The Baby Wow guy meme, starring you, from one photo

How to make a Baby Wow guy video yourself

You do not need this page to make one. This is how the video is put together, with the prompts for every shot, so you can build it with any picture model and image-to-video model you like.

1. Step 1

   Draw three stills from your photo

   Use a picture model that takes a reference photo and draw three stills from the same photo: the walk-up, the bite and the dance back. One photo behind all three keeps the face the same, and describing the party the same way each time keeps the hall from changing between shots.

2. Step 2

   Turn each still into five seconds of video

   Give each still to an image-to-video model with one line about what happens in it, and ask for one continuous handheld shot with no cuts. Everything should look like another guest filmed it, a little soft and grainy in the party light, not like a film.

3. Step 3

   Cut the three together

   Lay the clips end to end at 9:16 with hard cuts, five seconds each. Leave the words off, as the meme has none, and add the trend sound on TikTok when you post rather than in the edit, so the post is listed under the sound.

The shots, second by second

The prompts, shot by shot

Each shot is made in two steps. Give its still prompt to a picture model with your photo as the reference, then give the picture it draws to an image-to-video model with the motion prompt. Add these endings to every prompt: they set the look and keep the faces the same from shot to shot.

1. 0–5sThe walk-up

   Still prompt

   Copy

   A quinceañera party at night in a decorated reception hall: strings of warm lights, pink and gold balloon arches, round tables with white tablecloths, a crowded dance floor with guests dancing behind. The person in the reference photo, in their own clothes from the photo, stands on the dance floor about three metres from the camera, holding a concha in one hand, mid dance step, playful and confident. Full body, facing the camera. The concha is a round, palm-sized Mexican sweet bread roll, golden underneath, its domed top a crackly pink sugar crust scored with curved lines, round like a bun rather than shaped like a shell.

   Motion prompt

   Copy

   They dance straight toward the camera with loose, playful steps, shoulders bouncing and the concha held up in time with the beat, until they are close to the lens. Guests keep dancing behind them and the party lights flicker. Handheld camera, as if filmed by a guest.

2. 5–10sThe bite

   Still prompt

   Copy

   A close-up at the same quinceañera party, warm string lights and dancing guests blurred behind. The person in the reference photo is right in front of the camera, head and shoulders filling the frame. They hold a concha in one hand just below their chin, mouth closed, looking dead straight into the lens with a completely serious, deadpan expression. The concha is a round, palm-sized Mexican sweet bread roll, golden underneath, its domed top a crackly pink sugar crust scored with curved lines, round like a bun rather than shaped like a shell.

   Motion prompt

   Copy

   They lift the concha, take a big bite out of it, lower it again and chew slowly with their mouth closed, holding a dead-serious stare straight into the lens, one eyebrow slightly raised, sugar crumbs falling. They do not smile. The camera holds close with a slight handheld shake.

3. 10–15sBack to the party

   Still prompt

   Copy

   The same quinceañera party, a crowded dance floor under warm string lights and coloured DJ lights. A medium-wide shot of the dance floor. In the centre of the frame, about two metres from the camera, the person in the reference photo faces the camera, seen from head to knees, mid step backwards toward the dancing crowd, cheeks full, still chewing and deadpan. The foreground is empty dance floor: no hands, arms or objects near the camera.

   Motion prompt

   Copy

   Still facing the camera and still chewing, they dance backwards away from it with bouncing shoulders, back into the crowd of dancing guests, until the dancers close around them. Handheld camera, as if filmed by a guest, party lights.

Where it goes wrong

• Do not ask for a phone video by name

  Tell a picture model the image is a smartphone video and it may draw the phone itself, black bezel and notch included, around your picture. Describe the look instead: handheld, a little soft, mixed party light.

• Describe the concha in every still

  Each still is drawn on its own, so say what a concha looks like every time: a round sweet bun with a crackly pink sugar top. Say only "concha" and you get a plain bun; call the pattern a seashell and you get a bread shaped like one.

• Keep the bread out of the last shot

  With a bitten pastry in the picture near the camera, the model tends to put it in a hand reaching in from the viewer's side while you dance off empty-handed. After a hard cut nobody misses it, so leave it out of the dance back.

• Use a clear, front-facing photo

  One person, face fully visible and looking roughly at the camera, in good light. The bite is a close-up, so the face matters more than the outfit; sunglasses, filters and far-away shots leave the model too little to work with.

• Only people who said yes

  Do not use celebrities, or the man from the original clip, or anyone who has not agreed to be in the video. A realistic video of a real person made without their consent can hurt them, and platforms take it down.

• Label it as AI-generated

  Switch on TikTok's AI-generated content label before you post. Realistic AI video of people is expected to carry it, and viewers trust a post that says so.