AI Action Figure Video

AI action figure video from one photo of you: a toy version of yourself in a blister box or stepping out of a toy box. 5 s vertical with sound, 63 credits.

This AI action figure video generator turns one photo of you into a toy version of yourself: a glossy jointed figure with your face, hair and clothes, standing in a blue blister box or walking out of an orange toy box onto a desk. MiniMax H3 Max draws the toy and the packaging around it. 5 seconds at 480P is 63 credits, about $0.62 on the $9.90 first pack, quoted before you generate. Expect small accessories to be wrong: our box clip drew two laptops, not three different items.

  • From 63 credits per clip
  • From your photos
  • 5s / 10s / 15s
  • 480P
  • Audio available

Loading your account…

Model

MiniMax H3 Max

Browse by task

One clear, full-length photo of yourself or an adult who agreed to appear, facing the camera, in even light. The toy is built from your face, hair and clothes, so a plain outfit reads better than a busy pattern. JPG, PNG or WebP, up to 10 MB each.

What scene would you like to create?

Choose a scene. The prompt is fixed and cannot be edited.

Prompt726/2000

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
Blister box: a stiff head turn and wave.Made on Cicadas · MiniMax H3 Max · 5s
Made from these photos (AI-made, fictional)
  • Your photoYour photo
Use this recipe

About AI action figure video on Cicadas

The action figure trend shows a person as a collectible toy in its box: moulded plastic, stiff joints, small accessories in the tray. This page makes it from a single photo. Pick the boxed figure or the unboxing, add one clear full-length photo of yourself, and MiniMax H3 Max draws a vertical clip of 5 seconds by default, with sound. The photo is a reference, so the toy is a new drawing built from your face, hair and clothes, not a filter on the picture. The scenes ask for a plain box with no lettering and no brand names.

To change the clothes of the same photo on a spin, see the AI outfit change video; to keep your photo as a picture and draw a change between two images, the AI morph video. For your own wording around the photo, use AI reference to video; the MiniMax H3 page lists what the model behind this page costs per second. We put seven November trends through the same photo-to-video test, and the ones that failed are written up beside the ones that worked in AI video trends, November 2026: we tested seven from one photo.

AI action figure video examples made on Cicadas

From your photos5s · 480P

Blister box: a stiff head turn and wave.

MiniMax H3 Max reference to video, 5 seconds at 480P with sound, vertical, from the site's sample photo of a woman. A glossy jointed plastic figure in the photo's sweater and jeans stands in a blue blister card on a white shelf; it turns its head and lifts a stiff wave while the camera pushes in. It differs from the prompt in two ways: the tray holds two laptops, not three different accessories, and the cup carries a small round emblem the prompt did not ask for. The sound includes one loud click and was not listened to.

Made from these photos (AI-made, fictional)
  • Your photoYour photo
Use this recipe ↗
From your photos5s · 480P

Unboxing: jointed steps and a hands-on-hips pose.

MiniMax H3 Max reference to video, 5 seconds at 480P with sound, vertical, from the site's sample photo of a man. An orange window box stands open on a desk; a glossy plastic figure of him walks out on jointed legs and ends with its hands on its hips. It differs from the prompt in one way: by the end the figure stands taller than the box it came out of. The sound was not listened to.

Made from these photos (AI-made, fictional)
  • Your photoYour photo
Use this recipe ↗

Why use Cicadas for AI action figure video

You as a jointed toy

Both scenes describe glossy moulded plastic with visible joints at the shoulders, elbows and knees. In our box clip the figure wore the sweater and jeans of the sample photo, and in both clips its movements were stiff on purpose: a head turn and a stiff wave in the box clip, two jointed steps and a hands-on-hips pose in the unboxing.

Two packages, two moves

The boxed scene is a blue blister card on a white shelf, with the camera pushing in as the figure waves. The unboxing is an orange window box open on a wooden desk, with the figure walking out toward the camera. Each scene is a fixed prompt, so you pick the one you want.

Accessories and sizes drift

Small details are where the model slips. The box scene asks for a coffee cup, a laptop and a pair of headphones, and our clip drew two laptops in the tray and a small round emblem on the cup that the prompt did not ask for. In the unboxing the figure ends taller than the box it stepped out of.

Price before you generate

Prices at 480P: 63 credits for 5 seconds, 125 for 10 and 188 for 15 (768P: 100, 200 and 300). The button shows the amount first, and a generation that fails is refunded in credits.

How to use AI action figure video

  1. 01

    Sign in and pick a scene: Blister box or Unboxing.

  2. 02

    Add one clear, full-length photo of yourself, keep 5 seconds or choose 10 or 15, and check the quote.

  3. 03

    Tick the photo confirmation, generate, and download the MP4 from My videos; add your own caption or sticker in your editor.

Keep the accessory list short

The model counts poorly in small trays. Our box clip was asked for three different accessories and drew two laptops. Where you can edit the wording, name one or two accessories and say what each one is, and expect to check the tray in the result.

A blank box is a request, not a promise

Both scenes ask for packaging with no lettering and no logos, and in our clips the box stayed plain apart from a small round emblem on a cup. Image models like to invent packaging text, so look at the box before you post, and add your own title in an editor.

Choosing a full-length photo

A full-length, front-facing photo in even light, with a plain outfit and nobody else in the frame. The more of your face and clothes the model can read, the closer the toy gets. Pets and group photos are not what these scenes are written for.

AI action figure video prompt ideas

These are the tested scenes on this page. Each scene is fixed and its prompt is read-only: pick one above, or press “Use this prompt”.

  • “Vertical, one continuous shot of a collectible action figure of the person from Image 1 standing inside a toy blister box on a white shelf. The figure is glossy moulded plastic with visible joints at the shoulders, elbows and knees, about fifteen centimetres tall, with the face, hair and clothes of the person in the photo turned into a toy. Next to it in the plastic tray sit three small accessories: a coffee cup, a laptop and a pair of headphones. The box is a plain bright blue card with a clear plastic window and no lettering at all. The camera pushes in slowly; the figure turns its head toward the camera and lifts one arm in a stiff toy wave. Sound: a soft plastic creak, no music. No text, no logos, no brand names.”

  • “Vertical, one continuous shot at desk level. A plain orange toy box with a clear window and no lettering stands open on a wooden desk. A collectible action figure of the person from Image 1, glossy moulded plastic with visible joints, with the face, hair and clothes of the person in the photo turned into a toy, steps out of the box onto the desk with stiff jointed movements, takes two steps toward the camera, puts its hands on its hips and strikes a hero pose. A desk lamp lights it warmly from the side and the background is softly blurred. The camera stays still. Sound: small plastic clicks for each step, no music. No text, no logos, no brand names.”

AI action figure video FAQ

Tested on Cicadas · reviewed 2026-11-10

Local implementation, 2026-11-10. Two locked MiniMax H3 Max reference-to-video scenes from one photo, recorded from the site's sample woman and sample man, 5 seconds at 480P, vertical, sound on, USD 0.25 each (docs/research/claude-trends-20261110/). Box clip: two laptops in the tray and a small round emblem on the cup, neither asked for; unboxing: the figure ends taller than its box. Not run: 10 and 15 seconds, 768P, pets. The audio was measured, not listened to. The page's consent line excludes children, celebrities and public figures.

Updated Nov 10, 2026 · How we test

Related guides