Video Gen Now

Reference to video

The mode that solves the hardest problem in AI video: the same face, the same product, the same look, shot after shot. Upload up to nine references, call them out in the prompt as Image 1 and Image 2, and direct the scene around them.

Upload the subjects that have to stay recognisable, then name them in the prompt as Image 1, Image 2, and so on.

Sign in to upload an image. Everything you have typed is kept.

Native audio

Sound effects, ambience and lip-synced speech, generated from the same prompt. Costs the same either way.

121 credits

Rendering is paid in credits, and new accounts start at zero. Pricing

Made with this model

Every clip below was rendered here, on the settings shown under it. The caption is the exact prompt that produced it.

The speckled teal mug sits on a wooden cafe counter with steam rising from it; a hand slides it forward into frame. Warm morning light, shallow focus.

Seedance 2.0 · 720p · 16:9 · 4s

The coral origami crane unfolds its wings and lifts off a wooden desk, drifting past a window into the evening light. Smooth tracking shot.

MiniMax H3 · 2K · 16:9 · 5s

How reference to video works here

  1. Upload your references

    Up to nine images: a character from a couple of angles, a product on its own, a colour treatment you want carried across — anything that has to stay recognisable.

  2. Reference them by number

    “Image 1 is the barista, Image 2 is the cup.” The numbering is how the model knows which reference belongs to which part of the scene.

  3. Direct the scene

    Everything else is an ordinary prompt: action, camera, light. The references constrain identity; the prompt decides what happens.

Specs at a glance

ModelDurationResolutionNative audioReference imagesFrom
Seedance 2.04–15 seconds480p · 720pYesUp to 931 credits for 5 seconds
MiniMax H35–15 seconds2KNoUp to 9130 credits for 5 seconds

Getting identity to stick

One subject per reference image. A photo containing two people gives the model an ambiguous target.

Match the lighting you are about to ask for. A hard-flash reference fights a golden-hour prompt.

Two or three angles of the same character beat nine near-identical crops.

Name every reference in the prompt. An uploaded image the prompt never mentions is largely ignored.

Reference to video questions