Grok Imagine Video 1.5 Preview: Image-to-Video
Generate videos from images using the Grok Imagine Video 1.5 Preview model with support for multiple aspect ratios, resolutions, and durations up to 15 seconds.
Generate videos from images using the Grok Imagine Video 1.5 Preview model with support for multiple aspect ratios, resolutions, and durations up to 15 seconds.
About this model
Grok Imagine Video 1.5 Preview is an advanced image-to-video generation model that transforms your static images into fluid, high-quality videos. Supporting durations from 1 to 15 seconds with resolutions up to 720p, it excels at producing cinematic animations across a wide range of aspect ratios. Whether you need portrait, landscape, or square formats, this model delivers smooth motion and consistent visual quality from a single reference image.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.08/sec at 480p, $0.14/sec at 720p (default 8s = $0.64) | Pay-as-you-go with no subscription required. Credits deducted per generation. |
| Fal.ai | Not available | This model is not available on Fal.ai. |
| Replicate | Not available | This model is not available on Replicate. |
Pay-as-you-go with no subscription required. Credits deducted per generation.
This model is not available on Fal.ai.
This model is not available on Replicate.
** Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Text description for video generation. | The whale suddenly begins swimming through the apartment as if the room is underwater. Furniture crashes into walls, water bursts outward, and the whale breaks through multiple rooms while the camera follows beside it. |
| Image URLs | array | Upload or provide up to 7 image URLs to use as reference input for video generation. | https://cdn.muapi.ai/assets/grok-imagine-video-1-5-preview.jpg |
| Aspect Ratio | Enum (8 options) | Aspect ratio for the generated video. Use 'auto' to match the input image. | auto |
| Resolution | Enum (2 options) | Output video resolution. | 480p |
| Duration (seconds) | int | Video duration in seconds. | 8 |
Text description for video generation.
The whale suddenly begins swimming through the apartment as if the room is underwater. Furniture crashes into walls, water bursts outward, and the whale breaks through multiple rooms while the camera follows beside it.Upload or provide up to 7 image URLs to use as reference input for video generation.
https://cdn.muapi.ai/assets/grok-imagine-video-1-5-preview.jpgAspect ratio for the generated video. Use 'auto' to match the input image.
autoOutput video resolution.
480pVideo duration in seconds.
8Developer documentation
Upload your image(s): Provide up to 7 image URLs via the images_list field. Supported formats: JPEG, PNG, WebP (max 20MB each).
Write a prompt (optional): Describe the motion or scene you want — e.g., "A person walking through a neon-lit city, camera slowly panning right."
Set duration: Choose between 1 and 15 seconds. Default is 8 seconds.
Choose aspect ratio: Select auto to match your input image dimensions, or specify 16:9, 9:16, 1:1, 4:3, 3:4, 3:2, or 2:3.
Select resolution: Choose 480p for faster generation or 720p for higher quality output.
Submit and poll: The API returns a request_id immediately. Poll GET /api/v1/predictions/{request_id}/result until status is completed.
Frequently asked
No, the prompt is optional. You can submit just an image and the model will animate it based on the visual content. Adding a descriptive prompt gives you more control over the motion and scene.
You can provide up to 7 image URLs in the `images_list` field. The model uses them as reference frames for the video generation.
480p generates faster and costs less per second. 720p produces sharper, higher-resolution output and is recommended for final deliverables or content where visual quality is critical.
The model supports auto, 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3. Use 'auto' to preserve your input image's original proportions.