Google Veo 2 | Image to Video
Convert still images into videos using Google Veo 2. Provide an image and a text prompt to generate dynamic videos with configurable aspect ratio and duration from 5 to 8 seconds.
Quick Start
Requires an each::labs API key. Get one at eachlabs.ai.
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "veo-2-image-to-video",
"version": "0.0.1",
"input": {
"image_url": "https://example.com/garden.jpg",
"prompt": "Flowers swaying in a gentle breeze, butterflies landing on petals",
"duration": "5s",
"aspect_ratio": "16:9"
}
}'
Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
| aspect_ratio | string | auto | Aspect ratio. Options: auto, auto_prefer_portrait, 16:9, 9:16 |
| duration | string | 5s | Video duration. Options: 5s, 6s, 7s, 8s |
| image_url | string | - | URL of the input image |
| prompt | string | - | Text prompt for video generation |
Examples
Animate a landscape photo:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "veo-2-image-to-video",
"version": "0.0.1",
"input": {
"image_url": "https://example.com/autumn-forest.jpg",
"prompt": "Leaves gently falling from trees, sunlight streaming through the canopy, a light breeze rustling the foliage",
"duration": "8s",
"aspect_ratio": "16:9"
}
}'
Portrait video with auto aspect ratio:
curl -X POST https://api.eachlabs.ai/v1/prediction \
-H "Content-Type: application/json" \
-H "X-API-Key: $EACHLABS_API_KEY" \
-d '{
"model": "veo-2-image-to-video",
"version": "0.0.1",
"input": {
"image_url": "https://example.com/portrait-photo.jpg",
"prompt": "The person blinks and smiles softly, hair moving slightly",
"duration": "5s",
"aspect_ratio": "auto_prefer_portrait"
}
}'
Related Models
- Google Veo 3 | Image to Video - Newer generation with audio
- Google Veo 3 Fast | Image to Video - Fast Veo 3 variant
- Wan 2.2 | Image to Video - Alternative image-to-video model