Upload two photos. Bing Bing Bing AI makes a 12s street kicking video at 720p with an original beat for 2 credits. Adults only.
Adults only: 18+ for the human Duo mode.
2 credits · 720p · 12s
Sample video
A Bing Bing Bing kicking trend clip: the bounce, the kicks at the lens, and the run at the camera. The demo below is @jakeyang04's two furry street monsters version from 18 October, with 2.0M+ plays — the trend's biggest AI post. It is not the parrots version. Your video is made from your own photos with the Duo or Two pets prompts below.
Sample video
Demo: TikTok @jakeyang04 (two furry street monsters Bing Bing Bing reel). This demo is a real trend clip, not a video this site generated.
Make your video
2 credits are charged when you generate. Failed video jobs are refunded.
Choose your photo first. Sign in when you generate. Credit packs
Where the Bing Bing Bing trend came from
The kicking meme comes from a real street video circulating since 2024. An AI animal wave followed in mid-October 2026, with a series of AI pairs on the same grey side street. The two furry street monsters post passed 1M views, and how-to templates followed from 22 October.
The look: two figures bouncing on a beat on cracked wet concrete, parked scooters and blue plastic crates behind them, taking turns kicking at the lens, then both running at the camera kicking and grinning, a cartoon bing on every kick.
How to make it in 3 steps
1. Upload two photos
Two photos for Duo or Two pets. The first photo is the left side, the second is the right side. Adults only, 18+, for the human Duo mode.
2. Choose Duo or Two pets
Duo keeps two adults on the street, left first. Two pets keeps two pets upright on their hind legs on the same street, running the same kicking routine.
3. Generate · 2 credits
Credits are charged when you generate. Wan 3.0 (wan3.0-video) makes a 12s, 720p clip with an original beat. Resolution is always sent as 720P.
What it looks like
Duo: two adults stand side by side on a grey side street — cracked wet concrete, parked scooters, stacked blue plastic crates — bouncing lightly, knees bent, ready to kick. Each face, body, and outfit stays exactly as in their own photo.
Two pets: two pets stand upright on their hind legs on the same street, species, breed, and fur locked to their photos, front paws raised, ready to kick.
The video is one continuous take: bounce on the beat, left kick at the lens, right high front kick, left quick kicks with a hand from the bottom edge blocking one foot, right spin and kick, then both run at the camera kicking and grinning. The sound is an original punchy phonk-style beat with a cowbell and a cartoon bing on every kick, with no lyrics and no specific track.
Which photo works best
Use sharp full-body photos facing the camera, in good daylight, with faces clear. Adults only, 18+, for the human Duo mode. Your clothes are kept exactly, and the street is built behind you.
For Two pets, use sharp photos that show each pet, head to paws. Upload two separate photos — the first is the left side, the second is the right side. A single photo showing two people together is still a Duo video; see the FAQ. Use your own photos only, no celebrities.
Prompts
Also on the prompts page. The Duo pair is the default; Two pets swaps in its own prompts.
Duo · Internal first-frame prompt
Use the two uploaded photos as the base. The first photo is the person on the left, the second photo is the person on the right. Keep each person's face, body shape, skin tone, hair, hands, outfit, colors, fabrics, shoes, and accessories exactly the same as in their own photo. Do not blend the two people, do not swap their clothes, and do not turn either person into a celebrity lookalike. Show the two adults standing side by side on a grey side street, facing the camera, bouncing lightly on their feet with knees bent, ready to kick. Behind them: cracked wet concrete, parked scooters, and stacked blue plastic crates. Overcast daylight, photorealistic, not CGI. Vertical 9:16. Exactly two adults, no text, no logos.
Duo · Video · 12s
A single continuous take with no cuts, shot from one fixed camera position. Keep both people's faces, bodies, outfits, and the side street exactly as in the still image, with identity locked to the still throughout. The two bounce on the beat, then the person on the left kicks at the lens, then the person on the right answers with a high front kick, then the left person fires off quick kicks while a hand reaches in from the bottom edge of the frame and blocks one foot, then the right person spins and kicks, and finally both run toward the camera kicking and grinning. Kicks stay playful and rhythmic, and both people stay in frame. Audio: an original punchy phonk-style beat with a cowbell and a cartoon bing sound on every kick, with no lyrics and no specific track. No text, no logos.
