Cicadas.ai

Bulin 47 AI Video Maker

Make a Bulin 47 AI trend video from 1 or 2 photos: a street freestyle with a speaker and a crowd, 5 to 15 seconds. 10 seconds is 125 credits. No face swap.

  • From 63 credits per clip
  • From your photos
  • 5s / 10s / 15s
  • 480P
  • Audio available

Loading your account…

Model

MiniMax H3 Max

Browse by task

The one who freestyles

Sign in to upload

The one holding the speaker (optional)

Sign in to upload

One clear, well-lit photo per person, face visible. Use your own photos, or friends who agreed. People must be adults; no photos of children. An empty slot uses the first photo again. JPG, PNG or WebP, up to 10 MB each.

What scene would you like to create?

A scene fills the prompt below. It calls your photos Image 1, Image 2 and so on; keep those names when you edit it.

Prompt624/2000

Actual output: 10s, 9:16, 480P. Writing “4K” in the prompt does not change this resolution. Faces and details may change; successful results still cost credits if you dislike them.

More settings · 9:16 · 10s · Audio
Aspect ratio
Duration
Resolution
Audio

Checking generation and private storage configuration.

Billing and delivery

Generate charges the displayed quote for the current length and resolution. If generation fails or the file fails our check, the credits come back automatically; a finished clip you don’t like is still charged. Finished clips stay in My videos.

Estimated cost: 125 credits
Sign in to generate

Sample result

10s · MP4
A street freestyle with a friend on the speaker.Made on Cicadas · MiniMax H3 Max · 10s
Made from these photos (AI-made, fictional)
  • The one who freestylesThe one who freestyles
  • The one holding the speakerThe one holding the speaker
Use this recipe

About Bulin 47 AI on Cicadas

Bulin 47 AI turns one or two photos into a vertical street-freestyle clip in the style of the Bulin 47 trend: one person freestyling on the pavement, a friend holding a speaker, onlookers around. Cicadas makes it with MiniMax H3 Max as a new clip of 5, 10 or 15 seconds. It does not put your face onto the original video and does not use its audio. A 10-second clip is 125 credits.

Bulin 47 AI examples made on Cicadas

From your photos10s · 480P

A street freestyle with a friend on the speaker.

MiniMax H3 Max, 10 seconds with sound, vertical, from two photos. He freestyles on a night street with a hand on his chest while the friend in the denim jacket holds a small speaker beside him; both keep their faces and outfits. The onlookers are invented and look alike. The sound is a fast electronic beat with a chanted voice, although the prompt asked for no vocals.

Made from these photos (AI-made, fictional)
  • The one who freestylesThe one who freestyles
  • The one holding the speakerThe one holding the speaker
Use this recipe ↗
From your photos5s · 480P

One photo, a daytime plaza.

MiniMax H3 Max, 5 seconds with sound, vertical, from one photo. She grooves in a city plaza with a small speaker on the ground and passers-by behind her. Five seconds is a few moves, not a full freestyle. The sound is an upbeat electronic beat.

Made from these photos (AI-made, fictional)
  • The one who freestylesThe one who freestyles
Use this recipe ↗

Why use Cicadas for Bulin 47 AI

A Bulin 47 AI video from your own photos

The first photo is the one who freestyles and the second is the friend with the speaker. Leave the second slot empty and the first photo is used again.

A new clip, not a face swap

Most versions of this trend replace the faces in the original recording. This page draws a new scene from a description instead, so the street, the crowd and the moves are new every time and nobody is edited into someone else's video.

A generated beat, not the original audio

MiniMax H3 Max generates sound with the picture: in our runs a fast electronic beat, once with a chanted voice. The original freestyle and its beat are not included. At 480P, 5 seconds is 63 credits, 10 seconds is 125 and 15 seconds is 188; at 768P they are 100, 200 and 300.

How to use Bulin 47 AI

  1. 01

    Sign in and add one clear, front-facing photo per person: the one who freestyles, and a friend to hold the speaker.

  2. 02

    Pick a scene (night street, daytime plaza or face to face), choose 5, 10 or 15 seconds, and check the quote.

