Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Added support for text-to-image generation and image editing alongside existing video capabilities. - Updated skill description and documentation to include image generation/editing workflows. - Clarified setup, configuration, and best practices for both images and videos. - Added limits for image requests and detailed error handling for new features. - Included metadata for OpenClaw integration.
What This Skill Does
Connects to xAI's Grok Imagine API to generate images and videos from text prompts, edit existing images or videos with natural language, and animate static images. Handles async video jobs with polling and automatic delivery via chat.
Combines image generation, video creation, and editing in one skill with built-in async polling, so you don't need separate tools or manual API wiring for long-running jobs.
When to use it
- Generate product mockup images from text descriptions
- Animate a static photo into a short clip
- Edit a video's color grade or speed with a text prompt
- Create multiple image variations to explore visual concepts
- Produce social media video content from scene descriptions
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Generate a video of a golden retriever running through a sunny meadow
- 1Submit text-to-video request to Grok Imagine API with the prompt
- 2Receive job ID and begin polling for completion
- 3Send progress updates to user every few seconds
- 4Download completed video file to workspace on job success
MP4 video file delivered to the user via chat
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.