Two pets · Internal first-frame prompt
Use the two uploaded photos as the base. The first photo is the pet on the left, the second photo is the pet on the right. Keep each pet's species, breed, face, coat color and markings, fur texture, body shape, and size exactly the same as in its own photo. Do not blend the two pets and do not turn them into cartoons. Show the two pets standing upright on their hind legs side by side on a grey side street, facing the camera, bouncing lightly with front paws raised, ready to kick. Behind them: cracked wet concrete, parked scooters, and stacked blue plastic crates. Overcast daylight, photorealistic, not CGI. Vertical 9:16. Exactly two pets, no text, no logos.
Two pets · Video · 12s
A single continuous take with no cuts, shot from one fixed camera position. Keep both pets' species, breeds, faces, coats, bodies, and the side street exactly as in the still image, with identity locked to the still throughout. The two bounce on the beat on their hind legs, then the pet on the left kicks at the lens, then the pet on the right answers with a high front kick, then the left pet fires off quick kicks while a hand reaches in from the bottom edge of the frame and blocks one paw, then the right pet spins and kicks, and finally both hop toward the camera kicking and grinning. Kicks stay playful and rhythmic, and both pets stay in frame. Audio: an original punchy phonk-style beat with a cowbell and a cartoon bing sound on every kick, with no lyrics and no specific track. No text, no logos.
Pricing
Bing Bing Bing is 2 credits for a 720p, 12 second video with an original beat. Credits do not expire. There is no subscription.
$9.99
Try
2 credits
$19.99
Creator
6 credits
$49.99
Studio
18 credits
All purchases are final and non-refundable. If a paid Bing Bing Bing video fails, or is still running after 10 minutes, the 2 credits charged for that video are returned automatically. A finished video is not refunded. For billing errors such as a duplicate charge, email support@knightcatai.com.
Yes for the human Duo mode: 18+ only and adults only. Photos must be you or adults who agreed. Use photos you own or have permission to use. No celebrity lookalikes. The Two pets mode uses pet photos.
Can I use one photo that already shows two people?+
Yes. Duo is the mode for two people, however they arrive in your uploads. Two separate photos, left first, is the cleanest. A single photo showing two people together is also a Duo video: both people are kept, left and right as they stand in the photo. There is no separate one-photo mode.
What is the kicking routine?+
Both bounce on the beat, the left side kicks at the lens, the right side answers with a high front kick, the left side fires quick kicks while a hand from the bottom edge blocks one foot, the right side spins and kicks, and both run at the camera kicking and grinning.
Does it include a specific song?+
No. The sound is an original punchy phonk-style beat with a cowbell and a cartoon bing sound on every kick, with no lyrics. No specific track is promised.
Where do I get the prompt?+
You do not need to write one. The page uses fixed prompts for the internal first frame and the video. You can read the Duo and Two pets prompts in the Prompts section below or on the prompts page.
Is it a real street video?+
No. Every clip is newly generated AI video from your photos. Label the result as AI where a platform asks.
What photo works best?+
Use sharp full-body photos facing the camera, in good daylight, with faces clear. Adults only, 18+, for the human Duo mode. For Two pets, use sharp photos of each pet, and the pets are shown upright on their hind legs.
How long is the Bing Bing Bing video and how much does it cost?+
Every Bing Bing Bing video is 12 seconds at 720p, with an original phonk-style beat, cowbell, and a bing sound on every kick. It costs 2 credits when you click Generate. Packs: $9.99 for 2 credits, $19.99 for 6 credits, and $49.99 for 18 credits.
More pet video templates
Other Knight Cat AI tools that turn pet photos into short videos with sound. Some templates also use your photo.
