What is Grok Imagine (I2V)?

Grok Imagine (I2V) is an AI model (image to video) available on Artifio.ai through xai. You can run it in our workspace from a single shared wallet and download your outputs.

How much does Grok Imagine (I2V) cost on Artifio?

Grok Imagine (I2V) starts at about $0.010 per second on Artifio.ai. The exact cost is shown in the workspace before you confirm and can vary with the options you select.

How do I use Grok Imagine (I2V) on Artifio?

Click Generate Now to open the workspace at /create/grok-imagine-i2v. Fill in the form fields, review the live cost estimate, and run your generation.

What kind of outputs does Grok Imagine (I2V) produce?

Grok Imagine (I2V) is configured for image to video workflows in the video category. See the technical parameters below for supported inputs and options.

Can I try Grok Imagine (I2V) for free?

Sign up free, top up your wallet from $5, and you can run Grok Imagine (I2V) pay-as-you-go without a separate subscription for this model.

Grok Imagine (I2V) — AI Video Generator

Name: Grok Imagine (I2V)
Brand: Artifio
Price: 0.010 USD
Availability: InStock

$1 on us$1 on us + a free Gold trial to get you startedClaim your $1 + trial Terms apply

artifio.ai

Grok Imagine (I2V) — AI Video Generator | Artifio.ai

About Grok Imagine (I2V)

Grok Imagine's image-to-video variant animates a still picture. You supply a source image plus a text prompt describing the motion you want, and grok-imagine-video, the standard video model in xAI's Imagine API, uses the image as the opening frame and animates its content from your instructions. The mode has been part of the Imagine API since xAI opened video generation to developers in January 2026, and it is distinct from the newer Grok Imagine 1.5, which is a separate dedicated image-to-video model.

It shares infrastructure with the family's text-to-video, editing, and extension modes, so an animated photo can be pushed onward through the same pipeline. On artifio.ai it sits in one workspace with 100+ other models, pay-per-generation, no per-model subscription.

Features

Accepts the source image as a public URL, a base64-encoded data URI, or a stored file id from xAI's Files API.
The text prompt directs motion: camera moves, subject action, and scene atmosphere.
Clip length is configurable from 1 to 15 seconds.
Output inherits the source image's aspect ratio by default; an explicit aspect ratio parameter overrides it.
480p and 720p output resolutions on grok-imagine-video.
A companion extension mode continues any finished clip from its last frame, chaining animated stills into longer sequences.

What people use it for

Bringing product photography to life for listings and ads without a video shoot.
Animating illustrations, concept art, or archival photos into short moving shots.
Turning a strong generated still into motion while keeping its exact composition.
Building multi-shot sequences by animating an image and then extending the result.

Reported strengths

Three input paths, including stored file ids, avoid re-uploading bytes in production pipelines.
Defaulting to the source image's aspect ratio keeps animated output drop-in compatible with the original asset.
The 15-second ceiling and extension mode together support scene-length results, unusual for a single-image starting point.
SDKs manage the asynchronous polling loop automatically, with manual start-and-poll control available when needed.

Reported limitations

Overriding the aspect ratio stretches the source image to fit rather than cropping it.
Resolution caps at 720p on this model; 1080p image-to-video requires stepping up to Grok Imagine 1.5.
A first-frame image cannot be combined with reference images in one request; the API rejects that combination.
Generation runs asynchronously over several minutes and results land on temporary URLs.

Sources

Image-to-Video (xAI Docs)
Video Generation (xAI Docs)
grok-imagine-video model page (xAI Docs)