NewSeedance 2.5just landed. A full 30 seconds, with sound, in one take.30 seconds, with sound, one take.Try it immediatelyTry it

xAI · Clips · standard

Grok Imagine Video 1.5

xAI's clip model. Needs an image to start from, and always generates audio.

What it costs

5s33.5 credits

What it takes

Aspect ratios16:9 9:16 1:1 4:3 3:4 3:2 2:3
Resolutions480p 720p
Duration1–15 seconds
Reference imagesNot accepted
AudioAlways generated
Required inputsimage

When to reach for it

A prompt alone will not produce a clip here. The model requires a starting image, which makes it an animator rather than a generator. That is a real constraint to plan around, and also the source of its main strength: because the first frame is yours, the look of the clip is settled before the model does anything.

It always generates audio; there is no silent mode. Treat that as part of the output rather than a feature you can decline, and say what you do *not* want in the prompt if the model's instinct for scoring a scene is getting in the way.

Seven aspect ratios, the widest set of any clip model here apart from Seedance, and takes from one to fifteen seconds, which is unusually flexible at the short end. One second is a genuinely useful length for a punctuating cut. No reference images beyond the required starting frame, so it cannot hold a character across shots; pair it with an image model that can, and feed it the frames.

Made with it

Guides that cover it

Grok Imagine Video 1.5 is one pick in the composer.

Every model in this catalog runs from the same prompt bar, priced in the same credits. New accounts start with some to spend.

Start picturing