The wait is over. Google's Nano Banana 2.1 is now live.

Vidu Q4 | Preview | Reference to Video

Image Gen·Vidu Q4·by Vidu

Vidu Q4 Preview Reference-to-Video turns reference images into consistent videos with optional audio. Create short clips for storyboards and branded content.

Try it now →
API reference
Runtime (p50)
5m
Estimated price
$0.045–$0.39 per second, depending on resolution
Call the API
prediction.sh
sh
curl -X POST \
  -H "Authorization: Bearer $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "vidu-q4-preview-reference-to-video",
    "input": {
        "audio": true,
        "prompt": "The red-haired woman from the reference stands still in the middle of a vast open field filled with rows of huge white bedsheets hanging on long clotheslines, golden hour sunlight shining through the fabric. A strong wind makes the sheets billow and snap around her. One large sheet sweeps across the camera and slides away, revealing her looking straight into the lens with a soft smile, her long copper waves and cream knit cardigan moving in the wind. Slow push-in, analog film look, fine grain, fashion editorial.",
        "duration": 5,
        "image_urls": [
            "https://cdn-us.eachlabs.ai/defaults/f373b8c1ccf34f67bf442719a97b5590.png"
        ],
        "resolution": "720p",
        "aspect_ratio": "16:9"
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/

Related models

4 models
MiniMax | H3 | Max | Turbo | Image to Video AI model preview
MiniMax | H3 | Max | Turbo | Image to Videofal
Hearthbroken Car Video AI model preview
Hearthbroken Car VideoUnified AI API for hundreds models. Access video, image, and audio generation from leading providers through one integration with eachlabs.
Alibaba | Wan | 3.0 | Image to Video AI model preview
Alibaba | Wan | 3.0 | Image to VideoAlibaba
Smash and Grab Video AI model preview
Smash and Grab VideoUnified AI API for hundreds models. Access video, image, and audio generation from leading providers through one integration with eachlabs.
* FAQ

About Vidu Q4 | Preview | Reference to Video

01 / 03

What is Vidu Q4 Preview Reference-to-Video?

Vidu Q4 Preview Reference-to-Video generates a video from a text prompt and one to fifteen reference images. It refers to the subjects in those images to maintain consistency in the resulting scene. You can choose a duration from three to sixteen seconds, select an aspect ratio and resolution, and optionally generate audio alongside the video.