The generator

Two photos in. One Rumpelstiltskin barn video out.

This page is the tool itself: the panel at the bottom is the whole product. One photo for the little man who tiptoes, shushes and dances; one for the maiden who waits in the hay and reacts.

15s

15-second widescreen clip

16:9 / 720P

Ready for short-form posts

50

Technical failures are refunded

What this generator does

It makes one specific video and makes it well. A fixed scene description pins the barn, the lantern, the camera and the beats; your two photos decide who performs them. The result is 15 seconds, 16:9, silent.

That is why there is no prompt box and no parameter list. A general video model would ask you to describe the scene, the camera and the mood, then give you a different barn every time. Here the scene is a constant, so the only creative decision is which two photos go in - and every render is reproducible for the price you paid.

What it deliberately does not do: there is no prompt box, no model picker, no scene library and no timeline. One fixed scene, one fixed beat list, one output length. The trade is flexibility for reliability - every render costs the same, both faces are generated separately rather than blended, and a failed render is refunded automatically. If you need a different scene or a longer clip, a general-purpose video model is the right tool instead.

Nothing to configure - the panel below is the same two-photo workflow described above.

Start with the Rumpelstiltskin AI generator →
Two photos to one videoSame barn, same dance15 second video

Create your Rumpelstiltskin video

Photo 1 becomes the little man who tiptoes, shushes and dances. Photo 2 becomes the maiden who waits in the hay and reacts.

The little man (who tiptoes in)JPG / PNG / WEBP · ≤5MB
The maiden (watching from the hay)JPG / PNG / WEBP · ≤5MB

For the best result

  • One person (or pet) per photo, facing the camera
  • Face clear and well lit - no sunglasses, hats or hands over it
  • Head to the waist or knees, so the outfit shows
  • No mirror selfies - the phone can end up in the video

Choose quality

Every beat of the barn clip - the tiptoe, the shush, the arms-out dance - in one 15-second 16:9 video.

Output

Made from these 2 photos

The clip is silent, so you can lay the trending sound over it in TikTok or Reels. Finished videos land in My videos.

0/2 photos added

Video model: Seedance 2.0. AI-generated.

Two photos inOne Rumpelstiltskin video outThe same barn, the same dance15 seconds, 16:9No editing neededCredits never expire

Rumpelstiltskin AI questions

One subject per photo, facing the camera, evenly lit, no sunglasses or hats. A photo from the head down to the waist or knees keeps the outfit, which matters because the outfit is generated too. Photos of pets and illustrated characters work the same way.

Ready for your Rumpelstiltskin video?

Two photos in, one 15-second barn video out. Packs start at $6.99, credits never expire, and you only spend them when you press generate.

Make my video