Grok Imagine — AI Image & Video Generator by xAI
Generate images or animate photos with text-to-video and image-to-video modes, three creative styles, and flexible aspect ratios.
Create Your Video
Preview
Your video will appear here
Generating your video...
Create Your Video
Click to upload or drag and drop
Supported: JPG, PNG (max 20MB)
Preview
Your video will appear here
Generating your video...
Create with Grok Imagine in 3 Steps
Pick a mode, describe your vision, and generate.
Choose a Mode
Select Text-to-Video to create from a prompt, or Image-to-Video to animate an uploaded photo.
Describe & Configure
Write a prompt (up to 2 000 chars), pick a creative style (Fun / Normal / Spicy), and set the aspect ratio (2:3, 3:2, or 1:1).
Generate & Save
Hit Generate — results appear in seconds. Preview inline, then download the file to use anywhere.
Why Choose Grok Imagine?
xAI's creative engine with multiple styles and lightning-fast output.
Three Creative Styles
Fun, Normal, and Spicy modes let you dial in the tone — from playful illustrations to bold, high-contrast visuals.
Flexible Aspect Ratios
Output in 2:3 portrait, 3:2 landscape, or 1:1 square — optimised for Instagram, Twitter, blogs, and print.
Fast Generation
Results in 5–15 seconds thanks to xAI's optimised inference infrastructure. Iterate fast, ship faster.
About Grok Imagine
Grok Imagine is xAI's AI-powered creative tool. It generates images from text prompts or transforms uploaded photos into video with three style presets (Fun, Normal, Spicy) and three aspect ratios (2:3, 3:2, 1:1). Each generation costs 30 gems, with results delivered in seconds.
Grok Imagine — Common Questions
Quick answers about xAI's creative AI model.
What is Grok Imagine?
Grok Imagine is xAI's AI image and video generation system. It creates visuals from text prompts or transforms uploaded images using multiple creative modes.
What are the creative modes?
Three styles are available: Fun (playful, whimsical), Normal (balanced, realistic), and Spicy (bold, high-contrast). Each changes the overall aesthetic of the output.
Which aspect ratios are supported?
2:3 portrait, 3:2 landscape, and 1:1 square — covering social media, websites, and print use cases.
How fast is generation?
Typically 5–15 seconds depending on prompt complexity and current system load.
Can I upload my own images?
Yes. Switch to Image-to-Video mode, upload a JPEG, PNG, or WEBP file (max 10 MB), add an optional prompt, and generate.
What formats are supported?
Input supports JPEG, PNG, and WEBP (max 10 MB). Output is delivered as a downloadable file.
Can I use the output commercially?
Yes. Content generated through Haavid with Grok Imagine may be used for commercial purposes.
How much does it cost?
Each generation costs 30 gems. Visit the pricing page for gem packages and subscription options.