Back to all modelsGrok Imagine Video 1.5 Reference-to-VideoGenerates a video from up to seven reference images and optional preset voices.xAIImage to video147.8 credits/RunvoicePlaygroundAPIRead docs InputPrompt * @Image1 The cowboy cat taps out a message on the telegraph key, paw bobbing rhythmically, the bandana fluttering in the desert wind. It pauses, glances up toward the mesas with a suspicious squint, ears swiveling, then goes back to tapping. Dust drifts across the table and the sunset light warms its fur. The camera slowly pushes in to a close-up. Sound: the click of the telegraph key, wind, distant crows.Reference image * grok-imagine-video-1.5-reference-input-1.1.pngReference image 2 Select or drop an imagePNG, JPEG, WEBP · up to 25 MiBReference image 3 Select or drop an imagePNG, JPEG, WEBP · up to 25 MiBReference image 4 Select or drop an imagePNG, JPEG, WEBP · up to 25 MiBAspect ratio 1:116:99:164:33:43:22:3Duration 1 second2 seconds3 seconds4 seconds5 seconds6 seconds7 seconds8 seconds9 seconds10 seconds11 seconds12 seconds13 seconds14 seconds15 secondsResolution 480p720pJust a moment…Output00:00ExampleTry an exampleCowboy cat on the telegraph720p · 10sMore models