Grok Imagine Video 1.5 with References
If you make marketing or social video content, this update means you can generate consistent-looking video (same face, same voice, same product) across multiple clips from just a text prompt, without needing a starting image — handy for quick promotional or explainer videos. It is currently limited to SuperGrok Heavy/Plus subscribers and API access.
What changed
Source summary
xAI released Grok Imagine Video 1.5, adding native text-to-video generation at 1080p without a starting image, voice-reference support to keep a character's face and voice consistent across scenes, and up to seven references per generation to lock elements like faces, products or locations. It is rolling out to SuperGrok Heavy and SuperGrok Plus subscribers and via the xAI API (grok-imagine-video-1.5).
Why it matters to your work
Practical interpretation
If you make marketing or social video content, this update means you can generate consistent-looking video (same face, same voice, same product) across multiple clips from just a text prompt, without needing a starting image — handy for quick promotional or explainer videos. It is currently limited to SuperGrok Heavy/Plus subscribers and API access.
When this could help
Worth trying now for any video project that needs character or product consistency across multiple scenes, or voice continuity paired with a character's face.
Imagine Video 1.5 with References lets you lock specific elements (faces, products, locations) across video generations using up to 7 reference images. Pair a character image with a voice reference so the same face and voice carry across scenes. Native 1080p for text-to-video and image-to-video. Available on grok.com/imagine, iOS, Android, and the xAI API.
How to get started
Go to grok.com/imagine or the iOS app. Upload up to 7 reference images to lock elements (face, product, location). Optionally add a voice reference to pair with a character image. Describe the scene and generate.
Provider guidance ↗
Build it into your routine
SCALA suggested workflow
Consistent character video series
For a multi-scene video project, upload reference images for your main character and location once, then generate each scene with the same references to maintain visual continuity.
What to check
- Image and voice references were initially US-only for SuperGrok Heavy and Plus tiers. API voice reference support requires contacting sales. Sample API code uses 720p, not 1080p. Pricing and API rates are not stated. Source ↗
Sources & provider guides
Official documentation checked 12 Oct 2026. SCALA prompts and workflows are suggestions, not claims of hands-on testing.
Source & availability
This is a summary of a published provider announcement, with practical context from SCALA’s feed.
Plan, region, workspace and rollout conditions may affect access in Australia. Check the original source for current availability.
x.ai