hotel lobbyAIEnglish

TWO PHOTOS · FAIRY-TALE TIPTOE

Rumpelstiltskin AI
Your pair. A mischievous entrance.

Put your pair into the barn scene: one character tiptoes in a dark tailcoat and pink bow tie while the other watches. The reference and role instructions are included.

2 portraitsReference + prompt included216 credits at default settings
01

Your reference clip

Rumpelstiltskin AI reference frame
Rumpelstiltskin AI12s reference · 2 photos
02

Reference images

2 photos · assigned roles
Photo 1Tiptoeing character
Photo 2Observer

Photo 1 replaces the small curly-haired lead in the dark tailcoat and pink bow tie. Photo 2 replaces the blonde observer. Preserve the lead body proportions, costume and pointed heels. JPG / PNG · 10 MB each.

Video type

AI results may vary from the reference.

Edit the prompt Optional for presets

Say what to change, what Image 1 or Image 2 supplies, and what to preserve from Video 1.

04

Model & format

AI motion and generated audio may differ from the reference.

JPG / PNG · 300–6000 px per side. New model option; results may vary.

Duration
Quality
Size
Compare model costs

15s output · 12s reference · entry quality for each model

Seedance 2.0 Fast480p · 216 creditsReference audio when available
MiniMax H3768P · 216 creditsReference audio when available

Cost comparison only. Output quality and identity consistency are not guaranteed; choose your final settings below.

Generation costSeedance 2.0 Fast · 15s · 480p · 16:9
216 credits

Use existing credits or buy a one-time pack. No subscription.

Buying credits does not start generation. Confirm here when you are ready. Confirmed failures return credits.

Your uploads and prompt are processed by an AI service. Use only material you have permission to use. Privacy & retention

THE TREND

What is the Rumpelstiltskin AI tiptoe template?

Rumpelstiltskin is a fairy-tale name, while this video template focuses on a specific comic tiptoe sequence. In a hay-filled barn, the small curly-haired character makes a shushing gesture, steps in pointed heels and appears in foot-level close-ups. A blonde observer remains a separate role. This is a short reference-guided scene, not a retelling of the whole fairy tale.

How to make your Rumpelstiltskin AI video

  1. 01

    Choose the tiptoeing character

    Photo 1 replaces the curly-haired lead in the dark tailcoat. The prompt keeps the reference costume, body proportions and exaggerated steps.

  2. 02

    Choose the observer

    Photo 2 replaces the blonde person watching. That face may be less visible in shots taken from behind; the preset does not force extra close-ups.

  3. 03

    Review the steps and cuts

    Start with the 15-second landscape output. Check the lead identity, the shushing gesture, shoes and observer across the camera cuts.

Add your photos

Let the footwork carry the joke

Use portraits, not costume photos

The reference provides the tailcoat, bow tie and shoes. Your uploads supply the identities; they do not need matching clothes.

Keep the landscape frame

The barn reference is 16:9. A vertical generation can reframe the observer or the feet, so inspect the full result if you change the ratio.

Check the difficult details

Fast feet, heels and partly hidden faces can change during generation. Original requests the same sequence but cannot guarantee frame-for-frame reproduction.

Rumpelstiltskin AI: questions before you generate

Does this generate a Rumpelstiltskin fairy-tale movie?

No. It makes a short version of the barn tiptoe sequence shown here, using your two portraits. It does not generate the spinning-straw story or a full film.

Can I replace only the tiptoeing character?

This preset assigns two photo roles and requires both portraits. For a custom one-person instruction, use the reference-video editor with media you are permitted to upload.

Will it change my body to match the character?

The prompt preserves the reference body proportions, outfit and movement while replacing identity. Body shape and likeness are model-dependent; a specific transformation is not guaranteed.

Why is the reference 12 seconds but the output 15?

The reference is a 12-second excerpt. Available output settings are 5, 10 or 15 seconds, with 15 selected by default. The model interprets the sequence for the chosen length rather than copying its frames.

Where do the preview and audio come from?

The preview is the public tiptoe reference from AI Hotel Lobby, with source audio retained. It is not a result generated on this site. Generated audio can differ; no soundtrack overlay is added for this preset.

How much does this template cost?

The default 15-second Seedance Fast output at 480p uses 216 credits, including the 12-second reference. The smallest pack is 240 credits for $6.99. Generation is paid; previewing is free. Other settings have their own exact quote shown before you confirm.

What happens after I pay?

Buying credits does not start a video. Return to the saved studio, review the cost and confirm generation. Confirmed generation failures return credits. Photos and prompts stay in a device draft for 30 minutes; submitted files are processed by an AI service.

Photo privacy and retention · Use your own reference in the Genjutsu-style editor

Trend sources & reference

Sources explain the trend and identify the reference. They do not endorse this tool or demonstrate a result made with your photos.