  3. 03

    Tick the photo confirmation, generate, then download the MP4 from My videos and add your sound when you post.

Bulin 47 AI prompt ideas

Copy one into the prompt box above and adapt it to your shot. Or write your own shot by shot in the prompt generator.

  • “Vertical phone footage on a city street at night outside a restaurant, one continuous shot. A loose ring of onlookers stands on the pavement around the person from Image 1, who freestyles to the beat: a glance to the side, a side-to-side groove with loose shoulders, a tap on the chest, a point at the crowd, then a freeze with a smirk. Beside them the person from Image 2 holds a small portable speaker at chest height and nods along. Keep each face, hair and outfit as in its photo. Warm streetlight, handheld camera with a gentle wobble. Sound: a hard, fast dembow-style beat, no vocals. No text, no logos, no shop signs.”

  • “Vertical phone footage in a sunny city plaza, one continuous shot. A few passers-by stop to watch the person from Image 1, who freestyles to a beat from a small speaker on the ground: a side-to-side groove, quick hand gestures toward the camera, a tap on the chest, then a freeze with a grin. Keep the face, hair and outfit as in the photo. Bright daylight, handheld camera. Sound: a hard, fast dembow-style beat, no vocals. No text, no logos, no shop signs.”

  • “Vertical phone footage on a city street at night, one continuous shot. The people from Image 1 and Image 2 stand face to face and take turns freestyling with big hand gestures, each nodding while the other goes, a small speaker on a ledge between them and a few onlookers behind. Keep each face, hair and outfit as in its photo. Warm streetlight, handheld camera. Sound: a hard, fast dembow-style beat, no vocals. No text, no logos, no shop signs.”

Bulin 47 AI FAQ

Tested on Cicadas · reviewed 2026-10-11

Recorded on 2026-10-11 with MiniMax H3 Max reference-to-video through fal.ai, with requests built by this site's input mapping: a 10-second night-street clip from two photos (125 credits here, back in 28 seconds) and a 5-second plaza clip from one photo (63 credits, 25 seconds), both 9:16 at 480P with sound. The lead and the friend holding the speaker kept their faces and outfits; the invented onlookers looked alike. The sound was a fast electronic beat, with a chanted voice in the longer clip although the prompt asked for no vocals (two automated listeners). The face-to-face scene, 768P, 15-second clips and generation from this page end to end were not run.

Updated Oct 11, 2026 · How we test

MiniMax H3 Max · Recorded Cicadas sample
MiniMax H3 Max · 9:16 · 1–2 photosNew

Raindance AI Video Generator

Make a Raindance AI video from 1 or 2 photos: a golden-hour seaside clip with a pier, a beach and a sunset, 5 to 15 seconds. 15 seconds is 188 credits. No song.

MiniMax H3 Max · from 63 credits

Tested 2026-10-11

MiniMax H3 Max · Recorded Cicadas sample
MiniMax H3 Max · 9:16 · 2 photosNew

Hotel Lobby AI Video Generator

Make a Hotel Lobby AI video from two photos, people or pets: a duet at one hanging mic in an orange room. 10 seconds costs 125 credits. No song included.

MiniMax H3 Max · from 63 credits

Tested 2026-10-05

MiniMax H3 Max · Recorded Cicadas sample
MiniMax H3 Max · 9:16 · 1–2 photosNew

Summrs AI Alternative for Trend Videos

A Summrs AI alternative for Hotel Lobby, Raindance and Bulin 47 clips: 1 or 2 photos in, a new 5 to 15 second video out, priced per clip. No face swap.

MiniMax H3 Max · from 63 credits

Tested 2026-10-11

Veo 3.1 Fast · Recorded Cicadas sample
Veo 3.1 Fast · beat, voices and rapping · 8sNew

AI Rap Video Generator

Write the bars and get an AI rap video with the beat, voices and characters rapping on screen, made with Veo 3.1 Fast. Original characters only; quote first.

Veo 3.1 Fast · from 100 credits

Tested 2026-09-30