Skip to content
Image FxImage Fx

Grok Imagine AI video from text or image

Turn a prompt or a single image into a dynamic AI video with Grok Imagine. Choose 480p or 720p output and any length from 6 to 30 seconds.

Model

Usually 1-3 min
Cat DJ at sunset6 s · 16:9 · 720p · Fun style
Greenhouse in orbit

Tips for Grok Imagine

Describe one clear moment and the camera, e.g. “slow drift, zero gravity, soft window light”. Fun style turns up the energy.

Showcase

Grok Imagine Video Examples

Real clips, with the prompts that made them.

Cat DJ at sunset

A ginger cat in sunglasses DJs at a rooftop party at sunset, paws scratching the turntables, colourful lights and a dancing crowd behind.

Greenhouse in orbit

An astronaut floats slowly through a greenhouse module on a space station, leaves and water droplets drifting in zero gravity, soft sunlight through the window, Earth below.

Common Questions & Answers

Grok Imagine is an AI video model from xAI that turns text prompts or images into short, dynamic video clips. On Image Fx you can use it for both text-to-video and image-to-video generation.

Pricing is per second: 480p costs 36 credits per second and 720p costs 63 credits per second. For example, a 10-second 720p video costs 630 credits.

Normal mode follows your prompt closely for predictable results, while Fun mode adds more creative and playful motion. Try both to see which fits your idea best.

You can generate videos from 6 to 30 seconds long. Longer videos cost more credits since pricing is per second.

Text-to-video supports 16:9, 9:16, 1:1, 2:3 and 3:2. For image-to-video, the video follows the aspect ratio of your uploaded image.

Most videos are ready in 1-5 minutes. If a generation fails, your credits are automatically refunded.

Yes. Videos you generate with Grok Imagine on Image Fx can be used for personal and commercial projects, including social media and marketing.