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...

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

By AI Daily Post Edited by Brian Petersen, Editor-in-Chief

June 4, 2026 • 2 min read

Elon Musk’s xAI has pushed its visual‑generation line forward with Grok Imagine Video 1.5, now in preview. The model takes a single still and, on request, expands it into a short clip that can reach 720p resolution. Users supply text prompts that describe camera moves, pacing and atmosphere; the system then animates the scene while preserving the original image’s lighting and detail, according to the company.

While the tech is impressive, it isn’t a standalone product yet—it’s accessible through the xAI API and can be wired up with only a few lines of code. Multiple shots can be stitched together, producing longer sequences that retain a consistent visual style.

But here’s the reality: xAI is stepping into a space already occupied by video‑AI services such as Seedance and Google’s Veo. OpenAI recently pulled its Sora model, citing resource constraints and an unclear business case, leaving room for new entrants.

The rollout suggests xAI is betting on text‑driven video generation as a viable offering, even as the market tests what sustainable models look like.

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. Multiple shots can also be stitched together into longer scenes that maintain a consistent look. The model is currently available as a preview through the xAI API and can be set up with just a few lines of code.

xAI is now competing directly with video AI providers like Seedance and Google's Veo. OpenAI recently pulled its Sora video model, citing resource constraints and what was likely a missing business model.

xAI updates Grok Imagine to 1.5 with image-to-video generation at 720p resolution - THE DECODER

Why this matters

We see xAI’s Grok Imagine Video 1.5 as a modest step toward more accessible animation tools. Turning a single still into a 720p clip, guided by text that describes camera moves, pacing and atmosphere, could let developers prototype visual concepts without custom pipelines. Yet the preview nature of the release leaves performance details vague; we have no data on latency, artifact rates or how well the model preserves lighting under complex motion.

For founders eyeing product differentiation, the ability to stitch multiple shots into longer scenes suggests a workflow that scales beyond isolated GIF‑like outputs, but integration challenges remain unclear. Researchers may find the claim of “keeping the original image’s details and lighting intact” an interesting benchmark, though reproducibility will depend on access to the model and evaluation metrics. In short, the feature expands the toolbox, but whether it will replace existing video‑generation methods or simply coexist with them is still uncertain.

We’ll watch how the community tests the limits of this preview.