Make a Bulin 47 AI video with one character photo and the original sound. The template replaces the main performer, aiming to preserve the person with the portable speaker, the crowd, and the camera movement.
Bulin 47 AI guide: choose a photo, replace the performer, and review your video.
Bulin 47 AI turns one character photo into a rap-performance video. The target is the performer in sunglasses and an open light-pink shirt, standing behind the person with the portable speaker. The loaded clip supplies the dance, gestures, camera, room, and timing. Your photo defines the replacement face, hair, skin tone, body, clothes, and accessories. The surrounding people are outside the replacement role.
The performance is already loaded. Start with one photo of the person who should take the lead.
STEP 1
Add one photo with a clear face, hair, clothes, and upper body. That photo is the only appearance reference. The person holding the portable speaker does not need a photo.
STEP 2
Sign in and select Generate. Uploading the photo does not start a paid request.
STEP 3
Open My creations, watch your Bulin 47 AI result with the original sound, and download the version you want to keep.
Explore the roles and camera moments in the loaded performance. Each Bulin 47 AI video uses your photo for one character while aiming to retain the surrounding scene.
The Bulin 47 AI template uses Photo 1 for the entire character. Choose a clear picture of the face, hair, clothes, and upper body. Sunglasses, the light-pink shirt, and other details from the original performer should not remain unless they are also in your photo. A tight crop that hides the outfit gives the model less to follow.
The person in front holding the portable speaker is outside the replacement role. Bulin 47 AI instructs the edit to preserve their face, clothes, actions, and speaker, along with everyone else in the room. You do not need a second crowd photo. Overlapping people can still be altered accidentally, so check the foreground person as well as your lead.
Bulin 47 AI follows a clip with turns, close gestures, and a phone crossing the camera near the end. The edit is asked to track the same character behind those obstructions. Watch that final moment when previewing: the character should return with the same face and outfit. Hands, identity, and mouth movement can still drift; precise lip sync is not guaranteed.
Choose this preset when you want one character inside the loaded performance. For a different room, a new dance, or several replacement roles, start with a tool that supports that task.
Use Bulin 47 AI to put yourself or a consenting friend into the featured performance. You can start with a photo without recording your own choreography. The clip provides the gestures and rhythm; it does not record a new vocal performance.
Bulin 47 AI can use a character image you have permission to edit. Pick the intended outfit in that image before uploading. A later attempt with another outfit is a separate generation; the page does not create a batch of costume variations from one click.
For your own footage, a different crowd, or more than one replacement, use Motion Transfer on the homepage and write the prompt for that material.
One photo starts the edit. These settings and controls describe what you can choose before generating.
Use Replace to change your selected picture before generating. There is one role to fill, so no ordering of background portraits or extra cast images is needed.
The Bulin 47 AI reference is already loaded. Play it before choosing a photo to see the gestures, turns, and close-up framing your character will follow.
Find your Bulin 47 AI clips in My creations or video history. You can return to an existing result to preview and download it without starting another generation.
Bulin 47 AI uses Seedance 2.5 Edit with this reference’s original sound. No separate soundtrack upload is needed. The model is selected for this template.
The price uses the loaded performance and the resolution you select. The Generate control shows the credit cost for that request. Plan examples elsewhere may use other models.
For your first ideas.
$100.0 charged yearly
2,400 credits/year
Up to 400 images
Up to 240 videos
For a steady creative flow.
$360.0 charged yearly
21,600 credits/year
Up to 3,600 images
Up to 2,160 videos
For more creations, more often.
$599.0 charged yearly
48,000 credits/year
Up to 8,000 images
Up to 4,800 videos
Try before you subscribe
Prices in USD; taxes and total shown at checkout. Subscriptions renew automatically; cancel in Billing settings. Subscription credits expire each period; one-time credits never expire.
Refunds: request within 72 hours. Used purchased credits and applicable non-refundable processing costs (up to 6%) are deducted. Terms · Refund Policy
Photos, who changes, sound, and the finished video.
Upload one photo into Photo 1. Do not use a collage or a picture of several people. The model needs one clear identity for the only role being replaced.
Only the main performer who wears sunglasses and an open light-pink shirt and stands behind the person holding the portable speaker. The person with the speaker, the speaker itself, and the other people are meant to stay.
Use a sharp photo where the face, hair, clothes, and upper body are visible. Avoid a covered face, heavy blur, and a crop that cuts off the outfit you want to see.
The prepared instruction asks the model to preserve every other person without adding, removing, duplicating, or merging anyone. Crowded frames and overlapping bodies can still mix a face or a hand, so watch those moments before you share the result.
The same performer should continue through turns and through moments when a phone or another person blocks the view. That is the requested edit, not a guarantee. Hands and identity details can still be wrong.
The edit follows the source performer’s mouth movement and timing. Precise lip sync is not guaranteed, especially when the face is turned or partly hidden.
Yes. The finished video keeps the original sound from this reference. You do not upload a song or switch audio on. This page does not name the audio or grant a license to use it.
The result follows the loaded performance, about 23 seconds in a vertical frame. There is no duration picker on this page.
Seedance 2.5 Edit. The model is selected for this template. To use another model or your own reference video, open the Motion Transfer homepage and choose a suitable workflow there.
No. Leave the prepared prompt in place unless you have a specific change. If you edit it, keep Photo 1 assigned to that one performer and do not ask the model to change the other people.
You can watch the reference and choose a photo before generating. Creating a video requires signing in and enough credits for the cost shown on Generate. Selecting a photo does not start a paid request.
Open My creations or your video history after generation and download the result you want to keep.
Use a photo you have permission to edit. This template does not grant rights to the footage or the soundtrack. Share the result only where you have permission, and follow the destination platform’s rules for AI-created media.
Choose one clear character photo and bring its look into this performance, with the original soundtrack included.
