From two portraits to a stadium screen moment
By Tip Toe AI Team · Updated:
Short answer
Give Tip Toe AI two photos of adults and it stages the whole moment: choose the venue, how the pair react and the outfits, and a vertical MP4 comes back. Nothing needs typing.
The steps
- Open the generator and drop a portrait into each slot, one person per slot.
- Choose the presets: the venue, the reaction and the outfits.
- Check the frame: the video is 9:16, made for phone screens.
- Sign in with Google and confirm the photo consent.
- Top up credits if your balance is short; a pack is paid once.
- Render: a full video uses 100 credits. Save the MP4 and add your own sound.
What is already decided
The round screen, the hug, the moment of noticing and the reaction come in a set order, shot by one fixed camera. Your photos supply the faces and the presets supply the surroundings.
Because the order does not vary, a sound placed once keeps lining up with the reaction, even though every run looks a little different.
After the render
The file waits in My videos for download or a share link. For help with audio, open the sound guide.
Quick answers before you go up on the big screen
Do I need to type anything?
No. You add two photos and tick a few presets.
Which photos work best?
Sharp portraits of two adults, evenly lit, each looking at the camera and framed from the chest up or wider.
Does closing the tab stop the render?
No. It carries on and the clip lands in My videos.
Is the video tall or wide?
Tall, 9:16, the shape short-video feeds expect.
Ready to be on the big screen?
Two portraits, a venue and a reaction you choose. A pack is a single payment, nothing renews, and a render that fails returns its credits.
Make my video