
A clear starting photo
- One adult, facing forward or at a slight angle.
- Forehead, eyes, cheeks and mouth visible.
- Sharp details, even light and a neutral expression.
Your face in the bread-and-cheek reaction. One photo, one foreground role.Your face in the concha reaction: sweet bread, puffed cheeks and a look at the camera. One adult photo, a fixed banquet scene and the original black-polo look; clothing details can vary.
A banquet guest moves toward the camera, eats a concha sweet bread, and reacts with puffed cheeks before turning away. This bread-and-cheek reaction is the specific BbY WOW meme here, not a general dance using the same song.
The foreground guest in the black polo is the only custom role. The guest in white behind him also eats, but is not a replacement target. The full reference ends as the lead turns to leave; it does not show him walking completely out of the scene.
Source post linked by MakeViralThis is the selected reference, not our generated example. The linked post is a source cited by MakeViral; it is not a claim about who first created the meme.
The full 7-second reference includes the approach, bite, cheek reaction and start of the turn. The 5-second option is an opening excerpt and stops before the turn.
The black-polo guest comes forward and brings the sweet bread to his mouth. The fixed reference supplies the movement and camera.
Puffed cheeks and a look toward the camera carry the joke. Check whether the generated face remains recognizable during this close-up.
In the complete reference, the guest turns and begins moving away. The clip ends during that movement, without extending it into an invented exit.
One photo supplies the foreground identity. The reference guides the banquet, black-polo outfit and reaction; generated details may differ.
Choose yourself or an adult who has agreed to appear. Keep the forehead, eyes and mouth visible.
Choose the 5-second opening or full 7-second clip, then 480P or 720P. Review the current total on the generation button.
Check the face, hands and bread throughout the generated result before downloading or sharing.
Use one adult in good light with a neutral expression. These guides illustrate photo clarity, not generated concha examples.


This template targets the foreground face and hair, not the entire cast or wardrobe.
The black-polo guest is the only target. Background guests, including the man in white, are not selectable roles.
The reference provides the timing, camera and banquet. Your photo provides the face and hair; no separate clothes or scene controls are needed.
Eating and puffed cheeks can distort facial details. Check the hands, mouth and bread in the result. Exact likeness and frame-by-frame reproduction are not guaranteed.
Your selected length and quality determine the total shown before generation.
5-second opening or full 7-second reference, 480P or 720P, vertical 9:16. The default is the full 7 seconds at 480P. The short version does not include the turn.
Sign in to check your balance. The generation button shows the current total; a new generation is a separate paid attempt. Changing settings or previewing the scene does not start one.
Higher resolution does not guarantee better identity or food-contact details. Review an existing result before starting another attempt.
Several videos share the song. This page targets only the concha reaction.
Try another reaction or bring your own video.
The concha reaction: the foreground banquet guest in a black polo eats sweet bread, reacts with puffed cheeks and starts turning away. It is not the cowboy-hat wedding, garage dance or two-cat version.
One clear photo of a single adult with the forehead and mouth visible. Use your own photo or one you have permission to use. Children, pets and group photos are outside this version's scope.
The foreground adult in the black polo is the only replacement target. The man in white and other guests are not selectable roles. The reference keeps their performances in the background.
The template aims to keep the fixed banquet scene, black polo and reference body. Your photo supplies the face and hair, not a selected new wardrobe or background. Clothing details can change: our example added a white collar from the input photo. There are no separate outfit or background controls.
Choose 5 or 7 seconds at 480P or 720P, in 9:16. The default is the full 7-second reference at 480P. Both options start at the beginning; 5 seconds stops before the turn. The full clip ends as the guest begins leaving, not after a complete walk-out. The generation button shows the current total credits.
The selected reference clip's audio is retained. Check the result before sharing; using this generator does not give unrestricted music rights for every platform or commercial use. This is an independent template, not an official KAROL G product or an artist endorsement.
Confirmed technical failures return the task's credits under the site's existing process. An imperfect but completed result is not the same as a technical failure. If a task is delayed or its status is unclear, check History before starting another paid attempt.
Exact likeness and movement are not guaranteed. Food near the mouth, puffed cheeks and hand contact are difficult for generative video. Check the face, hands and bread throughout your result before sharing.
The tool may save a short-lived browser draft and sends your photo to the video provider when you generate. Provider retention follows its policies. Inputs are not added to our public template library. Results are private to your account by default and can be deleted from History. See the Privacy Policy for processing and deletion requests.