Skip to main content
xAI unveils Grok Imagine 1.5 AI tool generating 720p video from text prompts, showcasing futuristic text-to-video innovation

Editorial illustration for xAI launches Grok Imagine 1.5, adding 720p text‑prompted image‑to‑video

xAI launches Grok Imagine 1.5, adding 720p text‑prompted...

Updated: 3 min read

OpenAI’s Sora is stuck in the garage. xAI just rolled out a new car. The company launched Grok Imagine 1.5, a model that turns a single picture into a short, 720p video.

You tell it what to do with text prompts: pan left, speed up, make it moody. It animates the scene while keeping the original image’s details and lighting intact. You can stitch multiple shots together into longer, consistent clips.

It’s available now as an API preview, requiring just a few lines of code to set up. That puts it directly against Seedance and Google’s Veo. The timing is pointed.

One retreats, the other advances.

Elon Musk's AI company xAI has released Grok Imagine Video 1.5 in preview, a new image-to-video model. The model turns a single still image into a short video at up to 720p resolution. Users describe camera movements, pacing, and atmosphere through text prompts, and the model animates the scene while keeping the original image's details and lighting intact, according to xAI.

This isn’t about winning a demo war. It’s about offering a camera operator’s control. The bet is that fidelity to the source image plus precise text direction matters more than raw spectacle.

While others wrestle with compute costs or vague business plans, xAI shipped a tool. A simple, direct one. The window for flashy prototypes is shutting.

What’s left is the harder work of building something people will actually use.

Common Questions Answered

What is Grok Imagine 1.5 and how does it convert images to video?

Grok Imagine 1.5 is xAI's new model that transforms a single image into a short 720p video using text prompts to control the animation. Users can specify camera movements like panning left, adjusting speed, or changing the mood, while the model preserves the original image's details and lighting throughout the animation process.

What text-prompted controls are available in Grok Imagine 1.5?

Grok Imagine 1.5 allows users to direct animations through text prompts including camera movements such as panning left, speed adjustments, and mood modifications. These precise text directions give users camera operator-level control over how the source image is animated into video.

How can developers access Grok Imagine 1.5 and integrate it into their applications?

Grok Imagine 1.5 is available as an API preview that requires only a few lines of code to set up, making it accessible for developers to integrate the image-to-video functionality into their applications. This streamlined implementation approach contrasts with more complex deployment processes for competing solutions.

Can users create longer videos with Grok Imagine 1.5?

Yes, users can stitch multiple shots together into longer, consistent video clips using Grok Imagine 1.5. This capability allows for more complex video creation while maintaining visual consistency across the stitched segments.

How does Grok Imagine 1.5 compare to OpenAI's Sora?

While OpenAI's Sora remains in limited availability, xAI has shipped Grok Imagine 1.5 as a publicly available API preview focused on practical usability rather than raw spectacle. xAI's approach emphasizes fidelity to the source image and precise text-directed control, positioning it as a tool designed for actual use rather than demonstration purposes.

LIVE03:21OpenAI's Miles Wang in Talks for USD 2B AI Drug Discovery Startup