SpaceXAImodelImagine Video 1.5 with References
Grok's video model can now take image and voice references, generate video from text alone, and output native 1080p.
Details
- Image and voice references carry a look and a voice into new generations
- Text-to-video works with no starting image, pairing image generation with image-to-video underneath
- Native 1080p is supported for both text-to-video and image-to-video
- Text-to-video and 1080p are generally available on grok.com/imagine, iOS, and Android
- References started in the US for SuperGrok Heavy and SuperGrok Plus, rolling out to all tiers over the following days
Best for
Keeping a character, product, or voice consistent across several clips
When to use it
You need multiple shots that look and sound like they belong together
Who benefits
Social and video marketers producing short-form clips in a set
Join the newsletter to get ahead with AI.
I share strategies, new modules, free guides, and tools to get you better at using AI in your work.
Leading a team? See team programs →