Cicadas.ai

CICADAS.AI / AI VIDEO TRENDS

AI video trends you can make today

An AI video trend is a clip format that spreads on TikTok, Reels and Shorts and that people remake with a generator: the gas station dance, the orange-room duet, the zombie who is still your friend. This page lists all 9 trends Cicadas can make, newest first. Each one shows a clip we recorded, the prompt behind it, what went wrong in it, and the price you see before you start.

EVERY SAMPLE IS A REAL RUNModel, settings, date and request ID are in the testing record ↗

AI video trends, newest first

The samples were recorded with AI-made photos of fictional people and pets; your photos will give a different result.

Gas Station Dance AI

  • From your photos · 1–3 photos
  • MiniMax H3 Max
  • from 63 credits
  • added Oct 5, 2026

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.

Make this trend

15s sample · 480P. MiniMax H3 Max, 15 seconds with sound, vertical, from three photos. The dance, the walking selfie and the car exit each keep the face and outfit of their photo. The lettering on the pumps and signs is made up, and the selfie cut shows the phone in his hand.

What went wrong in this sample: made-up lettering on the pumps and signs.

The prompt behind this sample

Vertical phone footage at a gas station forecourt at dusk, three hard cuts. Shot 1: the person from Image 1 dances freestyle beside a fuel pump, loose shoulders and quick footwork, filmed full-body by a friend. Shot 2: the person from Image 2 walks toward the camera filming a selfie video, grinning, the pumps and a parked car behind. Shot 3: the person from Image 3 steps out of the passenger door of a parked silver hatchback, shuts the door and strikes a pose. Keep each face, hair and outfit as in its photo. Warm low sun, handheld camera. Sound: an upbeat electronic dance beat, no vocals. No text, no logos, no brand names on the pumps.

Open with this prompt

Hotel Lobby AI

  • From your photos · 2 photos
  • MiniMax H3 Max
  • from 63 credits
  • added Oct 5, 2026

Make a Hotel Lobby AI video from two photos, people or pets: a duet at one hanging mic in an orange room. 10 seconds costs 125 credits. No song included.

Make this trend

10s sample · 768P. MiniMax H3 Max, 10 seconds with sound at 768P, vertical, from two photos. A locked-off full-body shot: both faces and outfits match the photos as they trade lines. A studio ceiling with spotlights shows above the orange wall, and the model added a rapped voice in made-up words although the prompt asked for no vocals.

What went wrong in this sample: a studio ceiling shows above the orange wall, and the voice is made-up words.

The prompt behind this sample

Vertical 9:16, one locked-off wide shot in a seamless bright orange studio, both people in frame from head to shoes for the whole clip. The person from Image 1 stands on the left and the person from Image 2 stands on the right, facing each other across one silver microphone that hangs from the ceiling between them. They take turns leaning toward the microphone and rapping with relaxed hand gestures, then nod along together. Keep both faces, hair and clothes exactly as in the photos. The camera never moves or cuts. Even studio light. Sound: a laid-back hip-hop drum beat, no vocals. No text, no logos.

Open with this prompt

AI Zombie Trend

  • From your photos · 2 photos
  • MiniMax H3 Max
  • from 63 credits
  • added Oct 5, 2026

Make the AI zombie trend from two photos: your pet, partner or friend turns, you stay, then a happy memory. 10 seconds costs 125 credits. No gore, no weapons.

Make this trend

10s sample · 480P. 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.

What went wrong in this sample: in the dark half the dog looks like a different, grey dog.

The prompt behind this sample

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.

Open with this prompt

Hug My Younger Self AI

  • From your photos · 2 photos
  • MiniMax H3 Max
  • from 63 credits
  • added Oct 5, 2026

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.

Make this trend

5s sample · 480P. MiniMax H3 Max, 5 seconds with sound, vertical, from an adult photo and a childhood photo. They look at each other, smile and end in a sideways hug; the curls, the cardigan and the sweater match the two photos. The hug comes only in the last second or so, and the birdsong is very quiet.

What went wrong in this sample: the hug only comes in the last second or so.

The prompt behind this sample

A quiet park bench on a sunny afternoon, vertical. The adult from Image 1 sits beside the child from Image 2, who is the same person years earlier. They look at each other and smile, then the child leans in and the adult gives a gentle sideways hug around the shoulders. Keep both faces, hair and clothes as in the photos. Soft natural light, slow push-in, warm nostalgic mood. Sound: soft birdsong and a light breeze, no music. No text.

