How do I turn two photos into a Bing Bing Bing Kicking video?
Updated:
Short answer
Add one photo for each character, an adult or a pet (or the same photo twice), and Tip Toe AI builds the street around them. Choose a place and an outfit, then spend 100 credits on the 12-second 720p video. Nothing needs typing, and you can close the tab while it renders.
The steps
- Begin in the generator and add a photo for the left and right characters.
- Pick the setting: street corner, living room, park path or car park, dressed in your own look, tracksuits or hoodies.
- Choose the frame: tall 9:16 for phones and short-form feeds, wide 16:9 for YouTube.
- Accept the photo consent and sign in with Google.
- Top up credits if your balance is empty. Packs are one-off and never renew.
- Render the full video for 100 credits, download the MP4, and lay the sound over it from second zero.
What is already decided
The ground-level camera, the bobbing, the walk forward, the order of the kicks and the blocking hand are baked into one scene that follows the viral clip. There's no prompt box: your photos only decide who kicks.
Beats arrive in the same order on every run, so a sound started at zero stays close to the action. Faces and small details still differ between runs.
Afterwards
Once finished, your clip sits in My videos for downloading or sharing by link. For the sound, see the sound guide.
Tip Toe AI is independent and has no connection to the creators of the original clips.
Questions people ask
Do I have to write anything?
No. The scene and camera are preset. You only choose photos, a place, an outfit and a frame shape.
May one photo stand in for both characters?
Yes. Put the same picture in both boxes and you get two copies of that subject, each kicking in turn.
Does leaving the page stop the render?
No. It carries on, and the finished video appears in My videos.
Tall or wide: which one?
9:16 suits TikTok, Reels and Shorts, and 16:9 suits YouTube and desktop screens. Both are open to every video.
Take your turn at the lens
Add two photos, or one photo twice, and you're both swinging at the camera. No subscription is involved, and the finished video carries no watermark.
Make my video