The manual way: build it in any AI tool
If you prefer your own tools, split the job in two. Asking a video model to invent the street, the terrace and two faces at once is where most attempts fall apart. Making the still picture first lets you decide who stands where and what the restaurant looks like.
Step one is the scene: put the photos side by side into an image editing model and describe the sidewalk, the terrace, the framing and what must not change. Step two is the motion: give that picture to an image to video model, describe what each person does, keep the handheld camera steady and ask for vertical 9:16 with sound if the model supports it.
- Scene prompt we use for Duo freestyle: "Take the two people from the left and right halves of this image and show them standing together on a sunny sidewalk in front of a busy Spanish restaurant terrace with outdoor tables, chairs and parasols. The person on the left holds a small portable bluetooth speaker. Keep both faces, hairstyles and outfits exactly the same as in the photos. Photorealistic, both people visible from the knees up, vertical 9:16 frame, shot like a phone video, no text, no logos."
- Motion prompt we use for Duo freestyle: "Street freestyle on the sidewalk: the person on the right raps fast and animated toward the camera with big hand gestures, the person on the left bounces beside them and rolls their shoulders up and down to the beat, people at the restaurant tables behind them turn and smile. Handheld phone camera, natural daylight, viral street video look. Keep both faces, hairstyles and outfits exactly as in the photo. Natural, realistic motion."
- Avoid fast camera moves. A steady handheld look keeps the faces stable.
- Ask for an original instrumental beat with no vocals. The original song and the artist voice are a copyright problem, and you can add the trending sound in the app when you post.
What it costs
A Bulin 47 video costs 50 credits, because it takes two AI steps: the scene picture and the video with sound. A 480p clip is 4 seconds, enough for one burst of the freestyle; an HD clip is 8 seconds at 720p and leaves room for a full back and forth. The tool shows the exact cost before you create anything.
Credit packs start at $9.90, are one-time payments with no subscription, and credits never expire. Videos made with credits have no watermark.
Tips for posting
The joke is in who is freestyling, so name the cast in the first line of the caption: "me and my brother outside our taco place", "my dad finally dropped his first verse", "the two interns on lunch break". Post the clip as it is so the terrace fills the screen.
The clip comes with its own beat. On TikTok and Instagram you can also pick the trending Dame Hombro sound in the app; if you do, lower the original beat so the two do not clash.