Group photos or a face too small in the frame.
  • Sunglasses, hands, heavy filters or shadows hiding key features.
  • Motion blur or a tightly cropped selfie with no clothing detail.
  • Expecting an exact copy of face, outfit, hands or lip sync.
What guides the result

Your photo, the reference and Wan 3.0

Your photo

Sets the requested face, hair, clothing and overall identity of the replacement performer.

Built-in video

Guides the scene, camera, expressions, dance sequence, timing and foldable-device interactions.

Wan 3.0

Generates a new video from those inputs. It may reinterpret details, especially fast motion, hands, props, spoken audio and music.

Behind the generation

How we write the prompt

The same prompt shown below is sent with your photo and the built-in video. It tells Wan 3.0 which input controls identity and which controls the performance.

  1. 01

    Lock the person

    Give the uploaded photo authority over the face, hair, clothing and accessories.

  2. 02

    Follow the performance

    Use the video for the phone reveal, step-back dance, camera, scene and timing.

  3. 03

    Protect continuity

    Ask for one continuous shot, stable identity and believable hands on the device.

The full prompt

iPhone Kupi Dance prompt

TASK: Faithful video recreation with complete character replacement.

Use @video_1 as the master reference for the entire video performance, including all body movements, facial expressions, hand gestures, lip movements, dialogue timing, camera framing, scene composition, prop interactions, and action sequences.

Use @image_1 as the exclusive reference for the new character's identity and appearance.

CHARACTER REPLACEMENT

Completely replace the original performer in @video_1 with the character shown in @image_1.

Preserve the new character's exact facial features, hairstyle, hair color, makeup, clothing, accessories, body proportions, and distinctive visual identity.

Do not copy any facial features, hairstyle, clothing, or accessories from the original performer in @video_1.

The new character must remain visually consistent throughout the entire video, including during rapid movements, head turns, and changes in distance from the camera.

PERFORMANCE RECREATION

Recreate the original performance from @video_1 as faithfully as possible, following the exact sequence and timing of actions.

- Begin with the character close to the camera, speaking directly to the viewer with exaggerated, expressive facial movements.

- Reproduce the original hand gestures, head tilts, eye movements, eyebrow expressions, and lip movements.

- Preserve the exact sequence of interactions with the foldable electronic device, including how it is held, opened, displayed toward the camera, and moved.

- Match the moment when the character moves backward and stands up, revealing more of the outfit.

- Reproduce the original energetic gestures, dramatic arm movements, theatrical body language, turns, and final movements.

- Maintain the original rhythm, pauses, movement directions, and timing of every action.

Do not simplify, reinterpret, rearrange, or invent any movements.

SCENE AND CAMERA

Preserve the original environment from @video_1, including the luxurious interior, warm lighting, nighttime city view, windows, curtains, furniture, and background composition.

Match the original camera position, perspective, framing, and shot composition.

Keep the camera stationary, with apparent framing changes caused only by the character's movement.

Preserve the original continuous-shot structure without introducing new camera angles, transitions, or cuts.

AUDIO AND LIP SYNC

Use the original audio from @video_1 as the reference.

Reproduce the spoken dialogue, vocal delivery, speaking rhythm, pauses, intonation, background sounds, and music as closely as possible.

Synchronize every mouth movement and facial expression with the corresponding dialogue and audio timing.

If the reference video is longer than the requested generation duration, reproduce only the first portion of the video, starting from 00:00, without skipping, compressing, or rearranging actions.

PROP CONSISTENCY

Preserve the foldable electronic device exactly as shown in @video_1.

Maintain its shape, size, folding mechanism, screen orientation, and interaction sequence.

Ensure realistic finger placement, correct hand-object contact, believable device movement, and natural physical interactions.

VISUAL QUALITY

Ultra-photorealistic live-action video, realistic skin texture, natural facial details, authentic human motion, physically accurate fabric movement, cinematic lighting, consistent character identity, and believable expressions.

Preserve the reference video's visual realism and spontaneous, expressive social-media performance style.

STRICT PRIORITY RULES

1. @image_1 controls the character's entire physical appearance and visual identity.

2. @video_1 controls all actions, expressions, lip movements, timing, camera framing, background, props, and performance.

3. Never transfer the original performer's physical appearance into the new character.

4. Never change the new character's appearance to match the original performer's styling.

5. Do not introduce new actions, dialogue, props, locations, or camera movements.

6. Maintain character consistency, realistic anatomy, natural motion, and accurate lip synchronization throughout.

7. Preserve the original performance timeline without skipping or reordering events.

FINAL GOAL

Create a visually faithful recreation of @video_1 in which the original performer has been seamlessly replaced by the completely different character from @image_1.

Everything except the performer's identity, physical appearance, outfit, and accessories should remain as close to the original video as possible.

9:16 vertical video, 15 seconds, photorealistic live-action, continuous performance, no subtitles, no added text, no watermark.

The prompt describes the intended result. Generative video can still change faces, movements, props and audio.

Pay once. Use your credits.

Know the cost before you start

Every pack uses the same 15-second, 720p settings. Generation time depends on the provider queue.

One-time video generation packs
PackVideosTotal (USD)Per video
Single render1$6.99$6.99
Two renders2$9.99$5.00
Studio pack5$19.99$4.00

No subscription and no free generation on signup. One accepted generation uses one video credit. Technical failures return that credit.

View packs & buy now ↗
Before you create

Questions you might have before generating

Can I use a selfie, or do I need a full-body photo?

A clear selfie can work. Choose one where your face, hair and shoulders are visible; showing more of your outfit gives the model more to work with when the dancer steps back.

Do I need to upload the dance video too?

No. The 15-second reference video is built in. You only upload one photo, and you can watch the reference on this page before generating.

Will the dancer look like me and keep my outfit?

Your photo guides the new performer's face, hair and clothing. Wan 3.0 can still change details during movement, so check the finished video before sharing it.

Will it copy the same dance and foldable-phone moves?

The reference guides the sequence, setting and timing. Fast gestures, hands and the phone can differ in the generated video; an exact recreation is not guaranteed.

Will my video have the original song and matching lip movements?

The reference provides audio and performance guidance, but the song, dialogue and lip sync may differ. This tool does not grant a license to use the original music.

Can I change the dance, prompt or video length?

Not in this generator. The reference, performance prompt and 15-second duration are fixed; you choose the person by uploading a photo.

Can I choose portrait or landscape output?

There is no aspect-ratio control. The reference is vertical, and Wan 3.0 uses adaptive framing, so the exact crop may vary.

How long will it take, and where do I get my video?

Generation time depends on the provider queue. Follow the task in My Creations, then preview and download the completed 720p video there.

Can I try it before paying?

You can watch the reference and examples without paying. Generating a video requires a credit; signup does not include a free generation.

How much does one video cost?

One accepted generation uses one credit. Packs cost $6.99 for one video, $9.99 for two or $19.99 for five.

What if I use a credit and the generation fails?

A task recorded as a technical failure returns its credit automatically. A completed video with details you dislike does not automatically count as a failed task.

Refund policy · Support

Keep exploring

Follow the song and dance