Animate an image into video with Gemini Omni 1.2 Flash. Add an optional last frame, 3-15s clips with native audio, up to 4K. Try free. Gemini Omni 1.2 Flash — animate a starting image (with optional ending frame) into a 3-15 second video with native synchronized audio.
Gemini Omni 1.2 Flash — animate a starting image (with optional ending frame) into a 3-15 second video with native synchronized audio.
About this model
Gemini Omni 1.2 Flash Image to Video animates a starting keyframe image (first_frame_url) into a 3-15 second video, with an optional ending keyframe (last_frame_url) for a controlled first-to-last-frame transition, and returns natively synchronized audio in the same pass. It is a focused entry point for keyframe animation: provide a first image, optionally a last image, a prompt, and your duration, aspect ratio, and resolution. When a last frame is supplied, duration is limited to 3-10 seconds. Pricing is per second of output ($0.023/s at 360p, $0.07/s at 720p, $0.105/s at 1080p, $0.21/s at 4K). For text-only generation see Gemini Omni 1.2 Flash; other 1.2 Flash endpoints: Gemini Omni 1.2 Flash, Gemini Omni 1.2 Flash Video Edit, Gemini Omni 1.2 Flash Reference to Video.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapi | $0.023–$0.21 per second (by resolution) | Pay-per-generation, no subscription. Billed per second of generated video. |
| Fal.ai | Not available | This model is not listed on Fal.ai. |
| Replicate | Not available | This model is not listed on Replicate. |
Pay-per-generation, no subscription. Billed per second of generated video.
This model is not listed on Fal.ai.
This model 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 | Describe the scene, action, camera movement, and sound. | The camera slowly pushes in as the subject turns and smiles, soft ambient music |
| First Frame | string | Image used as the first frame of the video. | - |
| Last Frame | string | Optional image used as the last frame. Requires first_frame_url; duration is then limited to 3-10 seconds. | - |
| Duration | integer | Video length in seconds (3-15). | 8 |
| Aspect Ratio | Enum (3 options) | Output aspect ratio. `auto` follows the reference image and is treated as 16:9 when none is provided. | 16:9 |
| Resolution | Enum (4 options) | Output resolution. Output priced per second of generated video: $0.023/s at 360p, $0.07/s at 720p, $0.105/s at 1080p, $0.21/s at 4K. | 720p |
| Seed | integer | Random seed (10000-99999). Omit for a random seed. | - |
Describe the scene, action, camera movement, and sound.
The camera slowly pushes in as the subject turns and smiles, soft ambient musicImage used as the first frame of the video.
-Optional image used as the last frame. Requires first_frame_url; duration is then limited to 3-10 seconds.
-Video length in seconds (3-15).
8Output aspect ratio. `auto` follows the reference image and is treated as 16:9 when none is provided.
16:9Output resolution. Output priced per second of generated video: $0.023/s at 360p, $0.07/s at 720p, $0.105/s at 1080p, $0.21/s at 4K.
720pRandom seed (10000-99999). Omit for a random seed.
-Developer documentation
Provide a first frame
Pass a publicly accessible image URL as first_frame_url.
Optionally add a last frame
Pass last_frame_url to define the ending image. Duration must then be 3-10 seconds.
Describe the motion Write a prompt covering action, camera, and sound.
Pick duration, aspect ratio, and resolution Duration 3-15s (3-10s with a last frame), resolution 360p-4K. Billing is $0.023/s at 360p, $0.07/s at 720p, $0.105/s at 1080p, $0.21/s at 4K.
Submit and poll
curl -X POST https://api.muapi.ai/api/v1/gemini-omni-flash-1-2-image-to-video
-H "Authorization: Bearer YOUR_API_KEY"
-H "Content-Type: application/json"
-d '{"prompt": "The camera slowly pushes in as the subject smiles", "first_frame_url": "https://example.com/first.png", "duration": 8, "resolution": "720p"}'
Then poll `GET /api/v1/predictions/{request_id}/result` until `status` is `completed`.
Frequently asked
It animates a starting image into a 3-15 second video with native audio, with an optional ending frame.
No. It's optional, requires `first_frame_url`, and limits duration to 3-10 seconds.
Per second of generated video: $0.023/s at 360p, $0.07/s at 720p, $0.105/s at 1080p, $0.21/s at 4K.
Image to Video uses your image as the actual first frame. [Reference to Video](/playground/gemini-omni-flash-1-2-reference-to-video) uses images only as subject, scene, or style references.
`16:9`, `9:16`, and `auto`, which follows the first-frame image.
Yes, dialogue, ambient sound, and music are generated natively.