AI Grow Up Video Generator

AI grow up video generator: a photo of your child, or of you as a child, grows up into an adult in a 5-second portrait clip. 63 credits. Fixed scenes only.

  • From 63 credits per clip
  • From your photos
  • 5s / 10s / 15s
  • 480P
  • Audio available
A school photo grows up.Made from this photo (AI-made, fictional)
  • As a childAs a child
Add your photo ↓

Loading your account…

Model

MiniMax H3 Max

Browse by task

The same person today (optional)

Sign in to upload

One clear, well-lit photo of the child with the whole face visible, alone in the picture: your own child, or you as a child. For the then-to-now scene, add a photo of the same person today. No photos of other people's children. JPG, PNG or WebP, up to 10 MB each.

What scene would you like to create?

Choose a scene. This page runs its tested scenes only; the prompt cannot be edited.

Prompt523/2000

This page runs only the scenes above, so the prompt cannot be edited.

Actual output: 5s, 9:16, 480P. Writing “4K” in the prompt does not change this resolution. Faces and details may change; successful results still cost credits if you dislike them.

More settings · 9:16 · 5s · Audio
Aspect ratio
Duration
Resolution
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.

Estimated cost: 63 credits
Sign in to generate

Sample result

5s · MP4
A school photo grows up.Made on Cicadas · MiniMax H3 Max · 5s
Made from these photos (AI-made, fictional)
  • As a childAs a child
Use this recipe

About AI grow up video on Cicadas

The AI grow up video generator takes one photo of a child and draws a short clip in which that child grows up: a head-and-shoulders portrait that starts on the child and ends on an adult. Use a photo of your own child if you are their parent or legal guardian, or a photo of yourself as a child. With one photo the grown-up is imagined by the model; add a photo of the same person today and the clip ends on that face instead. Cicadas makes it with MiniMax H3 Max: vertical, 5 seconds for 63 credits. The page runs only its own two scenes and the prompt cannot be edited. The result is a drawing, not a forecast of how a child will look.

AI grow up video examples made on Cicadas

From your photos5s · 480P

A school photo grows up.

MiniMax H3 Max, 5 seconds with sound, vertical, from one photo of a girl of about eight; back in 13 seconds. The portrait starts on the child and, after about a second and a half, blends into a woman of about thirty who smiles at the camera; for a moment the pigtails and the red cardigan fade like a double exposure. The model imagined the adult: the child has tight curls and the woman long waves. The backdrop and the framing do not change. The track is close to silent.

Made from these photos (AI-made, fictional)
  • As a childAs a child
Use this recipe ↗
From your photos5s · 480P

A toddler grows into a young man.

MiniMax H3 Max, 5 seconds with sound, vertical, from one photo of a toddler of about two; back in 14 seconds. The portrait starts on the toddler in dungarees, becomes an older boy and blends into a young man in a cream sweatshirt who smiles at the camera; the dungarees fade like a double exposure on the way. He ends at about twenty, younger than the thirty the prompt asks for. The hair stays brown. The sound is a sigh and a low whoosh, with no speech or music.

Made from these photos (AI-made, fictional)
  • As a childAs a child
Use this recipe ↗
From your photos5s · 480P

From the school photo to today.

MiniMax H3 Max, 5 seconds with sound, vertical, from two photos of the same person, as a child and as an adult; back in 29 seconds. The portrait starts on the child; the pigtails come down, the face matures step by step, the red cardigan turns into a yellow jumper, and the clip ends on the adult from the second photo, smiling. The backdrop and the framing do not change. The model redraws both pictures: it does not animate the photos themselves. The track is close to silent.

Made from these photos (AI-made, fictional)
  • As a childAs a child
  • The same person todayThe same person today
Use this recipe ↗

Why use Cicadas for AI grow up video

A child photo grows up in one take

From one photo, the model draws the child against a plain backdrop and lets the face mature into an adult. In our recorded clips a girl of about eight became a woman of about thirty, and a toddler became a young man of about twenty. Each clip passes through about a second of blend in which the earlier hair and clothes fade like a double exposure.

With a second photo, it ends on the real adult

Add a photo of the same person today and pick the then-to-now scene: the clip starts on the childhood photo and grows into the adult from the second photo. In our recorded clip the pigtails come down, the face matures step by step and the red cardigan turns into her yellow jumper.

Fixed scenes, and the price first

Because this page takes photos of children, it runs only its own two portrait scenes: the prompt is shown but cannot be changed. 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 grow up video

  1. 01

    Sign in and add one clear photo of the child with the whole face visible, alone in the picture. For the then-to-now scene, add a photo of the same person today.

  2. 02

    Pick a scene, keep 5 seconds, and check the quote.

  3. 03

    Tick the photo confirmation and generate. Save the MP4 from the result or from My videos.

AI grow up video prompt ideas

Choose a fixed scene above; this page does not accept custom or edited prompts.

  • “A head-and-shoulders portrait against a plain soft-blue studio backdrop, vertical. The clip begins on the child from Image 1 and, in one smooth take, the child grows up into an adult of about thirty, the same person years later: the face matures gradually, the hair changes with the years, and the clothes change into a plain everyday jumper. It ends on the adult smiling at the camera. The framing does not change. The camera stays still, one continuous shot, no cuts. Sound: quiet room tone, no music, no voices. No text.”

  • “A head-and-shoulders portrait against a plain soft-blue studio backdrop, vertical. The clip begins on the child from Image 1 and, in one smooth take, the child grows up into the adult from Image 2, the same person years later: the face matures gradually, the hair and clothes change with it, and it ends on the adult smiling at the camera. The framing does not change. The camera stays still, one continuous shot, no cuts. Sound: quiet room tone, no music, no voices. No text.”

AI grow up video FAQ

Tested on Cicadas · reviewed 2026-10-12

Recorded on 2026-10-12 with MiniMax H3 Max reference-to-video through fal.ai, each request sent once with the exact scene prompt of this page: 5 seconds, 9:16, 480P with sound. Grow up, from one photo of a girl of about eight: back in 13 seconds; she becomes a woman of about thirty with long wavy hair where the child had tight curls. Grow up, from one photo of a toddler of about two: back in 14 seconds; he becomes a young man of about twenty, younger than the prompt asks for. Both pass through about a second of blend in which the earlier hair and clothes fade like a double exposure. Then to now, from the girl's photo and a photo of the same person as an adult: back in 29 seconds; the pigtails come down, the face matures step by step and the clip ends on the adult from the second photo. All three keep a plain blue backdrop and a still camera, and the tracks are close to silent (two automated listeners). Tested and not used: wording that named the ages in between showed a clearer growing-up but ended on a teenager, and with the toddler it changed the child into a different one; a scene by a window ended on an older child. Babies under two, real photos, 10 and 15 seconds and 768P were not run. The photos are AI-made and fictional: no real child's photo was used in any test.

Updated Oct 12, 2026 · How we test