Bing Bing Bing

One photo of two adults or two pets together. Show both full bodies with a clear left and right subject. JPG, PNG, or WebP, up to 30 MB.

10 s · 9:16 · 720p · Soundtrack included

Credits per video: 100

Open your video library

Bing Bing Bing is the TikTok and Reels kicking meme: two people take turns throwing exaggerated kicks toward the camera, in time with the beat. AI remixes bring the same double act to pets and other unlikely pairs. Upload one photo showing two adults or two pets together to make your own version. The fun comes from the contrast: one subject makes a big move while the other holds the scene, then their roles switch. Each creation costs 100 site credits and produces a 10-second vertical 9:16 video in 720p MP4 format with the reference soundtrack included. Listen to the example before you begin so you know which sound accompanies this template. Choose a photo with two clearly separated, full-body subjects whose left and right positions are easy to distinguish. You can select your image before signing in, but generation requires an account; if you leave to sign in, select the photo again when you return.

Make your video in three steps

  1. Choose one JPG, PNG, or WebP image no larger than 30 MB. It must show either two adults or two pets together, with both full bodies visible and a clear left and right subject. Do not upload two separate portraits.
  2. Listen to the example, sign in, and select your photo again if you returned from signing in. When you are happy with the image, create the video for 100 site credits. The template adds the alternating kicks, street scene, and reference soundtrack.
  3. Open the finished result and watch the full clip with sound. Check both subjects, the movement, and the framing before downloading your MP4. You can revisit the result in your library; choosing to generate another version costs another 100 site credits.

One photo, two unmistakable subjects

Think of the starting image as a small stage for a double act. Both subjects need enough space to be read separately before any movement begins. A pair standing side by side is easier to understand than a tightly overlapping pose, especially when their legs cross or one body hides behind the other. Include the whole body of each adult or pet, not just faces and shoulders. Leave a little room around their feet and heads so the composition does not already feel squeezed at the edges.

Choose a picture where you can immediately say who is on the left and who is on the right. That simple distinction matters because the joke depends on taking turns, rather than showing two indistinguishable figures moving together. Different clothing, coat colors, or silhouettes can make the pair easier to follow. Avoid a busy group photo that leaves the intended duo unclear. This template takes one shared image, not two uploads that it later combines, so find a photo containing both subjects before you begin.

A useful final check is to look at the image at phone size. Can you still separate the two bodies and see where their legs or paws belong? If not, choose another shot rather than hoping movement will clarify it. A readable starting composition gives you a better basis for judging the finished clip, although it cannot guarantee that every facial feature, body detail, or pose will remain unchanged.

Adult duo: kick timing detailReference example · not your generated result

Make the pet pairing part of the joke

Two pets can bring a different kind of comedy to the same routine. A composed-looking pair becomes funny when the scene turns into an oversized street dance, while two expressive animals can make the alternating movement feel like a friendly challenge. Start with two pets together in one full-body photo. A close-up of two heads may be charming, but it leaves out the bodies needed to make the kicks readable. For this template, choose either two pets or two adults rather than a mixed adult-and-pet pair.

For pets with similar coloring, pay attention to the outlines. A small gap between them can help you follow each animal without relying on tiny differences in their faces. If one pet is much smaller, choose a picture where it is still clearly visible instead of tucked beneath or behind the other. The aim is not a perfectly posed portrait. It is a clear double act in which each participant has a recognizable place before the exaggerated movement starts.

Treat the animal movement as an intentionally fictional performance, not a demonstration of what a real pet should do. The amusing part is the unexpected choreography and the switch between participants. After generation, check paws, legs, tails, and the way each body meets the street. If those details look distracting, you may prefer a different starting image for a later creation instead of sharing a version whose main joke gets lost in confusing anatomy.

Cat and dog, a playful double actReference example · not your generated result

Alternating kicks that play toward the camera

The routine is built around playful, exaggerated kicks toward the camera on a street. Its rhythm comes from the handoff between the left and right subject. Watch for that exchange when you review the result: the eye should move naturally from one participant to the other, with enough contrast to understand whose turn it is. A strong still photo can introduce the pair, but it is the timing of the alternating gestures that gives the finished video its comic character.

