Making an Oh You Can Make It Cap AI video, step by step
Updated:
Short answer
Add a photo of whoever laughs and one of whoever spins (a single photo twice works too); Ozil Goal AI supplies the scene. A 5-second bonus preview lets you check them, and 1 credit buys the 14-second 720p video. No prompt, and the page can be closed meanwhile.

Step by step
- Start in the generator on the template page: one photo for the laugher, one for the spinner. Neither box may stay empty, though both can hold the same picture.
- Style it. Pick the bag (red handbag, gold mini bag, paper shopping bag or puppy) and the outfit (own clothes, white tee with blue dress, all black or party).
- Pick a format. TikTok, Reels and Shorts want tall 9:16; YouTube and desktop screens want wide 16:9.
- Tick consent and sign in with Google.
- Check with a bonus preview (5 seconds, 480p): both faces and their movement show up there.
- Spend 1 credit on the full video, then download the MP4.
Why nothing is typed
The studio, the static camera, the request, the twirl and the laughing fit are baked into one scene that mirrors the viral AI remake's cuts, and your photos only settle who gets which part.
Each run varies in faces and movement, and nothing is scripted to be said.
Afterwards
Finished clips wait in My videos, ready to download or share by link. For the trending sound, see the sound guide.
Ozil Goal AI stands on its own: the show, its cast and the people who posted the original clips have no part in it.
Questions people ask
Is there a prompt box?
No. The setup brings the studio and camera; you only pick photos, a bag, an outfit and a shape.
Can one photo play both people?
Yes, as a clone: you appear twice, once laughing and once spinning. Two different photos look more natural and are less likely to blend into one face.
Must I stay on the page?
Yes, close it. The job runs on our servers; come back later and the video is in My videos.
Tall or wide?
Tall 9:16 for TikTok, Reels and Shorts; wide 16:9 for YouTube or a computer screen. Previews work in both.
Your photos, your spin, your laugh
Two photos in, 14 seconds of HD video out, from $8.88. Nothing to subscribe to, and the file carries no watermark.
Make my video