Grok Imagine Video 1.5 AI Video Generator
xAI's second-generation Grok video model, covering text-to-video, image-to-video, and reference-to-video with up to seven images, all under one name. Clips run any whole second from 1 to 15, at 480p, 720p, or 1080p for text-to-video.
How to Master Grok Imagine Video 1.5
- Step 1
Start From a Frame You Already Like
Upload one image and the model animates from it. This is the most reliable way to keep a character on-model, because the look is fixed before any motion is generated.
- Step 2
Add References for a Cast, Not a Frame
Upload two or more images and it switches to reference-to-video: the images define subjects, identity, and style for a new scene, rather than an opening frame it animates. Use this to put several characters in one shot.
- Step 3
Pick Resolution by What the Shot Is For
480p is the cheapest tier and fine for drafts and quick beats. 720p is the quality pick for anything you will show players. 1080p is available when you generate from text alone.
- Step 4
Keep Clips as Short as the Beat Needs
Every whole second from 1 to 15 is available and pricing is per second, so a 3-second reaction shot costs 3 seconds' worth. There is no minimum preset to round up to.
Example Prompts
Slow push in on a hooded figure at a crossroads shrine, mist rolling past, lantern flame guttering, overcast dusk
A dragon banks hard over a burning coastal town, camera tracks alongside, embers streaming past the lens
Two adventurers meet in a rain-soaked alley, one lowers a hood, handheld camera, medieval lighting
Wide establishing shot of a mountain keep at dawn, clouds moving below the walls, banners snapping in wind
A spellcaster traces a sigil in the air, light builds and discharges, camera holds steady, dark stone chamber
💡 Click the copy button to use these prompts in your own generations
Technical Specifications for Grok Imagine Video 1.5
Frequently Asked Questions for Grok Imagine Video 1.5
About Grok Imagine Video 1.5 for CharGen
Grok Imagine Video 1.5 is xAI's second-generation video model, offered on CharGen as a single entry covering three routes. Prompt alone and it generates from text at up to 1080p. Add one image and it animates that image. Add more and it treats them as references that define subjects, identity, and style for a new scene. You pick the mode by what you upload, not by switching models.
Key Strengths
Clips can be as short as 1 second, which suits reaction shots and quick scene beats that most video models force you to pad out to 5 seconds. The seven-image reference ceiling handles party scenes and recurring NPCs, and the three resolution tiers let you draft cheap at 480p before re-rendering a keeper at 720p or 1080p.