Because the movement is directed toward the viewer, feet or paws can become prominent for a moment. That perspective is part of the visual gag, but it also makes unusual limb shapes easier to notice. Review more than the opening frame. Follow each kick through its approach and return, and look at the quieter participant as well as the one making the biggest move. Small changes can be less obvious while your attention is fixed on the center of the action.

The output is a 10-second vertical 9:16 clip at 720p, delivered as an MP4. Keep that narrow, upright frame in mind when choosing your photo: both subjects should remain easy to read as a pair rather than depending on a very wide composition. This is a fixed template experience, not a place to dial in choreography or camera settings. Choose your image for the scene you want, then judge the completed movement on its own merits.

Two friends, alternating kicksReference example · not your generated result

Hear the beat before creating

The soundtrack gives the alternating kicks their punchline. Listen for the moment one subject finishes and the other takes over: a clear handoff makes the pair feel like a double act rather than two unrelated figures. If you arrived looking for the Bing Bing Bing song or sound effect, play the example with sound to check that this is the version you want. The reference soundtrack is included in your generated video, so you do not need to upload a separate audio file.

The parrot pair beside this section shows how the joke works with animals. Notice the pause between their turns and the way each kick comes toward the viewer. Watch once with sound and once without it: the movement should still be easy to follow, while the beat gives it an extra comic accent. Your starting photo supplies the personalities, whether that is two serious-looking friends or a pair of pets with very different expressions.

Listen again when your result is ready. Follow both participants through the full ten seconds and check whether the switch between them feels satisfying alongside the soundtrack. Before publishing, check the permissions you need for that audio; including it in the file does not grant a music license. If you choose a different soundtrack later, listen to the whole edit again and check that its strongest beats still land where you want the joke to happen.

Parrot-pair referenceReference example · not your generated result

Know the credit cost and keep your result

Each new creation costs 100 site credits. Checking progress, reloading the page, or reopening an existing result is not a new generation and does not create a new charge. Your result library is the place to return to a completed video instead of starting over simply to see it again. If a page stops displaying the result as expected, check the existing creation in your library before pressing a button that requests another version.

Another generation costs another 100 site credits, whether you use a new photo or try the same pair again. Make that choice deliberately after watching the first result. Decide what you want to improve: a clearer starting pose, more separation between subjects, or a less crowded composition. Repeating the same input does not promise a particular correction, and there is no guarantee of perfect identity preservation. A useful second attempt begins with a specific reason to prefer a different source image.

You need to sign in to generate. Selecting a photo before login lets you prepare your choice, but you must select it again after returning from sign-in. Downloads for accounts without a paid order are watermarked. Accounts with a paid order receive the original without an added site watermark. This distinction concerns the downloaded file; it does not change the 100-site-credit price for each creation or establish soundtrack publishing rights.

A fantastical creature remixReference example · not your generated result

Choose a version you are happy to share

Give the complete clip a careful watch before sending it to friends or posting it. Check faces during the biggest movements, not just when the subjects are still. Look for extra or merged limbs, awkward contacts with the ground, and moments where the left and right participants become hard to distinguish. For pets, include ears, paws, and tails in that review. A funny idea is worth keeping only if the version you share still feels comfortable and understandable to you.

When comparing results, choose the one with the clearest interaction rather than automatically favoring the largest kick. A slightly smaller gesture can make a better double act if the turn-taking reads clearly and both participants remain recognizable. Watch once with sound for the overall joke and once while paying closer attention to visual details. There is no exact completion-time guarantee, so leave room to review the finished video rather than planning a share around an assumed delivery time.

For a caption, describe the fictional performance in your own voice: a friendly street showdown, a pet double act, or two companions taking turns stealing the scene. Do not present the reference parrots as your result. If you want a different direction next, explore the pet party page for another concept, try text-to-video for an idea that starts with words, or use the add-soundtrack tool when you want to work on a video's audio separately.

Pet duo: movement detailReference example · not your generated result

Bing Bing Bing questions, answered