Gemini Omni Flash 1.2 is Google's multimodal video model. This endpoint generates video from a text prompt combined with up to ten reference images and up to three reference videos, each addressable in the prompt, using them as visual references for subjects and settings. Output is available at 360p, 720p, 1080p, or 4K, with durations from 3 to 15 seconds.

google/gemini-omni-flash/v1.2/reference-to-video

Gemini Omni Flash 1.2 is Google's multimodal video model. This endpoint generates video from a text prompt combined with up to ten reference images and up to three reference videos, each addressable in the prompt, using them as visual references for subjects and settings. Output is available at 360p, 720p, 1080p, or 4K, with durations from 3 to 15 seconds.

Inference

Commercial use

Partner

Schema

Playground API Examples

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

google/gemini-omni-flash/v1.2/reference-to-video

Schema

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Input

Prompt*

Create a cinematic scene using the delivery robot from reference 1, the night-market setting from reference 2 and the takeaway box from reference 3. The robot travels slowly down the market's clear central passage, carrying the takeaway box securely inside its open front cargo compartment. Keep the box visible throughout. Its two wheels rotate naturally over the wet pavement, creating small ripples as they cross a shallow puddle. Warm lantern reflections slide across its yellow shell. The camera tracks backward at the robot's eye level, keeping it in a medium three-quarter view. Steam drifts from a nearby food stall as the robot passes. It gently slows beneath a striped awning, comes to a complete stop and tilts its body slightly toward the camera, its amber eyes glowing steadily. One continuous shot. Preserve the robot's silhouette, wheel count, colors and facial design; preserve the box's shape, lid and strap. Keep the market layout coherent. Warm practical lighting against cool evening shadows, tactile surfaces and subtle film grain. No cuts, dialogue, readable text or logos.

Create a cinematic scene using the delivery robot from reference 1, the night-market setting from reference 2 and the takeaway box from reference 3.

The robot travels slowly down the market's clear central passage, carrying the takeaway box securely inside its open front cargo compartment. Keep the box visible throughout. Its two wheels rotate naturally over the wet pavement, creating small ripples as they cross a shallow puddle. Warm lantern reflections slide across its yellow shell.

The camera tracks backward at the robot's eye level, keeping it in a medium three-quarter view. Steam drifts from a nearby food stall as the robot passes. It gently slows beneath a striped awning, comes to a complete stop and tilts its body slightly toward the camera, its amber eyes glowing steadily.

One continuous shot. Preserve the robot's silhouette, wheel count, colors and facial design; preserve the box's shape, lid and strap. Keep the market layout coherent. Warm practical lighting against cool evening shadows, tactile surfaces and subtle film grain. No cuts, dialogue, readable text or logos.

Type # to reference inputs.

Image URLs

Hint: Drag and drop files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL.

3 images added

Reference Video URLs

Hint: Drag and drop files from your computer, videos from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL.

Aspect Ratio

Resolution

Duration

Sign in to run

Result

Idle

What would you like to do next?

Download

{
  "video": {
    "url": "https://v3b.fal.media/files/b/0ab147d6/vRtnl1NXjw4zFM36pbV-N_0548d0e3af724fbc933be10475e50ee3.mp4",
    "content_type": "video/mp4",
    "file_name": "0548d0e3af724fbc933be10475e50ee3.mp4",
    "file_size": 5383840
  }
}

Billing is calculated per second of output video, by resolution. For 360p, your request will cost $0.0273 per second; for 720p, $0.0819 per second; for 1080p, $0.1229 per second; and for 4K, $0.2457 per second. Native audio is included, and reference images and videos are not billed. A 10-second 720p clip costs about $0.82, and the same clip at 1080p costs about $1.23.

Input

Prompt*

Additional Settings

Customize your input with more control.

Result

Idle

What would you like to do next?

Input

Prompt*

Create a cinematic scene using the delivery robot from reference 1, the night-market setting from reference 2 and the takeaway box from reference 3. The robot travels slowly down the market's clear central passage, carrying the takeaway box securely inside its open front cargo compartment. Keep the box visible throughout. Its two wheels rotate naturally over the wet pavement, creating small ripples as they cross a shallow puddle. Warm lantern reflections slide across its yellow shell. The camera tracks backward at the robot's eye level, keeping it in a medium three-quarter view. Steam drifts from a nearby food stall as the robot passes. It gently slows beneath a striped awning, comes to a complete stop and tilts its body slightly toward the camera, its amber eyes glowing steadily. One continuous shot. Preserve the robot's silhouette, wheel count, colors and facial design; preserve the box's shape, lid and strap. Keep the market layout coherent. Warm practical lighting against cool evening shadows, tactile surfaces and subtle film grain. No cuts, dialogue, readable text or logos.

Create a cinematic scene using the delivery robot from reference 1, the night-market setting from reference 2 and the takeaway box from reference 3.

The robot travels slowly down the market's clear central passage, carrying the takeaway box securely inside its open front cargo compartment. Keep the box visible throughout. Its two wheels rotate naturally over the wet pavement, creating small ripples as they cross a shallow puddle. Warm lantern reflections slide across its yellow shell.

The camera tracks backward at the robot's eye level, keeping it in a medium three-quarter view. Steam drifts from a nearby food stall as the robot passes. It gently slows beneath a striped awning, comes to a complete stop and tilts its body slightly toward the camera, its amber eyes glowing steadily.

One continuous shot. Preserve the robot's silhouette, wheel count, colors and facial design; preserve the box's shape, lid and strap. Keep the market layout coherent. Warm practical lighting against cool evening shadows, tactile surfaces and subtle film grain. No cuts, dialogue, readable text or logos.

Type # to reference inputs.

Image URLs

Hint: Drag and drop files from your computer, images from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL.

3 images added

Reference Video URLs

Hint: Drag and drop files from your computer, videos from web pages, paste from clipboard (Ctrl/Cmd+V), or provide a URL.

Aspect Ratio

Resolution

Duration

Sign in to run

Result

Idle

What would you like to do next?

Download

{
  "video": {
    "url": "https://v3b.fal.media/files/b/0ab147d6/vRtnl1NXjw4zFM36pbV-N_0548d0e3af724fbc933be10475e50ee3.mp4",
    "content_type": "video/mp4",
    "file_name": "0548d0e3af724fbc933be10475e50ee3.mp4",
    "file_size": 5383840
  }
}

Billing is calculated per second of output video, by resolution. For 360p, your request will cost $0.0273 per second; for 720p, $0.0819 per second; for 1080p, $0.1229 per second; and for 4K, $0.2457 per second. Native audio is included, and reference images and videos are not billed. A 10-second 720p clip costs about $0.82, and the same clip at 1080p costs about $1.23.

Gemini Omni Flash 1.2 Reference to Video (Image to Video) API on fal