grok-imagine
Generate images and videos using xAI Grok Imagine Extended. Text-to-image, image editing, text-to-video, image-to-video. Use when: user asks to generate, create, or draw an image, or create/animate a video. NOT for: image analysis/understanding (use the image tool instead). Triggers: generate image, create image, draw, grok imagine, make a picture, text to image, generate video, animate, text to video.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/ademczuk/grok-imagine-extendedWhat This Skill Does
The grok-imagine skill for OpenClaw integrates the powerful xAI Grok Imagine Extended suite directly into your workflow. It allows you to generate high-fidelity images and dynamic videos through simple natural language commands. Whether you need an illustration for a presentation, a stylized edit of an existing photograph, or an animated clip from a static source, this skill handles the heavy lifting by interfacing with the xAI API. It automates the process of image creation, file path handling, and video polling, providing a seamless bridge between your intent and visual output.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/ademczuk/grok-imagine-extended
Ensure your XAI_API_KEY is configured either as an environment variable, within your ~/.openclaw/openclaw.json configuration file, or present in ~/keys.txt to enable authentication with the xAI services.
Use Cases
This skill is perfect for creators, developers, and researchers. Common use cases include:
- Generating original concept art for game or project development.
- Applying artistic filters or modifiers to existing images using prompt-based editing.
- Creating short-form marketing videos or social media assets from textual prompts.
- Transforming static product photos into engaging, animated sequences with camera motion.
- Prototyping visual ideas quickly with high-quality resolution settings.
Example Prompts
- "Generate an image of a futuristic cyberpunk city at night with neon lights, set the resolution to 2k and use a 16:9 aspect ratio."
- "Animate this photo of a meadow, add a gentle camera zoom and some wind effects to the grass, keep it to 5 seconds."
- "Create a professional-looking watercolor painting based on this source image of my office desk."
Tips & Limitations
- Filenames: Always use descriptive, timestamped filenames (e.g.,
2026-03-01-project-concept.png) to keep your output directory organized. - Async Operations: Video generation is an asynchronous process; be prepared for the script to poll for status, which may take between 1 to 5 minutes depending on load.
- Costs: Be mindful of the tiered pricing;
grok-imagine-image-prois significantly more detailed but carries a higher cost than the default model. - Limits: When editing images, you are limited to a maximum of 3 input images for generation or 1 for video animation. The system automatically handles image downloading from temporary URLs to ensure your files persist locally.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-ademczuk-grok-imagine-extended": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, external-api
Related Skills
skills-weekly
OpenClaw Skills Weekly — tracks trending ClawHub skills, generates GitHubAwesome-style YouTube video scripts with two-track ranking (Movers + Rockets).
skills-weekly
OpenClaw Skills Weekly — tracks trending ClawHub skills, generates GitHubAwesome-style YouTube video scripts with two-track ranking (Movers + Rockets).
menuvision
Build beautiful HTML photo menus from restaurant URLs, PDFs, or photos using Gemini Vision and AI image generation