The #1 model in the global Image-to-Video ranking: up to 30 seconds, native music, effects and lip-sync, up to 7 images in one generation.
In the studio, click the model name at the top, then find on the left Grok — versions on the right:
All Grok 1.5 parameters:
Up to 7 images: the first is the starting frame, the rest are references.
Start frame
Ref 1 · character
Ref 2 · styleGrok's formula: camera + action + lighting + pace.
Hit "Generate" — the task enters the background queue (usually 30–90 seconds). The finished video will appear in your feed and in "My Videos"; tokens for failed generations are refunded automatically.
Real results from Airium Studio — hit play:
How to generate video in Grok Imagine 1.5 online?
Open Airium Studio, select the Grok Imagine 1.5 model in the catalog, set parameters, write your prompt, and click "Generate". Registration takes a minute — new users receive free tokens.
How much does video generation cost in Grok Imagine 1.5?
In Airium Studio, generating with Grok Imagine 1.5 costs approximately 18 G-tokens / 6 sec. You only pay for successful generations — tokens for failed ones are returned automatically.
What is the maximum video duration in Grok Imagine 1.5?
Available durations: 6–30 s. Parameters are set directly in the studio before generation.
Can I use Grok Imagine 1.5 without API keys or VPN?
Yes — Airium Studio works in the browser with no API keys, foreign bank cards, or VPN: simply select Grok Imagine 1.5 in the catalog and generate online.
| Parameter | Values | Tip |
|---|---|---|
| Duration | 6–30 s | social media — 6–10 sec |
| Format | 16:9 · 9:16 · 1:1 · 2:3 · 3:2 | in I2V — from image |
| Quality | 480p · 720p | 720p for publishing |
| Audio | native, always | music + effects + lip-sync |
| Images | up to 7 | spicy is not available with them |
| Price | ≈ 3 ⚡/sec | 6 s ≈ 18 · 30 s ≈ 90 |
«orbits in a circle», «slow push-in», «fly-through» — the primary language of Grok.
Lines in quotes → automatic lip-sync.
«preserve the color and style exactly» + smooth action.
15–30 s — describe in phases.