Reference to Video AI

Reference to video uses pictures of a character, a product and a place as guides for one new shot. Upload one to three images, say what each one is, and download an 8-second clip.

Three reference sets with static shot illustrations

Each group pairs its reference pictures with a static illustration of the intended shot, not a generated video. A robot stays orange inside a bookstore. A backpack stays recognizable on a trail. A traveler, a red kettle and a campsite stay distinct in one shot.

An orange robot walks to a bookstore desk

The orange robot walks to the wooden desk. Keep the robot color and the bookstore recognizable.

Suggested video settings: Veo 3.1 Fast · 8 seconds · 16:9 · 2 references

A rounded orange robot standing with both arms down on a plain cream background
Orange robot, rounded body, both arms down
A bookstore interior with wooden shelves and a desk near the front window
Bookstore interior with a wooden desk
The same orange robot walking toward the wooden desk inside the bookstore
Static illustrative still — not a frame from a generated MP4.

A hiking backpack shown on a forest trail

Show the backpack on the forest trail. Keep the pack shape, straps and color visible.

Suggested video settings: Veo 3.1 Fast · 8 seconds · 16:9 · 2 references

An olive hiking backpack standing upright on a white studio background
Olive hiking backpack, front view
A forest trail under tall green trees with soft daylight
A forest trail with tall trees
The same olive hiking backpack standing on the forest trail, straps and color still visible
Static illustrative still — not a frame from a generated MP4.

A traveler picks up a red kettle at camp

The traveler picks up the red kettle at the campsite. Keep the coat, the kettle and the tent recognizable.

Suggested video settings: Veo 3.1 Fast · 8 seconds · 9:16 · 3 references

An illustrated traveler in a navy coat standing with both arms down
Illustrated traveler in a navy coat
A bright red camping kettle on a plain light background
A bright red kettle
A campsite with a canvas tent and a stone fire ring in a meadow
A campsite with a tent and a fire ring
The same traveler in a navy coat lifting the red kettle beside the tent and fire ring
Static illustrative still — not a frame from a generated MP4.

What is reference-to-video AI?

Reference-to-video AI uses several pictures as guides for a new shot. One picture can carry a character, another a product, and another a place. The clip is a new scene, not a locked first frame and not a locked last frame.

A single opening frame has to stay the start of the shot. Reference to video can leave that frame and still keep the orange robot, the backpack or the red kettle recognizable while the action happens somewhere else.

The pictures guide identity, object and place. They do not guarantee that every edge stays identical, and they are not saved as a permanent character library. A clear subject note on each picture tells the shot which reference is which.

Reference to video vs one opening frame

Seedance 3 reference to video is the one to use when a character, a product and a place all have to survive inside a new shot. One opening frame keeps a single picture as the start of the clip. A prompt with no pictures invents the scene. A slideshow only cuts between stills.

Seedance 3 reference to videoOne opening framePrompt-only videoPhoto slideshow
What you start withOne to three picturesOne pictureWords onlyA stack of stills
What the pictures doGuide the character, object and place in a new shotLock the opening frameNothing is suppliedAppear as cuts
What can changeThe action and the camera, while the subjects stay recognizableMotion inside that same frameThe whole sceneOnly the cut order
What you take awayAn 8-second clip built from those referencesAn 8-second clip that opens on that one pictureA clip of an invented sceneThe same stills, one after another

This page stays on Veo 3.1 Fast. That model can take up to three pictures as references for one 8-second shot in 16:9 or 9:16. The pictures are guides for the new shot, not a first frame and a last frame.

How to combine character, product and scene references

Upload one to three pictures, name the subject in each one, describe how they meet, choose 16:9 or 9:16, then generate and check that each subject is still recognizable.

  1. Add the references in order

    Use one to three JPEG, PNG or WebP images, each up to 20MB. Put the character, the product and the place in the order you want them read. A fourth picture is refused, so none of the set is dropped in silence.

  2. Name each subject

    Write a short note on every picture, such as the orange robot or the red kettle. The note is added to the prompt in that same order. It is plain text, not a saved character ID.

  3. Describe the action

    Say what the subjects do together. The robot walks to the desk. The traveler picks up the kettle. Replacing one picture keeps the other pictures and the words you already wrote.

  4. Generate and check the details

    Preview the 8-second clip and download it. Look for the robot color, the backpack straps or the red kettle. If a subject disappeared, adjust that note or the action and generate again. The last finished clip stays until the new one succeeds.

Reference to video questions

What is reference to video?

Reference to video builds a new short clip from one to three pictures. Each picture guides a character, an object or a place. On Seedance 3 the result is an 8-second shot, not a slideshow and not a locked opening frame.

What is reference-to-video AI?

It is the workflow that keeps several references recognizable inside one new scene. You upload the pictures, name each subject, and describe the action. The model uses those pictures as guides rather than as the first and last frames.

How do I combine a character, a product and a scene?

Upload the character, the product and the place as separate pictures. Name each one, describe the action, choose 16:9 or 9:16, and generate. Then check that the coat, the product and the place are still recognizable.

How is this different from one opening frame?

One opening frame starts the clip on that exact picture. Reference to video can stage a new action while the subjects come from the pictures you uploaded. Use one frame when the photo itself has to be the start of the shot.

How many pictures can I add?

One, two or three JPEG, PNG or WebP images. Each file must be 20MB or smaller and open on your device. Zero pictures and a fourth picture are stopped before a generation starts.

Does the subject note create a character ID?

No. The note is text in the prompt, written as Reference 1, Reference 2 and Reference 3 in the order shown on the page. It tells the shot which picture is which. It is not stored as a reusable identity.

How long is the clip, and what shape can it be?

Veo 3.1 Fast makes an 8-second clip in 16:9 or 9:16. This page does not switch that model, because another model would treat the pictures as frames instead of references.

Will every detail match the references?

The subjects should stay recognizable: the robot color, the backpack shape, the red kettle. Faces, labels and small edges can still shift. Check the preview, then change a note or the action if a subject was lost.