Grok Imagine 1.5 Lite API animates one image into a 1–15 s clip with built-in sound, keeping its style. Try it online and view examples and docs.
Provider: xAI
Category: video generation
Endpoint: /v1/tasks
Status: Available
Cost: See live page pricing
Upload one image, describe how it should move, and get a 1–15 second video with sound already mixed in. The original style is kept and the aspect ratio approximately follows the image, which makes it easy to bring product shots, travel photos and illustrations to life.
Pricing
Standard Usage
Ready for generation
Configure your parameters and click "Run" to see the output here.
Image-to-video results
Source images and generated videos are shown separately. Copy a prompt to reproduce the motion language or adapt it to your own image.
A 16:9 photo becomes a tracking shot: the wave curls, spray sparkles in the backlight and the surf roars.
Original prompt
The wave curls and breaks behind the surfer as he carves down its face, white spray bursts and sparkles in the golden backlight, water rushes past. Smooth tracking camera following the surfer. Loud ocean surf and rushing water. Keep the photo realistic. No text, no logos.
A vertical café close-up: the milk stream draws a rosetta while steam rises, with soft café ambience.
Original prompt
Steamed milk pours in a thin stream into the espresso and a rosetta pattern slowly blooms on the surface, light steam rises, the barista's hand moves steadily. Slow push-in close-up. Soft cafe ambience, gentle pouring sound, quiet chatter in the background. No text, no logos.
A square product still gains ripples, drifting petals and moving light while the bottle stays unchanged.
Original prompt
Gentle ripples spread across the water around the perfume bottle, pink petals drift and rotate slowly, light caustics shimmer on the glass and background. Slow orbiting camera move around the bottle. Soft water droplets and calm ambient music. Keep the bottle shape and label area unchanged. No text, no logos.
A 4:3 wildlife photo comes alive: snow falls, the fox turns, sniffs the air and steps forward.
Original prompt
Snow falls steadily, the red fox turns its head, sniffs the air and takes a few careful steps forward through the snow, its breath visible in the cold air, branches drop a little snow. Slow handheld push-in. Quiet winter forest ambience, soft crunching snow. Keep the photo realistic. No text, no logos.
Choose by starting material, reference method, resolution, and shot-control requirements.
Endpoint control
Use a first frame or first/last frames for longer controlled transitions.
Fast image animation
Animate still images with efficient camera and subject motion.
Fast cinematic video
Create image-led video with optional generated audio.
Grok Imagine 1.5 Lite Image to Video turns a source image into a continuous video shot while preserving recognizable subject details.
The Playground and API use model ID grok-imagine-1.5-lite/image-to-video. Keep image guidance and motion instructions in the same request.
These specifications reflect the current HiAPI Grok Imagine 1.5 Lite Image to Video request contract. Endpoint frames and multimodal references are separate input modes and should not be mixed.
Start with a clear input image and a short clip, then increase duration after subject and motion are stable.
The first frame defines subject, composition, and shape. Add a matching last frame only when the ending state must be fixed, leaving room for the intended motion.
Write the middle process in time order, state whether the camera is locked, preserve stable details, and place sound cues next to their matching events.
Start at 1 seconds to inspect endpoint continuity and subject stability, then increase duration or create the production task with grok-imagine-1.5-lite/image-to-video.
This is a minimal asynchronous first-frame request. Use the API docs for callbacks, task retrieval, reference limits, and error handling.
curl -X POST "https://api.hiapi.ai/v1/tasks" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-imagine-1.5-lite/image-to-video",
"input": {
"prompt": "Slow cinematic camera movement, preserve the subject and composition, coherent natural motion.",
"image_url": "https://example.com/source.jpg",
"duration": 1,
"resolution": "480p"
}
}'Grok Imagine 1.5 Lite image-to-video turns one still image into a clip of 1 to 15 seconds. The image sets the subject, style and composition; your prompt describes what moves, how the camera travels and what the scene sounds like. Sound is generated with every clip.
The output approximately follows the aspect ratio of your image, so a vertical illustration stays vertical and a square still life stays square, though exact pixel dimensions may be rounded. That makes it a direct way to animate existing key visuals, product shots and artwork without re-framing them.
Photos stay photographic and illustrations keep their look. In the examples above, the perfume bottle and the fox keep their shape and detail while water, petals and snow move around them.
There is no aspect-ratio control. The examples above use 16:9, 9:16, 1:1 and 4:3 images, and each video comes out close to its input ratio (for example 16:9 in, 1264×720 out).
Describe a breaking wave, a milk pour, drifting petals or a slow push-in. Naming what must stay still helps keep the subject stable.
Surf, café chatter, water droplets or a quiet winter forest is generated with the clip. Mention the sound you want in the prompt.
Each scenario below matches one of the examples on this page.
Turn a single action or travel photo into a short clip with real motion and sound, like the surfer example, for social feeds and campaign openers.
Bring a vertical food or drink photo to life for Stories and Reels, as in the latte-art pour, without reshooting video.
Add ripples, drifting petals and moving light around a product while it stays unchanged, for listings and social posts.
Give a nature photo weather and life (falling snow, an animal turning its head) for intros, backgrounds and ambient loops.
Prepare the image in the final ratio first. The video will roughly follow it.
Use a publicly accessible image in the ratio you need, with the subject unobstructed.
Write what moves, how the camera travels and what you hear. Add “keep the original style” for illustrations.
Test at 480p with the default 6 seconds, then render the version you keep at 720p or 1080p.
Send prompt, image_url, duration and resolution to POST /v1/tasks, then poll or use a callback to fetch the video.
Pick by where the shot starts: with only a written idea, use Lite text-to-video; with an existing image, use Lite image-to-video. If you need to choose the output ratio for an image animation, look at the third column.
| Lite text-to-video | Lite image-to-video | Grok Imagine 1.5 image-to-video | |
|---|---|---|---|
| Starts from | Prompt only | One image + prompt | Image + prompt |
| Duration | 1–15 s | 1–15 s | 1–15 s |
| Resolution | 480p / 720p / 1080p | 480p / 720p / 1080p | 480p / 720p |
| Aspect ratio | 7 options, 16:9 to 9:16 | Approximately follows the input image | Selectable |
| Sound | Generated with every clip | Generated with every clip | See that model's page |
| Best for | Exploring ideas, ads and social clips from scratch | Bringing existing artwork, product shots or key visuals to life | Image animation when you need to choose the output ratio |
Live prices for every resolution are shown in the pricing panel above and on the pricing page.
Exactly one, passed as image_url. It must be publicly accessible.
No. The video approximately follows the aspect ratio of your image, with dimensions rounded to sizes the model supports. Crop or extend the image to the ratio you need before submitting.
Yes. Sound is generated with the picture and cannot be switched off. Describe the sound you want in the prompt.
Any whole-second duration from 1 to 15 seconds (default 6) at 480p, 720p or 1080p (default 720p).
Yes. This route requires both image_url and a prompt of up to 4,096 characters. Describe what moves, the camera and the sound rather than re-describing the image.
POST an asynchronous task to /v1/tasks with model set to grok-imagine-1.5-lite/image-to-video and prompt, image_url, duration and resolution inside input. Poll the task or use a callback to get the video URL.
Use a clear image with a complete composition, describe one main motion, and name what should stay unchanged, such as faces, the art style or the background layout.
By the requested duration at the selected resolution, plus a per-image input fee. The pricing panel shows the live rate, and the successful task record shows the final charge.