Open with this prompt

Human Pigeon AI

  • From your photos · 1 photo
  • MiniMax H3 Max
  • from 63 credits
  • added Oct 5, 2026

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.

Make this trend

5s sample · 480P. MiniMax H3 Max, 5 seconds with sound, vertical, from one portrait. The human-faced pigeon is there from the first frame, grins and flaps its wings between two ordinary pigeons. The head is much larger than a pigeon's, and it keeps smiling instead of pecking.

What went wrong in this sample: the head is much larger than a real pigeon’s.

The prompt behind this sample

Realistic vertical phone footage of a park bench. From the first frame, a pigeon with the human head and face of the person from Image 1, at pigeon scale, stands on the back of the bench. It tilts its head, puffs its chest, coos at the camera and flaps its wings once. Two ordinary pigeons sit beside it. Keep the face and hair as in the photo. Park sounds and pigeon cooing, no music. Handheld shot, soft daylight, no text.

Open with this prompt

Popcorn Volcano AI Video

  • Prompt only
  • MiniMax H3 Max
  • from 63 credits
  • added Oct 5, 2026

Make a popcorn volcano AI video from a prompt: corn poured from a helicopter into a lava crater, then a popcorn eruption. 10 seconds at 768P costs 200 credits.

Make this trend

10s sample · 768P. MiniMax H3 Max, 10 seconds with sound at 768P, vertical, from text only. Kernels pour from a red bucket at the helicopter door and the crater bursts into a popcorn cloud that fills the frame. The sound is a loud engine-like rumble; our automated listeners heard no distinct popping.

What went wrong in this sample: a loud rumble with no distinct popping sound.

The prompt behind this sample

Vertical phone footage shot from the open door of a helicopter hovering above a glowing lava crater. A gloved hand tips a large red bucket and a stream of dry corn kernels pours down into the lava. A beat later the crater erupts in a huge white cloud of popcorn that shoots up past the helicopter, and the camera jolts back. Sound: rotor noise and wind, a deep rumble, then loud rapid popping. Realistic daylight footage, no faces, no text, no logos.

Open with this prompt

AI ASMR video

  • Prompt only
  • Veo 3.1 Fast
  • from 100 credits
  • added Oct 1, 2026

Make an AI ASMR video: glass fruit cutting, kinetic sand or soap carving with crisp sound, in a vertical 8-second Veo 3.1 Fast clip. See the quote first.

Make this trend

8s sample · 720p. Veo 3.1 Fast, 8 seconds, 9:16, with sound. A knife cuts one slice off a translucent kiwi, which falls flat onto the board; a hand steadies the fruit. Our listener heard a thump and a light clatter rather than the crisp glassy crunch the prompt asked for.

What went wrong in this sample: a thump and a clatter instead of a crisp glassy crunch.

The prompt behind this sample

Extreme macro close-up, vertical. A sharp chef's knife slowly slices a translucent glass kiwi on a dark wooden board. Each slice cracks with a crisp, glassy crunch and falls with a delicate clink. Soft studio light, shallow depth of field, locked camera, one continuous shot, no music, no speech, no text.

Open with this prompt

AI Bigfoot video

  • Prompt only
  • Veo 3.1 Fast
  • from 100 credits
  • added Sep 30, 2026

Make an AI Bigfoot vlog: Bigfoot talks to the camera in a vertical 8-second clip with voice and forest sound, made with Veo 3.1 Fast. See the quote first.

Make this trend

8s sample · 720p. Veo 3.1 Fast, 8 seconds with sound, vertical. Bigfoot holds the camera at arm’s length in a sunlit pine forest and says the whole line word for word, with footsteps and heavy breathing under it.

The prompt behind this sample

Handheld selfie vlog, vertical. A friendly, shaggy Bigfoot holds the camera at arm's length in a misty pine forest at sunrise and says in a deep, cheerful voice: "Morning, everybody. Big day. I'm finally trying the trail mix you all keep leaving out." Birdsong, soft wind and twigs crunching under his feet. Natural phone-camera shake, one continuous shot, no text or logos.

