What does the output look like?
An animated school corridor
An animated character runs through a school corridor in the Grok Imagine Video text-to-video showcase.
Example published by fal: Grok Imagine Video text-to-videoWhat can Grok Imagine Video do?
Grok Imagine Video generates short videos with audio from text or one reference image.
- Short audio-enabled social clips
- Animating one reference image
- Testing the same concept across several aspect ratios
- Inputs
- Text, Image
- Durations
- 6s, 7s, 8s, 9s, 10s, 11s, 12s, 13s, 14s, 15s
- Aspect ratios
- 16:9, 9:16, 1:1, 2:3, 3:2
- Output options
- 480p, 720p
- Typical generation time
- About 10 minutes
- The model is strongest when the selected duration contains one clear action.
- Audio should be described explicitly even when the visual reference is doing most of the compositional work.
How much does Grok Imagine Video cost?
Base estimate
$0.10–$0.15 USD / second
1–1.5 credits / second
Estimated dollar cost uses the Solo monthly plan at $0.10 USD per credit. Your cost per credit depends on your plan.
Example: a 6-second clip
$0.60–$0.90 USD(6–9 credits)
Reference media and video editing may add to this estimate.
Video cost scales with duration. Resolution, sound, reference media, and generation mode can affect the final charge. Check the total shown in Starpop before generating.
How to use Grok Imagine Video
- Click “Create with Grok Imagine Video” and sign in or create an account. After setup, Starpop opens a new video workspace tab with the model selected.
- Describe the scene and audio, or attach one reference image and describe its movement.
- Choose a supported duration, aspect ratio, and resolution.
- Review the credit estimate and generate. Check the result in your workspace, then download it or adjust your inputs to try again.