Pick the performer
Choose one clear character photo. Keep the face, shoulders and outfit visible. Use a photo you have permission to process; prepare an upright character image first for a pet remix.
Loading your scene…
Loading your scene…
The street freestyle, reimagined
Your face. Your character.
A little shoulder bounce.
Make your own interpretation of the Bulin 47 freestyle: a lead performer, a speaker partner, and a crowd waiting for the next move.
Prepare my freestyleGeneration is not open yet. Prepare a photo and scene brief on your device.
Your freestyle desk
One consenting performer. A shoulder-led street moment.
JPG, PNG or WebP · up to 10 MB · each side over 340px
Create an original street-freestyle scene with the consenting adult from the reference. Preserve their recognizable face and outfit. An adult partner holds a portable speaker at waist height. The performer looks toward the speaker, makes two alternating shoulder bounces, gestures to a loose spectator circle, then pauses. Medium-wide steady framing, visible hands, restrained background movement. No real-artist face or voice imitation, text or logos. A new interpretation, not original footage.
Video generation is being prepared. No photo upload, account or payment is needed here.
Follow this workflowWatch the freestyle idea
Explore these third-party reference clips before preparing your own cast. These examples were not generated by Bulin47AI.
A familiar freestyle with a different lead performer.
Open reference clipCompare the face, outfit and motion with the street scene.
Open reference clipA six-second silent preview with a blue character.
Open reference clipReference clips are hosted by third parties. Playback and availability depend on the source. They illustrate the trend, not a promised result.
Choose your cast
A friend, a pet or a character changes what you need to prepare. Pick a workflow and start with the right reference.
One consenting performer. A shoulder-led street moment.
One-photo preparationPrepare an upright character from your dog or cat photo.
One-photo preparationA mascot or original character with a readable silhouette.
One-photo preparationWrite the performer, partner and shot before animating.
One-photo preparationPair a character photo with a motion clip you can use.
Photo + motion referencePrepare two separate identities and a shared composition.
Two-photo compositionThe idea behind the trend
The name refers to AI remixes inspired by Bulin 47’s street freestyle with Kevin Wai. The recognizable ingredients are the shoulder-led performance, a nearby partner with a portable speaker, and a watching crowd.
A remix can put a new character at the center. A photo gives the character a look; a motion reference guides the movement. Those are separate inputs, and a text prompt alone does not reproduce the original performance exactly.
Keep the exchange.
Make the performer your own.
From photo to performance
Choose one clear character photo. Keep the face, shoulders and outfit visible. Use a photo you have permission to process; prepare an upright character image first for a pet remix.
Select a workflow, then read its scene prompt. For motion transfer, pair the image with a 3–30 second reference you can use. A fixed-source freestyle needs a cleared reference before it can open.
Download a text brief with the selected template and scene instructions. Preparation files stay in this browser. Email accounts are being connected; video rendering and paid checkout will open after the studio setup is complete.
One-time credit packs, no subscription. Choose 720p or 1080p motion transfer. No free generation allowance.
A little movie magic
Room to try a few ideas
For your whole cast
Choose 3–15 seconds per video. We reserve the quoted amount and settle against delivered duration, rounded up to the next second (50 ms tolerance). Shorter clips return the difference. You never pay more than your quote. Taxes, if applicable, are shown at checkout. Checkout is not open yet.
Watch. Plan. Recreate.
The planned one-photo workflow pairs your portrait with a fixed freestyle reference behind the scenes. Generation is not open here yet.
Read the guideThe most useful portrait clearly shows the face and the body area involved in your chosen motion. Match it to the reference rather than using a tiny face crop.
Read the guideThe fixed template needs a permitted reference behind the scenes. Its preparation is separate from the planned one-photo user flow, which is not open yet.
Read the guideA pet preset prepares an experimental idea. Human motion-control documentation does not establish reliable animal anatomy or successful pet output.
Read the guideAn original character works best as a coherent visual design with a movement it can plausibly perform. Keep the silhouette and visible joints readable.
Read the guideA useful prompt describes appearance and scene while the reference supplies movement. Keep the first brief short enough to review and revise.
Read the guideFind the stage where the problem happens before changing the prompt. A local preview issue, a provider failure, and an imperfect result need different checks.
Read the guideA usable export needs a checked video file and a checked audio track. Neither motion transfer nor a public video link establishes music or footage permission.
Read the guideBefore you start
Video generation is being prepared. You can choose a workflow, check a photo locally, copy a scene prompt and save a preparation brief. No video is submitted or charged for.
One photo can define a single character. Motion transfer also needs an authorized reference video. A future fixed-source workflow would supply that reference for you; it is not open yet.
You can prepare those ideas here. A pet usually needs an upright stylized character image before human motion can be applied. Pet and mascot results have not been tested by this site.
The performer and speaker partner workflow has separate photo A and photo B slots for composition preparation. It does not send two identities into a single-character motion model or generate a duet.
No original soundtrack is provided by this preparation tool. Motion-model audio behavior is separate from permission to publish a recording. Plan your own permitted soundtrack and review the export before posting.
Preparing a scene brief and reading the guides costs nothing. Paid motion transfer is priced at 1 credit per second for 720p or 2 credits per second for 1080p. Credit packs cost $4.99 for 20 credits, $12.99 for 80 credits and $24.99 for 200 credits. No free generation is offered. Checkout is being connected.
The preparation desk reads selected files in your browser and makes no photo upload. The downloaded brief contains text, not your photo. Refreshing or closing the page clears the selected files.
No. Bulin 47 AI is an independent project, with no affiliation or endorsement by Bulin 47 or Kevin Wai. Use your own or authorized characters and make the AI origin clear when sharing a result.
The next performer could be you