Skip to main content

Video trend

AI Dog Ordering Tiramisu Video: How to Make It

“Dog ordering tiramisu” is a plain description of this format rather than an established trend name: a pet at a bakery window, guiding the seller’s every move with deadpan paw signals. Tiramisu Dog turns one photo into that full scene. This page walks through the decisions you actually make and the ones the template makes for you.

Final video
18.04 seconds
Your input
1 photo
Quality
720p
REFERENCE RECREATION18.04 SEC / 9 / 16
Tiramisu DogSource: @m.a.n.g.o__o · Dead Serious Tiramisu AI reel

From one photo to the full order

01

What you choose and what stays fixed

You choose one thing: who stands at the window. Everything else comes from the reference reel and does not change, including the shop interior, the tiramisu tray and ladyfinger biscuits, the seller’s hands and cake server, the gold “Kuruluş 1958” lettering, the street outside, the handheld camera move and the order of gestures. You cannot swap the dessert, add a second customer or change the location. If you want a different food or shop, this template is the wrong starting point.

02

Step 1: upload the customer

Open Tiramisu Dog and add one photo to the Window customer slot. A dog is the natural fit because the reference customer is a golden retriever, but the slot also accepts a cat or another pet, or a person. The template keeps species: a dog stays that dog, a cat stays a cat with its own coat and markings, and a person stays a person. Use a clear, well-lit photo of a single animal or person. The pet photo guide covers which shots work best.

03

Step 2: choose quality and review the price

Choose 480p, 720p or 1080p. The studio shows the price for your choice before anything is generated, and that quote covers preparing your photo and the scene as well as the video itself. Nothing is charged until you confirm. Higher resolution is a sensible choice for a pet with fine coat detail or markings, since those details carry the likeness.

04

Step 3: what comes back

The result is a single portrait 9:16 video of about 18 seconds, the full length of the reference, with no cuts. It keeps the original sound from the source: street ambience plus the scrape of the cake server and the rustle of the box paper. There is no speech, barking or song, so nothing needs translating or re-recording. If you want music, add it in your editor and make sure you have the rights to it.

05

Step 4: check the order before sharing

Watch the result once at full speed and once frame by frame around the gestures. Check that the customer’s face stays serious, that paws or hands stay on the window side of the glass, that the cake server and the slice stay one server and one slice, and that the bib, if your pet gets one, carries no lettering. The paw gesture breakdown lists where each of these moments falls.

06

Why it works as a short

The humour is restraint. Nothing loud happens: a customer who takes a dessert purchase far too seriously supervises a careful cut, signs approval and visibly despairs at the packaging. That reads instantly on a phone with the sound off, which suits feeds where many people scroll muted. A pet already known to your followers for a serious expression is the strongest casting, but that is an editorial suggestion, not a tested result.

Explore the Tiramisu Dog trend

How to make it

Choose the roles you want to change. Add a photo for each selected role.

Window customer in the Tiramisu Dog source video
Window customer
  1. 01

    Choose the customer

    Upload one clear photo of your pet or yourself, facing the camera with the face, ears and coat or hair visible. Upright or sitting pets work best.

  2. 02

    Review quality and price

    Choose 480p, 720p or 1080p and review the credit quote. It includes the video plus the photo and scene preparation for your customer.

  3. 03

    Check the order

    Watch the paw or hand gestures, the facepalm and the final stare, then download your portrait MP4 with the original sound.

01

Your pet at the window

One photo casts the customer outside the shop glass. A dog stays a dog and a cat stays a cat, with its own coat and markings; a person works too.

02

The whole deadpan order

The full 18-second take keeps the thumbs-up while the slice is cut, the measuring paws, the facepalm at the box and the final stare.

03

The shop stays the same

The camera stays behind the counter with the tiramisu tray, the seller's hands, the gold window lettering and the street behind.

04

An attributed AI source

The preview is @m.a.n.g.o__o's AI reel captioned "Dead Serious Tiramisu". It is a source reference, not an Oakgen-generated result. The original dog's name on its bib is not copied into your video.

Photo tips

  • One pet or person per photo
  • Face, ears and coat clearly visible
  • Looking towards the camera
  • No other animals in the photo
  • Check the paws near the cake server

Questions & answers

What is the Tiramisu Dog trend?

It is a fixed shop-window scene: a customer stands outside the glass and, with a completely serious face, directs where the tiramisu gets cut, measures the slice, facepalms at the box and stares. Tiramisu Dog is Oakgen's descriptive name for the supplied AI reel.

Is this the Dead Serious Tiramisu reel?

Yes. The reference is @m.a.n.g.o__o's AI reel captioned "Dead Serious Tiramisu", with a golden retriever as the customer. In Oakgen, your uploaded photo replaces that dog.

Does it work with a cat or another pet?

Yes. The template keeps the uploaded animal's species, coat and markings and adapts the gestures to its paws. Results vary with unusual body shapes, so review the video before sharing.

Can I use a photo of myself?

Yes. A person stays a person and makes the same gestures with their hands at the window. Upload a clear photo with the outfit you want.

Will my pet wear the bib with the dog's name?

No. The name on the original dog's bib is not copied. An animal without clothing may get a plain white bib with no text.

How many photos do I need?

One. The single photo casts the customer for the whole clip. The seller's hands, tray and street are part of the fixed scene.

How long is the video?

The output is about 18 seconds in portrait 9:16 format, matching the full reference.

Does it keep the original sound?

Yes. The final MP4 keeps the reference's street and serving sounds. There is no speech or song to replace.

Is the preview generated by Oakgen?

No. It is the attributed source AI reel, which is low resolution. Generated likeness and paw contact can vary; review your result before sharing.

How much does it cost?

3,869 credits per 720p video. The quote includes one character preparation, three scene references and the full video. Review the selected resolution's quote before generating.

Ideas for your next video

Plan a story, keep your character recognizable, and make the finished clip your own.

Explore the video trend playbook →

Make your Tiramisu Dog video

Upload 1 photo. Everything else is set.

Make this video