Which model makes this video?

This page uses MiniMax H3 Max to generate a new scene. It is not another brand’s proprietary filter or an exact copy of an original video template.

Does it include a trend song or original clip?

No original recording, lyrics, source clip or celebrity likeness is supplied. Sound is generated and can vary. Add music you have rights to use separately.

How do I recover my result later?

Sign in to the same account and open My videos to find completed jobs and download them. Keep a local copy. Another generation is a new charged job.

Can I make a video for free?

Sign up and get 1 free video — use it right here. One shared voucher per new account, valid for 7 days. Use it on a supported generation page for its fixed 5-second, 480P watermarked recipe. First-and-last-frame transitions are excluded. Security checks may require email verification; daily free places are limited. Other settings use the displayed credits.

AI Reference to Video: Consistent Characters

AI Reference to Video: Consistent Characters. Make a 5–15 second clip with MiniMax H3 Max. Start at 63 credits; inspect the quote and download from My videos.

AI Reference to Video: Consistent Characters on Cicadas turns your own photos into a 5, 10 or 15 second video with MiniMax H3 Max, at 480P or 768P, with sound. A clip costs from 63 credits, and the exact quote shows before you generate.

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

Loading your account…

Model

MiniMax H3 Max

Browse by task

Main subject

Second reference (optional)

Third reference (optional)

Use yourself, consenting adults or objects you have rights to use. No celebrities or minors. JPG, PNG or WebP, up to 10 MB each.

What scene would you like to create?

A scene fills the prompt below. It calls your photos Image 1, Image 2 and so on; keep those names when you edit it.

Prompt222/2000

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

Your video

5s · MP4

Your next video starts here.

Add a prompt or choose an idea above. Your result will appear here.

About AI Reference to Video: Consistent Characters on Cicadas

Use one to three reference photos to guide who or what appears in a newly generated scene. Name each subject as Image 1, Image 2 or Image 3. References guide appearance across the shot; they do not lock identity or make the uploaded image the first frame.

Why use Cicadas for AI Reference to Video: Consistent Characters

Reference subjects, not a starting frame

Use reference mode when the same adult or object should appear in a different setting. Use Image to video when you want the actual composition of one photo to start the clip. Neither guarantees perfect character consistency.

Start with one clear action

Use clear media you have rights to use and choose an editable scene below. Generated details and likeness can drift. These scene prompts are starting points without new paid output tests in this package.

Check credits before generating

At 480P, MiniMax H3 Max costs 63 credits for 5 seconds, 125 for 10 or 188 for 15; at 768P the prices are 100, 200 and 300. The generator shows the current quote before submission. Failed jobs return credits; an unwanted successful result is still charged.

How to use AI Reference to Video: Consistent Characters

01
Upload the reference photos, confirm your rights and identify each subject by its image number.
02
Load a scene and edit its action. Check length, resolution and the credit quote.
03
Generate, watch the whole result and download. Return to My videos with the same account to recover it; generating again creates a new charged job.

Reference subjects, not a starting frame

Choose the right next step

Use a related workflow when your input or intended result is different.

Open related tool