Animate a starting image into video with Gemini Omni 1.1 Flash. Add an optional ending keyframe for controlled first/last-frame transitions. Try free.
Gemini Omni 1.1 Flash Image to Video — animate a starting keyframe image into a video, with an optional ending keyframe image for controlled first/last-frame transitions, and native synchronized audio.
About this model
Gemini Omni 1.1 Flash Image to Video animates a starting keyframe image (first_frame_url) into a video, with an optional ending keyframe image (last_frame_url) for a controlled first/last-frame transition, and returns natively synchronized audio in the same pass. It's a focused, single-purpose entry point to Gemini Omni's keyframe animation capability: no reference images, reference video, voice, or character IDs to configure, just a starting image, an optional ending image, a prompt, and a resolution. For generating video from a text prompt instead of a starting image, see Gemini Omni 1.1 Flash. For editing an existing video, see Gemini Omni 1.1 Flash Video Edit; for tag-addressed multi-reference composition, see Gemini Omni 1.1 Flash Reference to Video.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapi | $0.10–$0.30 per second of output (by resolution) | Pay-per-generation, no subscription. Keyframe image-to-video with optional first/last-frame pair. |
| Fal.ai | Not available | Gemini Omni 1.1 Flash is not listed on Fal.ai. |
| Replicate | Not available | Gemini Omni 1.1 Flash is not listed on Replicate. |
Pay-per-generation, no subscription. Keyframe image-to-video with optional first/last-frame pair.
Gemini Omni 1.1 Flash is not listed on Fal.ai.
Gemini Omni 1.1 Flash is not listed on Replicate.
** Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Text description of the desired video content — visuals, camera direction, dialogue, and ambient audio cues. | A street musician plays a violin on a rainy Paris evening, raindrops tap the cobblestones, a slow melancholic melody, distant café chatter. |
| First Frame Image | string | Starting keyframe image the video is generated from. | - |
| Last Frame Image | string | Optional ending keyframe image. Requires first_frame_url to also be set. | - |
| Duration (seconds) | Enum (4 options) | Duration of the generated video in seconds. | 8 |
| Aspect Ratio | Enum (2 options) | Output video aspect ratio. | 16:9 |
| Resolution | Enum (3 options) | Output resolution. Billed per second of output: $0.10/s at 720p, $0.15/s at 1080p, $0.30/s at 4K. | 720p |
| Seed | int | Random seed (0–2147483647). Fix for reproducibility; results may still vary due to model stochasticity. | 0 |
Text description of the desired video content — visuals, camera direction, dialogue, and ambient audio cues.
A street musician plays a violin on a rainy Paris evening, raindrops tap the cobblestones, a slow melancholic melody, distant café chatter.Starting keyframe image the video is generated from.
-Optional ending keyframe image. Requires first_frame_url to also be set.
-Duration of the generated video in seconds.
8Output video aspect ratio.
16:9Output resolution. Billed per second of output: $0.10/s at 720p, $0.15/s at 1080p, $0.30/s at 4K.
720pRandom seed (0–2147483647). Fix for reproducibility; results may still vary due to model stochasticity.
0Developer documentation
Provide a starting keyframe
Pass a publicly accessible first_frame_url — this is the image the video animates from.
Optionally provide an ending keyframe
Pass last_frame_url to control where the motion ends. Requires first_frame_url to also be set.
Write a prompt describing the motion and sound Example: 'A street musician plays a violin on a rainy Paris evening, raindrops tap the cobblestones, a slow melancholic melody, distant café chatter.'
Choose resolution and aspect ratio Resolution is billed per second of output: $0.10/s at 720p, $0.15/s at 1080p, $0.30/s at 4K.
Submit and poll
curl -X POST https://api.muapi.ai/api/v1/gemini-omni-flash-1-1-image-to-video \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "A street musician plays a violin on a rainy Paris evening",
"first_frame_url": "https://example.com/start.jpg",
"resolution": "1080p",
"aspect_ratio": "16:9"
}'
Then poll GET /api/v1/predictions/{request_id}/result until status is completed.
Prompt tips
Frequently asked
It's a focused keyframe-animation endpoint: give it a starting image (and optionally an ending image) plus a prompt, and it returns a video that animates between them with natively synchronized audio.
This endpoint requires a starting image (`first_frame_url`) as the actual keyframe the video is generated from. [Gemini Omni 1.1 Flash](/playground/gemini-omni-flash-1-1-text-to-video) instead generates from a text prompt, where any `image_urls` are only auxiliary reference images, not a keyframe.
No, it's optional. When provided, it requires `first_frame_url` to also be set, and the model generates the motion connecting the two frames.
Billed per second of output video by resolution: $0.10/s at 720p, $0.15/s at 1080p, and $0.30/s at 4K. A 10-second 1080p clip costs $1.50.
No, this endpoint only accepts a prompt, `first_frame_url`, and optional `last_frame_url`. For reference images, a reference video, voice, or character inputs, use [Gemini Omni 1.1 Flash](/playground/gemini-omni-flash-1-1-text-to-video).