Cicadas.ai

Rumpelstiltskin AI Video Generator

Rumpelstiltskin AI: make the tiptoe dance meme as a 5-second clip in a castle hall, on a green screen or in a supermarket. 63 credits, no photo needed.

  • From 63 credits per clip
  • Text to video
  • 5s / 10s / 15s
  • 480P
  • Audio available
Through the torch-lit hall, on tiptoe.Made from text alone, no photo neededPick a scene ↓

Loading your account…

Model

MiniMax H3 Max

Browse by task

What scene would you like to create?

A scene fills the prompt below; edit it freely. No image upload needed. The recorded results are in the examples on this page.

Prompt609/2000
More settings · 9:16 · 5s · Audio
Aspect ratio
Duration
Resolution
Audio

Checking generation and private storage configuration.

Estimated cost: 63 credits
Sign in to generate

Sample result

5s · MP4
Through the torch-lit hall, on tiptoe.Made on Cicadas · MiniMax H3 Max · 5s
Use this recipe

About Rumpelstiltskin AI video on Cicadas

Rumpelstiltskin AI is the meme of a fairy-tale imp doing a tiptoe dance, in a clip that AI made to look like a 1980s fantasy film. This page makes your own version from text alone: the imp comes at the camera through a torch-lit castle hall, dances on a plain green screen you can cut into your own video, or tiptoes down a supermarket aisle. Cicadas makes it with MiniMax H3 Max as a vertical clip of 5, 10 or 15 seconds with sound; in our three clips the sound is footsteps. The song people post the meme with is not included, the scenes ask for plain white sneakers with no logo, and nothing is uploaded. A 5-second clip is 63 credits.

Rumpelstiltskin AI video examples made on Cicadas

Text to video5s · 480P

Through the torch-lit hall, on tiptoe.

MiniMax H3 Max, 5 seconds with sound, vertical, from text alone; back in 14 seconds. A small bearded imp in a brown tunic, a pointed cap and plain white high-top sneakers tiptoes toward the camera through a torch-lit stone hall, knees high and arms swinging, and ends in a close-up grin. The camera stays low and still, in one shot. The sound is rapid, light tapping, with no speech or music.

Use this recipe ↗
Text to video5s · 480P

The same dance on a green screen.

MiniMax H3 Max, 5 seconds with sound, vertical, from text alone; back in 19 seconds. The same imp dances on the spot on one even green background, knees high and arms swinging, grinning at the camera; his whole body stays in frame for the full clip. There is a soft shadow under his feet. The sound is rapid tapping, with no speech or music.

Use this recipe ↗
Text to video5s · 480P

Down the supermarket aisle.

MiniMax H3 Max, 5 seconds with sound, vertical, from text alone; back in 14 seconds. The same imp comes down a bright supermarket aisle toward the camera on tiptoe, arms swinging, and ends close to the lens. The shelves are blurred, colourful packaging with nothing readable on it, and the sneakers are plain white. The sound is hollow footsteps on a hard floor, with no speech or music.

Use this recipe ↗

Why use Cicadas for Rumpelstiltskin AI video

Three scenes of the tiptoe dance

Castle hall: the imp bounces toward the camera between torches and ends in a close-up grin. Green screen: his whole body stays in frame on a solid green background, for cutting into your own footage. Supermarket: he comes down a bright aisle. In all three he wears a brown tunic, a pointed cap and plain white high-top sneakers.

Change the place, keep the dance

Each scene fills an editable prompt. Change the place to an office, a gym or your street and keep the sentence that describes the imp and the dance. The scenes ask for footsteps and no music, and that is what our three clips have, so you can add the sound you want when you post.

See the price of every clip 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 Rumpelstiltskin AI video

  1. 01

    Sign in and pick a scene: castle hall, green screen or supermarket.

  2. 02

    Edit the place if you like, keep 5 seconds, and check the quote.

  3. 03

    Generate. Save the MP4 from the result or from My videos and add your own sound.

