Generate a clip from a prompt alone
Text to video runs up to 15 seconds at 480p, 720p or 1080p on the 1.5 endpoints, with dialogue, effects and score produced alongside the picture rather than dubbed on afterwards.
xAI
Image and video generation by xAI. One family covering both media: video up to 15 seconds at 1080p with audio produced in the same pass, and images at 1K or 2K across thirteen aspect ratios.
Features
Text to video runs up to 15 seconds at 480p, 720p or 1080p on the 1.5 endpoints, with dialogue, effects and score produced alongside the picture rather than dubbed on afterwards.
Image to video takes a frame you own — a product shot, a still from a shoot, an illustration — and moves it, keeping the source composition as the opening frame.
Reference to video accepts one to seven reference images and holds the same subject from clip to clip. Reference renders top out at 720p, so plan hero shots on text or image to video.
Edit video applies a written instruction to a clip up to 8.7 seconds; extend video continues from the last frame for up to 10 more. Both run at 480p, 720p or auto, with audio in the same pass.
The family launched in January 2026 with text and image generation and native audio on video. March added reference-to-video and extend-video, April a quality image tier, May Video 1.5 with 1080p, 15 seconds, clearer speech and lip-sync, July 1.5 text-to-video and reference-to-video, and August 2026 Image 2.0 with a quality setting and up to three input images. The current video generation has its own page at /models/grok-imagine-video-1-5.
Examples
A lone astronaut walks across a barren red desert on Mars, helmet visor reflecting a distant Earth. Wind kicks up fine dust. Camera slowly orbits from a low angle as the astronaut plants a flag. Ambient wind sounds and the hiss of a pressurized suit
Try this promptClose-up of a barista pouring steamed milk into a ceramic cup, latte art forming a rosetta pattern. Warm cafe lighting, shallow depth of field. Sounds of the espresso machine humming and milk frothing
Try this promptAerial drone shot sweeping over a Norwegian fjord at golden hour, mist rolling between snow-capped mountains, a small red fishing boat cutting through glassy water. Orchestral strings swell as the camera rises
Try this promptA street musician plays electric violin on a rain-soaked Tokyo crosswalk at night. Neon signs reflect in puddles. Pedestrians with umbrellas pass in slow motion. The violin melody is crisp and emotional, blending with city ambience
Try this promptThese prompts show the family's range across video and image. Run any of them in the Studio to see your own render.
Workflows
Video cost tracks clip length and output resolution, while images are priced per image, so the image tiers are the cheapest way to explore a look before committing it to motion. Credits come from one shared balance across image, video and speech, and the exact estimate is shown in the Studio before you generate.
Built for
FAQ
Limits, audio, licensing and price — the things worth knowing before you spend a credit.
Open the Studio, pick Grok Imagine, and see the credit estimate before you spend anything.