A cat and a dog
Each keeps its own species, face, coat and tail and stands at the counter using its front paws. One casting idea: the dog as the big one, covering its eyes, and the cat as the little one, unbothered.
Video trend
The reference has two golden retrievers, but each role keeps whatever species its photo shows. That makes the template work for a cat and a dog, two cats, or you and your pet. This page covers what to expect for each pair and how to choose the photos.
Each keeps its own species, face, coat and tail and stands at the counter using its front paws. One casting idea: the dog as the big one, covering its eyes, and the cat as the little one, unbothered.
Two cats work the same way. Cats are smaller than retrievers, so they sit lower behind the counter; that is expected, because the template keeps each animal's real proportions.
Put yourself in the big one's slot and your pet in the little one's: you pour the coffee, your pet makes the mess and you cover your eyes at the end. A person uses hands; an animal uses paws.
Two people who agreed to appear can take both roles, for example two siblings or roommates. Both wear the plain cream bib, which keeps the joke.
One subject per photo, face toward the camera, front paws or hands visible. Pick two subjects that look clearly different; two near-identical pets make it harder to tell whether the roles swapped.
Whatever the pair, the kitchen, the props, the camera moves, the timing and the song stay the same. We have not reviewed generated results for mixed pairs yet, so check yours before sharing.
Add a photo for the big one and little one.



Upload a clear photo for the Big one and the Little one. Two pets work best, ideally a bigger and a smaller one; a pet and a person, or two people who agreed to appear, work too.
Choose 480p, 720p or 1080p and review the quote. It includes the full video, both photo preparations and three scene references.
Watch that the two never swap faces, the milk stays one pool on the counter and the big one's paws cover its eyes at the end, then download your portrait MP4 with the original song.
The big one pours the coffee and the milk and covers its eyes at the end; the little one scoops the grounds, holds the mug and looks up proudly. Each keeps its own species, face, coat and markings.
All 17 seconds: the careful pour, the grounds spilling over the counter, the milk flooding past the mug in the closer shot, and the eye-covering ending, with the original song.
Both wear the cream bandana bib with the mint trim from the reference, left blank, so no name from the original clip ends up on your pets.
The preview is the AI reel the trend comes from. It is the motion and timing reference, not an Oakgen result.
It is a 17-second portrait AI clip of two golden retrievers standing at a kitchen counter in cream bibs, making coffee. The older dog pours from a black coffee pot, the puppy spoons in ground coffee and spills it, the milk misses the mug and floods the counter, and the older dog covers both eyes with its paws while the puppy looks up proudly. Oakgen's template puts your two pets, or people, in their places.
"Con la Misma Piedra" by Julio Iglesias, identified from the audio. The title means "with the same stone"; it brings to mind the Spanish expression about tripping over the same stone twice, which suits a kitchen where one mess follows another. Your video keeps that original soundtrack, and nobody on screen sings.
Yes. The big one and the little one each need a photo, so neither of the reference dogs appears in your video.
The big one stands on the left, pours the coffee and the milk and covers its eyes at the end. The little one stands on the right, scoops in the grounds, holds the mug and looks up proudly. Put your bigger or calmer pet in the big one's slot.
Yes. Each role keeps the uploaded animal's species, coat and markings, standing up at the counter and using its front paws. Bodies very different from a retriever's vary more, so review the video before sharing.
Both wear a plain cream bandana bib with a mint-green trim, the bibs from the reference with the lettering removed. Everything else comes from your photos.
Your own pets, yourself, or people who agreed to be in the video. Do not upload photos of celebrities, public figures or anyone who has not consented, and label AI videos clearly when you share them.
About 17 seconds in portrait 9:16, matching the reference from the first pour to the eye-covering ending.
No. It is the source AI reel used as the reference, not an Oakgen result. Review faces, paws and the milk before sharing.
3,748 credits per 720p video. The quote includes both photo preparations, three scene references and the complete video. Check it before generating.
Plan a story, keep your character recognizable, and make the finished clip your own.
Wizard Cat Dance, Dog Coffee Fail, Dog Car Dance and Tiramisu Dog side by side: photos needed, length, sound, costume and which pet suits which trend.
Review your finished Dog Coffee Fail AI video by timestamp: no swapped faces, the spilled grounds, the milk flood, the facepalm ending and blank bibs.
Make the Dog Coffee Fail AI video step by step: cast the big one and the little one, read the quote, check the milk spill and post the facepalm ending.
Upload 2 photos. Everything else is set.