Google modelsvideo generation api

google/gemini-omni-flash/reference-to-video

Name: Gemini Omni Flash
Author: Google

Gemini Omni Flash by Google - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.

Input

Prompt(string)

The text prompt describing the video. You can bind reference images to roles inline using tags like ``<IMAGE_REF_0>`` (see the Omni Flash prompt guide).

Image URL or upload(array)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum each

URLs of the reference images to incorporate into the video.

Duration(integer)

310

The duration of the generated video, in seconds. Range: 3 to 10.

Aspect Ratio(string)

The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

POSThttps://api.sandbase.ai/v1/run

Model IDgoogle/gemini-omni-flash/reference-to-video

Input Schema

4 parameters · 1 required · 3 optional

Parameter	Type	Required	Description
`prompt`	string	Required	The text prompt describing the video. You can bind reference images to roles inline using tags like ``<IMAGE_REF_0>`` (see the Omni Flash prompt guide). · Max length: 20000
`images`	string[]	Optional	URLs of the reference images to incorporate into the video.
`duration`	integer	Optional	The duration of the generated video, in seconds. · Min: 3 · Max: 10 · Default: 8
`aspect_ratio`	string	Optional	The aspect ratio of the generated image. · Options: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16 21:916:93:24:35:41:14:53:42:39:16

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "google/gemini-omni-flash/reference-to-video",
  "images": [
    "https://static.sandbase.ai/examples/google/gemini-omni-flash/reference-to-video/input_images_0.png",
    "https://static.sandbase.ai/examples/google/gemini-omni-flash/reference-to-video/input_images_1.png"
  ],
  "prompt": "A cat playfully batting at a ball of yarn in a sunlit living room.",
  "duration": 8
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to Gemini Omni Flash

API README

Gemini Omni Flash Reference to Video

Gemini Omni Flash Reference to Video generates a video under the guidance of reference imagery and a required written brief. Unlike the single-image animation variant, its images field accepts a collection of visual references that can be incorporated into the requested scene.

Reference roles can be bound inside the prompt with tags such as <IMAGE_REF_0>, making the connection between written direction and supplied material explicit. The endpoint also offers ten aspect ratios and a three-to-ten-second duration range for shaping the final delivery.

Highlights

Multiple visual references in one request. Provide an array of image URLs when a video should draw on more than one piece of source material.
Inline reference binding. Use tags such as <IMAGE_REF_0> in the prompt to assign supplied images to specific roles in the video brief.
Reference-guided generation. The Gemini Omni Flash catalog explicitly documents reference media as guidance for video generation.
Delivery controls for different placements. Ten aspect ratios and a duration range of three to ten seconds cover broad framing and timing needs.

Pricing

Local price formula: params.duration * 0.13

Technical Specs

Model ID: google/gemini-omni-flash/reference-to-video
Request fields: aspect_ratio (string, optional, enum: 21:9/16:9/3:2/4:3/5:4/1:1/4:5/3:4 (10 values total)); duration (integer, optional, min 3, max 10); images (array, optional); prompt (string, required)
Required fields: prompt
Output fields: content_type (string, optional); url (string, required)
Execution mode: async

When to Use

Use this variant when several reference images need to inform the people, objects, styling, or other roles described in a video prompt.
Choose it when reference-guided generation also needs a defined duration and aspect ratio for the target channel.