Face clear and sharp
Upload a clear photo of a pet (or you), face and markings sharp enough to read at building scale. Soft, tiny, or cropped-out subjects make identity drift.
Viral template
A short giant pet in the city: your photo keeps that motion. Genjutsu AI holds the timing. Stills change the look.
About 10 seconds
On this page
The panel below is the homepage studio, already on this template. The sample is the giant pet in the city motion reference.
Reference video

Giant Cat AI
10s · 840 credits · Seedance 2.5
Giant Cat AI is a Genjutsu AI photo-to-video template on genjutsuai.app. The reference clip is a huge pet peering in from outside a high-rise window while a helicopter circles a city skyline, then filling the frame as if the animal were as tall as the towers. Your still changes who is on screen; the sample keeps the staging.
Anyone who wants their pet — or themselves, as a joke — scaled up into that city-size walk, with permission for any pet photo.
The sample holds a huge pet peering in from outside a high-rise window while a helicopter circles a city skyline, then filling the frame as if the animal were as tall as the towers. A photo changes who is on screen; it should not rewrite the staging.
Background
Giant Cat is the hyper-real joke of a house pet scaled up to skyline height: a cat peering through a high-rise window, a helicopter circling, people staring up from the street. The footage plays it straight, like a disaster clip where the monster is just someone’s cat.
The wave grew with new video models in late 2025. On 22 October 2025 @mamacathome posted a giant white cat on CCTV (later about 3.3 million views). On 5 November 2025 @longliveai wrote that the internet was “flooded with hyper-realistic clips of a gigantic cat.” In 2026, accounts such as @thegiantcatworld and pet owners like @pixcelthecat kept posting New York walks. By 9 November 2026, #giantcat held about 10,250 TikTok videos and 409.7 million views.
This page is an independent Genjutsu AI photo-to-video remake of that giant-pet city beat. Genjutsu AI is not affiliated with MakeViral, CapCut, or Higgsfield.
How it works
01
This page opens with the Giant Cat AI clip already chosen. That file is the motion, the staging, and the timing.
02
A photo is optional. With no photo, the template still generates from the sample. Upload a clear pet photo so the giant city walk can keep the face, fur and markings at building scale.
03
Press Generate. The button shows credits for this length and quality first. Keep source audio on by default unless you want a silent export.
Photo tips
The set, the timing, and the camera are already in the sample. The still only has to show the subject clearly.
Upload a clear photo of a pet (or you), face and markings sharp enough to read at building scale. Soft, tiny, or cropped-out subjects make identity drift.
Ordinary daylight or clean indoor light is enough. Soft focus, heavy beauty filters, and extreme HDR make identity drift.
The sample already has the giant pet in the city staging. A photo with extra people or clutter makes the remap harder.
Use a photo of yourself, or of a friend who already agreed (or a child/pet you have permission for). Some templates ask you to skip children’s photos — follow that note when it appears.
Credits
The Generate button shows the credit price before you start. It follows the reference length and the quality you pick. A longer sample costs more, and 1080p costs more than 720p or 480p.
Sample length is the default. If a duration is missing, the studio measures the file, then shows credits. Your own reference video is priced from that file. Clips that are too long are rejected before a job starts.
Leave mute off for a soundtrack from the model, or check mute and add music later. Mute does not change the camera or the timing. A failed job returns the credits.
Use cases
The motion and the timing stay. The look changes.
Upload a clear pet photo and leave the sample. You get a short clip of that animal at building height outside a high-rise window.
One clip per subject who already said yes (or whose owner/guardian said yes). Separate photos keep each identity clean.
Run two photos through the same sample when you want to see which still holds the beat. Staging and timing stay fixed.
Generate with no photo to watch the motion, or to check credits and length. Add a photo on the next run.
Examples
The player at the top is the Giant Cat AI motion reference: a huge pet outside a city high-rise while a helicopter circles the skyline. That timing is what Genjutsu AI keeps when a photo changes the look.
Other published templates use the same photo-to-video studio. Each one keeps its own sample motion, and you can open it to generate on that template’s page.
A Genjutsu AI photo-to-video template of a huge pet peering in from outside a high-rise window while a helicopter circles a city skyline, then filling the frame as if the animal were as tall as the towers. Upload a photo to change who is on screen; keep the sample for motion and timing.
No. The clip generates from the template alone. Upload a photo when you want the look to change — with permission.
The aim is to keep the sample’s a huge pet peering in from outside a high-rise window while a helicopter circles a city skyline, then filling the frame as if the animal were as tall as the towers. Extreme crops or busy group shots make remapping harder.
Look at the Generate button. The shipped sample is about ~10s. The price follows that length and the quality you pick.
Yes. Source audio stays on uploads by default for this template. Mute in the studio if you want a silent export.
A clear pet photo (or a person, for a joke take), face and markings large and sharp. Skip group shots and tiny distant subjects.