One fixed shot
The reference is a single phone shot across a café table with no cuts. It sets every sip, glance and laugh, and every move of the dance, from the first frame to the last.
Video trend
Coffee Cat trend
Two at a café table share iced coffees, then the one on the left stands up and dances.
- Final video
- 15 seconds
- Your input
- 2 photos
- Quality
- 720p
MADE WITH OAKGEN15 SEC / 9 / 16
How to make it
Add a photo for both roles: the whole scene is redrawn from your photos. The moves and the camera are already set.
Left seat (the dancer)Right seat- 01
Add two photos
Upload one clear photo for each seat. The left seat is the one who stands up and dances.
- 02
Choose a quality
Select 480p, 720p or 1080p. The price shown includes preparing both photos.
- 03
Review and share
Check the clip from the first sip to the last dance move, then download your 15-second vertical MP4.
Two seats, one dance
Each seat takes one photo. The left seat pats the right seat's chin, then stands up and dances; the right seat stays at the table and swoons. Choose who sits where.
Everyone keeps their look
Each photo is prepared with a faint facial wireframe, then used as the character reference, so the face, build and look visible in it carry into the video. Nothing of the originals is kept.
The original audio
Oakgen copies the reference audio into your finished video, so the dance lands on the beat. Review your AI video before you share it.
Photo tips
- Clear face in good light
- Upper body and outfit visible
- One face per photo
- Looking towards the camera
- No sunglasses or face coverings
- Use photos you have permission to use
Questions & answers
What is the coffee cat AI trend?
It is a Reels format in which two share iced coffees at a café table at night. One pats the other's chin, the other swoons, and the first stands up and dances. The version that spread had a giant cat as the dancer. This Oakgen template recreates a 15-second version from your two photos.
How do I make a coffee cat AI video?
Open the Coffee Cat tool, add a photo for each seat, choose a quality and generate. The scene, the camera and the audio are already set, so there is no prompt to write.
Do I need two photos?
Yes. The whole scene is redrawn, so both seats need a photo. The left seat is the one who stands up and dances; the right seat stays at the table and swoons.
Does it use my outfit as well as my face?
Yes. Your photo is prepared with a faint facial wireframe while preserving the face, hair, build and clothing visible in it, so you appear in the clothes you upload. AI results can vary, so review the finished video.
Is real footage edited?
No. A line-drawing of the reference clip sets the movement and framing. The picture, including the two at the table and the café, is generated to match it.
Can I choose the video quality?
Yes. Choose 480p, 720p or 1080p before generating. The default is 720p. Higher resolutions cost more; your selected price is shown before you start.
What photos can I use?
Use clear photos you have permission to use, each showing one face with the whole look visible. The model can reject photos, including realistic photos of people; a rejected generation is refunded.
How much does it cost?
1,983 credits per 720p video. This includes preparing both photos. The selected price is shown before you generate.
How long does it take?
Render time varies with quality and demand. You can leave the page while it runs; the finished video is saved to your assets. Failed generations receive an automatic credit refund.
What is the video on this page?
It is an Oakgen video made with this template, so you can see what you will get. Oakgen is independent and is not affiliated with the creator of the Reel that started the trend.
Can I download and share it?
Yes. Review your video, then download the MP4 from the tool or your assets.
Make your Coffee Cat video
Upload a photo. Everything else is set.