Grok Video
Video modelGrok Video is a video generation model on JoyInAIGC: Text/image to video, 6–10s per clip. No GPU or setup — write a prompt in the browser and get a clip back, billed in credits by model and output.
Capabilities
- Type
- Video model
- Aspect ratios
- 2:3 · 3:2 · 1:1 · 16:9 · 9:16
- Resolutions
- 480p · 720p
- Clip length
- 6–10s
- Reference images
- 7
Credit cost
Exact credits charged per run — the same numbers the generate button shows before you spend anything.
| Resolution / Duration | Credits |
|---|---|
| 480p · 6s | 10 |
| 480p · 10s | 16 |
| 720p · 6s | 18 |
| 720p · 10s | 30 |
How to use it
- 1
Write a prompt describing the shot you want.
- 2
Pick Grok Video, then set the aspect ratio and resolution and clip length.
- 3
Generate, then download — output comes with commercial rights.
Try it now
AI Video Generator
Optional · JPG/PNG · add a reference for image-to-image / image-to-video
~15 credits this run
Your generated image will appear here
Credits are charged per generation by model compute (from ~1 credit). $1 = 40 credits.
Frequently asked questions
How many credits does Grok Video cost?
From 10 credits, varying by resolution and clip length — see the full table above. The exact cost is shown on the generate button before you run anything.
Do I need a separate plan for Grok Video?
No. Credits from one subscription work across every model on the site — switching models is just another run, not another plan.
Can I use Grok Video output commercially?
Yes. Output on paid plans comes with commercial rights — use it in storefronts, ads and social content.
Does Grok Video support image-to-video?
Yes — attach up to 7 reference images to guide the shot, or leave it empty for pure text-to-video.
Other models you can use
Seedance 2.0
Text/image/reference/audio to video, adaptive ratio
Seedance 2.0 Fast
Turbo Seedance 2.0
Seedance 2.0 Mini
Lightweight Seedance 2.0
Seedance 1.5 Pro
First/last-frame conditioned generation
Happy Horse 1.1
Text/image/reference to video
Wan 2.7
Image to video (first frame, optional audio drive), 2–15s, ratio follows source