XAI Grok Imagine · Reference to Video

Video·grok-imagine·by xAI

The Reference to Video Model generates video guided by one or more reference images using them as style and content references.

Runtime (p50)
2m
Estimated price
$0
Call the API
prediction.sh
sh
curl -X POST \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -H "Content-Type: application/json" \
  --data '{
    "model": "xai-grok-imagine-reference-to-video",
    "version": "0.0.1",
    "input": {
        "prompt": "Reference 1 and Reference 2 are cooking together in the kitchen.",
        "duration": 8,
        "image_urls": [
            "https://storage.googleapis.com/magicpoint/inputs/xai-grok-imagine-reference-to-video-input-1.png",
            "https://storage.googleapis.com/magicpoint/inputs/xai-grok-imagine-reference-to-video-input-2.png"
        ],
        "resolution": "480p",
        "aspect_ratio": "16:9"
    },
    "webhook_url": ""
}' \
  https://api.eachlabs.ai/v1/prediction/

Related models

4 models
* FAQ

About XAI Grok Imagine · Reference to Video

01 / 03

What is Grok Imagine Reference to Video and how does it animate images?

Grok Imagine Reference to Video is xAI's image-to-video model that generates short, motion-consistent video clips from reference images. It uses the Grok multimodal architecture to analyze visual context and produce smooth, scene-faithful animations suitable for product photography, concept art, and marketing visuals.