Rumpelstiltskin AI video prompt ideas

Copy one into the prompt box above and adapt it to your shot. Or write your own shot by shot in the prompt generator.

  • “A torch-lit stone hall in a castle, shot like a 1980s fantasy film with soft focus and film grain, vertical. Rumpelstiltskin, the imp from the fairy tale: a small, wiry old man with a long nose, pointed ears and a wispy grey beard, in a ragged brown medieval tunic, a pointed cap and spotless white high-top sneakers with no logos, comes toward the camera in an exaggerated, bouncy tiptoe dance, knees high and arms swinging, grinning. The camera stays still at floor height, one continuous shot, no cuts. Sound: quick light footsteps on stone with a faint echo, no music, no voices. No other people, no text.”

  • “A plain, evenly lit green-screen studio, vertical. Rumpelstiltskin, the imp from the fairy tale: a small, wiry old man with a long nose, pointed ears and a wispy grey beard, in a ragged brown medieval tunic, a pointed cap and spotless white high-top sneakers with no logos, dances on the spot in an exaggerated, bouncy tiptoe dance, knees high and arms swinging, grinning at the camera. His whole body stays in frame, the background is one solid bright green with no shadows, and the camera stays still. One continuous shot, no cuts. Sound: quick light footsteps, no music, no voices. No other people, no text.”

  • “A bright supermarket aisle at night, shot like a 1980s fantasy film with soft focus and film grain, vertical. Rumpelstiltskin, the imp from the fairy tale: a small, wiry old man with a long nose, pointed ears and a wispy grey beard, in a ragged brown medieval tunic, a pointed cap and spotless white high-top sneakers with no logos, comes down the aisle toward the camera in an exaggerated, bouncy tiptoe dance, knees high and arms swinging, grinning. The camera stays still at floor height, one continuous shot, no cuts. Sound: quick squeaky footsteps on a polished floor, no music, no voices. No other people, no text, no brand names on the shelves.”

Rumpelstiltskin AI video FAQ

Tested on Cicadas · reviewed 2026-10-13

Recorded on 2026-10-13 with MiniMax H3 Max text-to-video through fal.ai, each request sent once with the exact scene prompt of this page: 5 seconds, 9:16, 480P with sound. Castle hall: back in 14 seconds; the imp tiptoes toward the camera between torches and ends in a close-up. Green screen: 19 seconds; a full-body dance on one even green, with a soft shadow under the feet. Supermarket: 14 seconds; he comes down the aisle toward the camera. He wore the brown tunic, the pointed cap and plain white high-top sneakers in all three; we saw no logo and no readable lettering. Sound (two automated listeners): rapid tapping or footsteps on a hard floor in all three, no speech or music. These are our own scenes, not the clip the meme started from. Not tested: keying the green-screen clip, 10 and 15 seconds, 768P, other places, and prompts that ask for a song or a brand.

Updated Oct 13, 2026 · How we test

Veo 3.1 Fast · Recorded Cicadas sample
Veo 3.1 Fast · 9:16 · 8s with soundNew

AI Bigfoot Video Generator

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.

Veo 3.1 Fast · from 100 credits

Tested 2026-09-30

MiniMax H3 Max · Recorded Cicadas sample
MiniMax H3 Max · 9:16 · 1 photoNew

Human 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

MiniMax H3 Max · Recorded Cicadas sample
MiniMax H3 Max · 9:16 · text onlyNew

Popcorn Volcano AI Video Generator

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.

MiniMax H3 Max · from 63 credits

Tested 2026-10-05

Veo 3.1 Fast · Recorded Cicadas sample
Veo 3.1 Fast · sound always onNew

AI Video Generator with Sound

Describe the action and the sound, and get a 4, 6 or 8 second Veo 3.1 Fast MP4 with an audio track. AI video with sound effects, ambience or dialogue.

Veo 3.1 Fast · from 100 credits

Tested 2026-09-30