AI Video Generation with xAI Grok Video
xAI's video generation model creating videos from text prompts or images. Grok Video supports up to 15 seconds of output with flexible aspect ratios and resolution options, bringing xAI's capabilities to video content creation.
What makes Grok Video different
Text or image in, video out — one node
Grok Video handles both starting points in a single node: write a prompt and generate from scratch, or attach an input image and the model animates it. Durations run in clean 3-second steps — 3, 6, 9, 12, or 15 seconds — so you can iterate on short drafts and commit to longer takes with the same settings.
One of the cheapest per-second video models
At $0.05 per second for 480p and $0.07 per second for 720p, Grok Video sits at the budget end of the AI video market — a full 10-second 720p clip costs about $0.70. That per-second pricing makes it a strong pick for high-volume iteration: explore ideas here, then re-run the winning prompt through a premium model if you need more polish.
Eight aspect ratios, plus auto
Beyond the usual 16:9 and 9:16, Grok Video offers 4:3, 3:2, 1:1, 2:3, and 3:4 — and an auto mode that picks the frame for you. Vertical shorts, square feed posts, and classic photo ratios all render natively instead of being cropped after the fact.
Two modes on one board
This page covers the text- and image-to-video mode. Grok's Reference to Video mode accepts up to 7 reference images cited in the prompt as @Image1, @Image2 for consistent subjects across generations. Both run as nodes on the same Scenetra board, next to every other video model, so comparing outputs is a matter of dragging a second node.
Playground
A timelapse of a flower blooming in a sunlit meadow, cinematic quality
Drop images or click to upload
Try Grok Video in Scenetra
Open PlaygroundParameters
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt* | text | Text describing the video you want to generate. | — |
| Duration | select | Length of the generated video in seconds.3 · 6 · 9 · 12 · 15 | 6 |
| Resolution | select | Output video resolution.480p · 720p | 720p |
| Aspect Ratio | select | Video aspect ratio.auto · 16:9 · 4:3 · 3:2 · 1:1 · 2:3 · 3:4 · 9:16 | 16:9 |
| Input Image | image upload | Optional input image for image-to-video generation. | — |
Pricing
From $0.05 per second
Pay per generation — only pay for what you use.
480p
$0.05/s
per second
720p
$0.07/s
per second
What a video costs
| Duration | 480p | 720p |
|---|---|---|
| 5 seconds | $0.25 | $0.35 |
| 10 seconds | $0.50 | $0.70 |
Use cases
Social content
- Vertical 9:16 shorts
- Square feed clips
- Meme and reaction videos
- Rapid trend responses
Marketing & ads
- Low-cost ad variants
- Concept testing at volume
- Product teaser clips
- A/B visual hooks
Prototyping & previz
- Cheap first-draft shots
- Storyboard animatics
- Prompt exploration runs
- Style tests before premium renders
Image animation
- Bring stills to life
- Animate generated art
- Photo-based b-roll
- Character motion tests
Related models
Grok Imagine Video v1.5
xAI's latest image-to-video model. Grok Imagine Video v1.5 animates a single input image into a video up to 15 seconds long with synchronized audio generated at no extra cost. Pick 480p for fast iteration or 720p for production-quality output.
View model →Seedance 2.5
ByteDance's Seedance 2.5 generates cinematic videos up to 30 seconds from text prompts with synchronized audio — voice, sound effects, and background music — built in by default. The newest Seedance generation, with mp4 or high-fidelity mov output for multi-round editing pipelines.
View model →Hailuo 2.3
MiniMax's Hailuo 2.3 video generation model delivering 768p videos with both text-to-video and image-to-video support. A cost-effective option for social media content, quick iterations, and template-based video creation.
View model →Seedance 2.5
ByteDance's Seedance 2.5 generates cinematic videos up to 30 seconds from text prompts with synchronized audio — voice, sound effects, and background music — built in by default. The newest Seedance generation, with mp4 or high-fidelity mov output for multi-round editing pipelines.
View model →Frequently asked questions
What is Grok Video?+
Grok Video is xAI's video generation model, part of the Grok Imagine family. It creates videos of 3 to 15 seconds from a text prompt, or animates an input image if you attach one. On Scenetra it runs as a node in the visual workflow editor — web-based, no API key or waitlist required.
Can I use Grok Imagine video for free?+
You can try it free on Scenetra: new accounts start with free welcome credits and a 7-day trial, which covers your first generations. After that it's pay-per-generation from your credit balance — a 5-second 480p clip costs about $0.25 — with no subscription gating the model and nothing to cancel.
How much does Grok Video cost?+
On Scenetra, Grok Video costs $0.05 per second at 480p and $0.07 per second at 720p. A 10-second 720p video is about $0.70, which makes it one of the cheapest video models available. You only pay for what you generate.
Do I need an X Premium subscription to use Grok Video?+
Not on Scenetra. Access to Grok Imagine through the X app has changed over time and is often tied to subscription tiers, but on Scenetra there is no X account or Premium plan involved — you pay per generation from your credit balance, and the model sits alongside every other video model on your board.
Is Grok Imagine better than Sora 2?+
It depends on what you need. Grok Video's strengths are price ($0.05-$0.07 per second versus Sora 2's roughly $0.10) and fast iteration across many aspect ratios; community comparisons often rate it well for image-to-video motion. Sora 2 is stronger on complex prompt following in many tests. On Scenetra both are on the same board, so the practical answer is to run your prompt through each and compare.
Can Grok do image to video?+
Yes — attach an input image to the Grok Video node and the model animates it, guided by your prompt. If you need the newest xAI image-to-video quality, Grok Imagine Video v1.5 is also on Scenetra as a separate node with improved motion and native audio. And for consistent subjects across clips, the Reference to Video mode accepts up to 7 reference images.
How long can Grok videos be?+
You can choose 3, 6, 9, 12, or 15 seconds per generation. For longer pieces, generate multiple clips and join them with Scenetra's sequencing tools on the same board.
What resolutions and aspect ratios does Grok Video support?+
480p and 720p output, at aspect ratios 16:9, 4:3, 3:2, 1:1, 2:3, 3:4, and 9:16 — or auto, which lets the model pick the frame. 480p is roughly 30% cheaper per second, so it's the natural choice for drafts.
Start creating with Grok Video
Use Grok Video alongside 50+ other AI models in Scenetra's visual workflow editor. No setup required.
Get Started Free