Grok Imagine Video 1.5 in Twelver: photo animation and 1080p video
Video

Grok Imagine Video 1.5 in Twelver: photo animation and 1080p video

We’ve moved Grok video to version 1.5, the new generation of xAI’s model. The tools are the same — animate a photo, shoot from text, transition between frames. The picture is sharper, and there’s Full HD for the final cut.

What’s new

  • A new 1080p tier — for text-to-video and photo animation.
  • An animated photo stays closer to the original: wrinkles, the smile and fabric texture stay as they were.
  • Clips come with sound: rain, music, spoken lines — Russian included.
  • Transitions between two frames: you set the start and the end, the model invents the middle.
  • 1 to 15 seconds — pay only for the seconds you need.

At a glance

DetailValue
ModelGrok Imagine Video 1.5 (xAI)
ReplacesGrok Imagine Video
ModesFrom text · photo animation · transition from 1–5 frames · reworking an existing video
Clip length1–15 seconds
Resolution480p, 720p, 1080p (1080p for text and photo input)
Aspect ratios16:9, 9:16, 1:1, 4:3, 3:4, 3:2, 2:3
SoundYes: ambience, music, spoken lines
Where in TwelverChat · MCP server
Prices live on the video generation page.

Animate a photo

An old photograph and one sentence. The clip starts exactly on the source picture, and the grandmother says the very line from the prompt.

Prompt (in Russian): the grandmother in the old photo comes to life, laughs, turns her head slightly to the camera and says “Go on, take the picture!”; the wind stirs the apple branches, birds are singing. 6 seconds, 720p, with sound.

Text to video — in 1080p

Prompt: a night street in the rain, a street musician under a lamp plays a slow jazz melody on a saxophone, a passer-by with an umbrella stops to listen. 6 seconds, 16:9, 1080p, with sound.

The same prompt on the previous version and on 1.5 — a frame comparison — plus one more example, a transition from a studio shot into a room, are in the Grok chapter.

Frequently asked questions

What’s new in Grok Imagine Video 1.5?
1080p for text-to-video and photo animation, and a sharper picture: an animated photo keeps the face and detail of the original more faithfully. The modes are the same — text-to-video, photo animation, transitions between frames. Examples and a comparison with the previous version are in the Grok chapter.
Do Grok videos have sound?
Yes. Clips come with an audio track: ambience, music, and any lines you write into the prompt.
How do I try Grok Imagine Video 1.5?
Open the Grok chapter — it has a window with the model itself. You can carry on in Twelver chat.
How much does a Grok Imagine Video 1.5 clip cost?
It’s billed per second, from one second: 720p costs about 1.75× as much as 480p, 1080p about three times as much. Try takes at two seconds in 480p and switch to 1080p for the final. Current prices are on the video generation page.
Can I call Grok Imagine Video 1.5 from Claude or Cursor?
Yes, over MCP: Grok video generation is available through MCP in Claude, Cursor and other clients — see the MCP page.

Try it

Open in Twelver chat
Rate your experience