AI Zombie Trend Video Generator
Make the AI zombie trend from two photos: your pet or friend turns, you stay, then a cut to a happy memory. 10 seconds costs 125 credits. No gore, no weapons.
- From 63 credits per clip
- From your photos
- 5s / 10s / 15s
- 480P
- Audio available
MiniMax H3 Max
Who turns (pet or friend)
Sign in to uploadClear, well-lit photos, one subject each. Your pet, yourself, or a friend who agreed. People must be adults; no photos of children. JPG, PNG or WebP, up to 10 MB each.
What scene would you like to create?
A scene fills the prompt below. It calls your photos Image 1, Image 2 and so on; keep those names when you edit it.
More settings · 9:16 · 10s · Audio
Checking generation and private storage configuration.
Billing and delivery
Generate charges the displayed quote for the current length and resolution. If generation fails or the file fails our check, the credits come back automatically; a finished clip you don’t like is still charged. Finished clips stay in My videos.
Sample result
10s · MP4
Who turns (pet or friend)
You
About AI zombie video on Cicadas
The AI zombie trend is a short two-part story: someone you love, a pet or a friend, appears as a zombie, you do not run, and the clip cuts to a warm memory of the two of you. Cicadas makes it from two photos with MiniMax H3 Max as a vertical clip of 5, 10 or 15 seconds with natural sound. Our scenes leave out the gun, blood and wounds used in many versions. A 10-second clip is 125 credits. The sofa scene is a continuous shot without the memory cut.
AI zombie video examples made on Cicadas
Still my friend: the dog in the hallway.
MiniMax H3 Max, 10 seconds with sound, vertical, from a photo of a dog and a photo of its owner. In a dark hallway the zombie dog sniffs her hand and presses against it; after a hard cut the same dog leaps for a ball in a sunny yard. In the dark half its coat is drawn grey and shaggy, so it looks like a different dog until the cut.
Who turns (pet or friend)
You
He didn't run.
MiniMax H3 Max, 10 seconds with sound, vertical, from two photos. On an empty street the zombie, in his friend's denim jacket and hoodie, stops and hugs him; after a hard cut both laugh on a sofa. The zombie has a generic zombie face, so until the cut the friend is recognisable only by his clothes.
Who turns (pet or friend)
You
Why use Cicadas for AI zombie video
The Still My Friend story, with your own pet
Photo 1 is who turns, photo 2 is you. In our recorded dog clip the zombie dog stands in a dark hallway, sniffs the owner's hand and presses against it, then the clip cuts to the same dog leaping for a ball in a sunny yard.
An AI zombie video without gore or weapons
Many versions aim a gun at the zombie. These scenes ask for no blood, wounds or weapons, which also keeps a clip inside platform and model rules. The sound is natural, with no music: in our clips, growling and sniffing in one, footsteps and a laugh in the other.
See the price of every AI zombie video first
At 480P, 5 seconds is 63 credits, 10 seconds is 125 and 15 seconds is 188; at 768P they are 100, 200 and 300. A failed generation returns its credits.
How to use AI zombie video
- 01
Sign in and add two photos: who turns (your pet, or a friend who is in on it) and you.
- 02
Pick a scene (pet, friend or the sofa night), keep 10 seconds for both parts, and check the quote.
- 03
Tick the photo confirmation, generate, then download the MP4 from My videos and add your own music when you post.
AI zombie video prompt ideas
Copy one into the prompt box above and adapt it to your shot.
“A short story in two parts with one hard cut, vertical. Part 1: a dim, dusty abandoned house at dusk. The pet from Image 1 stands in the hallway as a zombie: fur matted and grey with ash, eyes pale and cloudy, growling low. The person from Image 2 kneels and slowly holds out a hand. The pet stops growling, sniffs the hand and presses its head against it. Part 2, hard cut: a bright sunny backyard, the same pet healthy and clean, leaping to catch a ball the person throws, both happy. Keep the pet and the person as in the photos. Natural sound only, no music. No blood, no wounds, no weapons, no text.”
“A short story in two parts with one hard cut, vertical. Part 1: an empty city street at dusk, abandoned cars and drifting paper. Only two figures. The person from Image 1 shuffles forward as a zombie but stays recognisable: the same face, hair and clothes as in the photo, with grey skin, pale cloudy eyes and dust on the clothes, arms slightly raised. The person from Image 2 stands still, facing them, and does not run. The zombie stops one step away, lowers its arms and leans in for a slow hug. Part 2, hard cut: a warm living room, the same two people healthy and laughing on a sofa. Keep both faces, hair and builds as in the photos. Natural sound only, no music. No blood, no wounds, no weapons, no text.”
“One continuous shot, vertical: a cosy living room at night lit by a television. The pet from Image 1 sits on the sofa as a zombie: fur matted and grey with ash, eyes pale and cloudy. The person from Image 2 sits beside it and holds out a bowl of popcorn. The pet sniffs, gently takes one piece and leans against the person, who scratches its head. Keep the pet and the person as in the photos. Natural sound only, no music. No blood, no wounds, no weapons, no text.”
AI zombie video FAQ
Tested on Cicadas · reviewed 2026-10-05
Recorded on 2026-10-05 with MiniMax H3 Max reference-to-video through fal.ai: two 10-second clips, 9:16 at 480P with sound, 125 credits each here: a dog and its owner, and two friends. The provider returned them in 20 and 16 seconds. Both have a hard cut from the zombie half to the healthy half. The zombie dog was drawn grey and shaggy and the zombie friend had a generic face; the healthy halves matched the photos. No music in either soundtrack (two automated listeners). A first friend run showed two bald zombies; its wording was changed and it is not shown. The sofa scene, 768P, and 5 and 15 seconds were not run.
Updated Oct 5, 2026 · How we test
Related tools
MiniMax H3 Max · Recorded Cicadas sampleGas Station Dance AI Video Generator
Make the gas station dance AI trend from 1 to 3 photos: vertical cuts or a group dance, 5 to 15 seconds. 10 seconds costs 125 credits. No song included.
MiniMax H3 Max · from 63 credits
Tested 2026-10-05
MiniMax H3 Max · Recorded Cicadas sampleHug My Younger Self AI Video
Make a hug my younger self AI video from two photos, you now and you as a child. A 5-second park-bench hug costs 63 credits. Both photos must be of you.
MiniMax H3 Max · from 63 credits
Tested 2026-10-05
MiniMax H3 Max · Recorded Cicadas sampleHuman Pigeon AI Video Generator
Make a human pigeon AI video from one portrait: a pigeon with your face bobs, coos and flaps among ordinary pigeons. A 5-second clip costs 63 credits.
MiniMax H3 Max · from 63 credits
Tested 2026-10-05