# xAI's new model animates one photo into video — 'preview' is the word doing the work

> xAI released Grok Imagine 1.5, an image-to-video preview, on 3 June 2026 — promising, not proven.

*Cinematic video from a single still, at 720p, in preview. Impressive — and genuinely unfinished.*

By Bez · InsidersFeed
Canonical: https://insidersfeed.com/news/grok-imagine-1-5-preview-is-the-word

> **Key:** **The take:** turning one photo into a believable moving clip is a genuinely hard trick, and xAI says it's done it. Two words deserve more attention than they're getting in the hype reel: **preview** and **720p**. Both appear in xAI's own announcement — they're honest, not hidden — and both do a lot of quiet load-bearing work that's worth naming clearly.

On **3 June 2026**, xAI dropped **`grok-imagine-video-1.5-preview`** via its API: feed it a single still, get back cinematic video with camera moves, atmosphere and physics, 'faithful to the source.' If it delivers what the launch page shows, it's a real entry in the hottest, most-crowded corner of generative AI. The capability story is legitimately interesting. That doesn't mean the words in the headline are doing the same work as the words in the fine print.

## What 'preview' and '720p' actually mean here

Let's be precise about what xAI is claiming and what it isn't. **'Preview'** is an early, evolving release where behaviour and quality can change. The announcement is an invitation to try the model, not a certificate of finished product. Generative video models in preview routinely have issues that disappear before GA — temporal flicker, subject drift, inconsistent physics — and it's genuinely unknown how many of those this one carries. That's not a dunk; that's the definition of preview.

**'Up to 720p'** is the honest ceiling of the current output, and it sits below where the most-established image-to-video systems already operate. Several mature rivals — Runway, OpenAI's Sora, Kuaishou's Kling among them — are generally available and, by their own published claims, reach higher output resolutions than a 720p preview. That gap matters if you're building a product that needs sharp output, and it's worth seeing the shape of the field rather than the launch page in isolation:

| | Grok Imagine 1.5 (xAI) | Established rivals |
| --- | --- | --- |
| **Stage** | Preview | Generally available |
| **Output ceiling** | Up to 720p (per xAI) | Higher resolutions claimed |
| **Access** | xAI API (developers) | Web apps and/or APIs |

*Grok Imagine figures are xAI's own; rivals' figures are each company's own published claims as of June 2026. Independent, like-for-like quality comparisons don't yet exist.*

Neither of those caveats is a knock on xAI. They're just the accurate read of what 'preview at up to 720p' means, which is useful to know if you're deciding whether to build on this today or wait.

> **Note:** **Credit where it's due:** xAI is clearly building a *stack*, not running a stunt. This release follows a May 'Quality Mode' image launch for enterprise/teams — there's a coherent, deliberate API-first creative play here. And shipping a preview is how you learn at scale. The flag is on the framing, not the work.

## The strategy underneath

> We're excited to unveil the Grok Imagine API, a unified bundle of powerful APIs designed for end-to-end creative workflows.
> — [xAI](https://x.ai/news/grok-imagine-api), 2026-05-01

The quieter story is pricing and positioning. xAI says its flagship **Grok 4.3** runs at **$1.25/M input, $2.50/M output** — aggressive numbers relative to many tier-1 peers — and it's now bolting a creative-media line on top. That's a company trying to undercut on text *and* land in image/video at once. Ambitious strategy; early execution. The architecture of the bet makes sense: a developer who builds on xAI's text API is the obvious next sale for the image and video API. The question is whether a 720p preview is the thing that locks in that relationship or whether developers wait for the GA version with sharper output. Watch what xAI announces as version 1.5 comes out of preview — that is when the actual competitive comparison becomes possible.

> Using cached input tokens can significantly reduce your costs.
> — [xAI](https://docs.x.ai/developers/models/grok-4.3), 2026-06-03

## The honest verdict

An image-to-video model entering at 720p in preview is a credible opening move in a space that still has no settled leader. It's not a category win; it's a round-one punch from a company with the resources to stay in the fight for as long as it takes. The right question for developers evaluating this right now is: does 720p preview quality serve your use case today, or does your product need 1080p GA stability? If the answer is yes to the first, try it; if no, bookmark the GA announcement. Either way, xAI's creative-stack trajectory is worth following — this is clearly not the last move they make here.

## Key takeaways

- xAI released grok-imagine-video-1.5-preview on 3 June 2026 — a model that animates one still into cinematic video at up to 720p, per xAI.
- 'Preview' means early, evolving and unfinished — the quality claims are xAI's own and the model is still being iterated.
- 720p is honest in the announcement and easy to skim past: it's below the higher-resolution output mature, generally available competitors claim by their own figures.
- The coherent part: this follows a May image Quality Mode, so xAI is building a stack, not running a stunt.
- The commercial read: Grok 4.3 at $1.25/M in, $2.50/M out shows price aggression in text — whether that follows into video pricing is the question that will actually move developer adoption.

## FAQ

### Is Grok Imagine 1.5 actually good?
xAI's launch page looks strong, but it's a preview at up to 720p — that means it's promising rather than proven. The capability claims are xAI's own, and independent benchmarks will tell the real story. Expect it to improve; don't lock in evaluation off the announcement alone.

### What does 'preview' mean here?
An early, evolving release that isn't a finished product. Behaviour and quality can change, the 720p ceiling may shift, and known rough edges may not yet be fixed. xAI is explicitly calling it a preview — that's an honest signal, not a marketing hedge.

### How does it compare to competitors like Runway or Sora?
Established image-to-video systems such as Runway, OpenAI's Sora and Kuaishou's Kling are generally available and, by their own published claims, reach higher output resolutions than Grok Imagine 1.5's up-to-720p preview. Mature GA systems also have more third-party quality data available. Grok Imagine 1.5 is catching up, not leading, on resolution — but xAI is moving fast and the gap may close.

### Why does Grok 4.3 pricing matter here?
Grok 4.3 at $1.25/M in and $2.50/M out (per xAI) signals price aggression across the xAI API line. If xAI extends that competitive pricing to image and video APIs, that changes the developer calculus — cheaper creative-media output from a lab that also has cheap text is a genuine differentiator if the quality closes the gap.

### Should I build on Grok Imagine 1.5 today?
Depends on your resolution and stability requirements. If 720p and evolving-preview stability works for your use case, it's worth experimenting now. If you need 1080p or production-stable output, waiting for the GA release is the lower-risk call.

## Sources

- [Grok Imagine 1.5](https://x.ai/news/grok-imagine-1-5) — xAI, 2026-06-03
- [Grok Imagine API](https://x.ai/news/grok-imagine-api) — xAI, 2026-05-01
- [Grok 4.3 — models](https://docs.x.ai/developers/models/grok-4.3) — xAI, 2026-06-03
