# Google Gemini Omni Flash 1.1 Image to Video - Core.Today AI API

> Google Gemini Omni Flash 1.1 image-to-video via Fal.AI. Animates a still image into 3-10 second video with synchronized audio, or interpolates between a first and an optional end frame — 16:9 or 9:16 at 360p to 4K.

- **Provider**: Google
- **Model ID**: google/gemini-omni-flash/v1.1/image-to-video
- **Category**: Video Generation
- **Credits**: 1860 per 8s 720p video — billed per second (360p 70/s, 720p 233/s, 1080p 349/s, 4k 698/s)
- **Speed**: Fast
- **Quality**: High

## Features
- Animates a still image with physically coherent motion
- Optional end frame for first-to-last interpolation
- Synchronized native audio
- Four resolution tiers from 360p to 4K, billed per second

## Use Cases
- Bringing photos, product shots and illustrations to life
- Transitions between two keyframes
- Animated thumbnails and social posts
- Motion tests for concept art

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **prompt**: string - The text prompt describing the video — how the first image should be animated or interpolated into the optional end image.
- **image_url**: string - URL of the first frame to animate.

### Optional
- **end_image_url**: string - Optional URL of the end frame. When provided, the model interpolates between the two images in order.
- **duration**: integer (default: 8) - The duration of the generated video in seconds (3-10), billed per second.
- **aspect_ratio**: string (default: 16:9) - The aspect ratio of the generated video.
  Options: 16:9, 9:16
- **resolution**: string (default: 720p) - The resolution of the generated video. Higher resolutions cost more per second.
  Options: 360p, 720p, 1080p, 4k

## Examples

### Dog in sunlight
Animate a still photo at the default 720p and 8 seconds.
```json
{
  "model": "google/gemini-omni-flash/v1.1/image-to-video",
  "input": {
    "prompt": "The dog turns its head and wags its tail in warm sunlight.",
    "image_url": "https://storage.googleapis.com/falserverless/example_inputs/dog.png",
    "duration": 8,
    "aspect_ratio": "16:9",
    "resolution": "720p"
  }
}
```

### Quick 360p draft
A cheap 4-second draft to check motion before a high-resolution render.
```json
{
  "model": "google/gemini-omni-flash/v1.1/image-to-video",
  "input": {
    "prompt": "The dog runs toward the camera and jumps playfully.",
    "image_url": "https://storage.googleapis.com/falserverless/example_inputs/dog.png",
    "duration": 4,
    "resolution": "360p"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- Pick aspect_ratio to match the input image to avoid awkward framing.
- Add end_image_url to control where the motion ends.
- Draft at 360p (70/s), then re-render at a higher resolution.
- Describe the sounds you want in the prompt — audio is generated with the video.

## Documentation
https://fal.ai/models/google/gemini-omni-flash/v1.1/image-to-video