Open with this prompt

AI rap video

  • Prompt only
  • Veo 3.1 Fast
  • from 100 credits
  • added Sep 30, 2026

Write the bars and get an AI rap video with the beat, voices and characters rapping on screen, made with Veo 3.1 Fast. Original characters only; quote first.

Make this trend

8s sample · 720p. Veo 3.1 Fast, 8 seconds with sound, vertical. Two original cartoon cats rap both written lines word for word over a hip-hop beat with scratches; partway through, the shot cuts from a wide view to a closer one.

What went wrong in this sample: the shot cuts from wide to close partway through.

The prompt behind this sample

Two original cartoon cats in tiny hoodies stand on either side of one hanging microphone in a small recording studio with foam panels. They trade short rap lines over a simple boom-bap beat. The orange cat raps: "Woke up at noon, still the king of the couch." The grey cat answers: "Knocked your cup down, now you're yelling ouch." Mouths move with the words, heads nod to the beat, locked medium shot, one continuous take, no text or logos.

Open with this prompt

How to make an AI video trend on Cicadas

  1. 01

    Pick the trend

    Each trend has its own page with the scene prompt already written and the default length and format chosen (most are vertical 9:16).

  2. 02

    Add your photos, or edit the prompt

    Pages marked “From your photos” take 1–3 photos: you, adults who agreed to be in the clip, or your pet. The other pages need only the prompt.

  3. 03

    Confirm the price, generate, download

    The exact credits show before you press Generate, and nothing is charged until you confirm. The result is a private MP4 in your account; a provider failure refunds the credits automatically.

AI video trend prompts: what we learned recording these

Each point below comes from a clip on these pages, including the takes we threw away and recorded again.

Name people by photo order

Writing “the person from Image 1 stands on the left” kept both faces and both outfits matched to the photos in the orange-room duet.

For a full-body shot, say “from head to shoes”

Our first 768P duet was cropped at the thighs and jumped once. Adding “from head to shoes” and “the camera never moves or cuts” gave a locked full-body shot on the next take.

Put the subject in the first sentence

In the first take of the street pigeon clip the subject was described late, and the flock was ordinary pigeons until a cut. We moved it to the first sentence and recorded again; in the published clip the face is still small until halfway.

“No vocals” is not always obeyed

Both orange-room samples asked for a drum beat with no vocals, and the model still added a rapped voice in made-up words. For a clean track, replace the sound in your editor.

Do not count on lettering

The pumps and signs in the gas station sample carry made-up letters. Add any text that has to be read afterwards.

Sound follows the picture loosely

The popcorn volcano sample has a loud rumble and no distinct popping; in the ASMR sample the glass fruit gives a thump, not a crisp crunch.

What these pages do not do

Content policy

Questions about AI video trends

What is an AI video trend?

A short-video format that spreads on social apps and that people remake with an AI video generator. It usually has a fixed setting and a fixed action, and sometimes a fixed song: the gas station dance, the orange-room duet, hugging your younger self.

Which AI model makes these trend videos?

This list uses MiniMax H3 Max and Veo 3.1 Fast. The pages that take your photos run on MiniMax H3 Max, which can draw the people or pets in your photos into a new scene. Every page names the model it uses.

How much does an AI trend video cost?

The cheapest clip on this list starts at 63 credits; the price depends on the model, the length and the resolution. You see the exact credits before each run and nothing is charged until you confirm. A provider failure is refunded automatically.

Can I use my own photo?

Yes. 5 of the pages are marked “From your photos” and take 1–3 photos: you, adults who agreed to be in the clip, or your pet. You confirm that before generating. Photos of children are not accepted; only the younger-self page takes one, and it must be a childhood photo of you.

Is the trend’s song included?

No. Clips come with sound the model generated (a beat, ambience or a spoken line) but not the trend’s song. You can add music in the app you post on.

Can I post these on TikTok or Instagram?

The clips are vertical MP4 files you can upload as they are. Label them as AI-generated where the platform asks for it, and use only photos you have the right to use.

How often are new trends added?

We add a page when a trend has a fixed format we can reproduce with a real sample. The list is ordered by the date each page was added, and every entry shows that date.

Keep going

Image to video Skip the trend and animate any picture.Prompt library The prompt, settings and cost of every clip we recorded.Compare all models Prices, lengths and recorded samples for each model.Pricing How credits work and how refunds happen.