Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Fix: TIMESTAMP bug in Python f-strings. Fix: consistent paths with expanduser. Added editing limitation note.
What This Skill Does
Generates images from text prompts using xAI's Grok/Flux API, outputting PNG files saved locally. Also handles style-transfer editing by using an existing image as a reference for a new generation. Supports aspect ratio selection and batch generation of up to 10 images per request.
Using base64 response format avoids temporary URL expiry issues common with other image generation APIs.
When to use it
- Generate a product mockup image from a text description
- Create a batch of social media thumbnails in 1:1 format
- Apply an oil painting style to a photo from a local file
- Generate a widescreen banner from a prompt with 2:1 aspect ratio
- Reimagine an existing image as a pencil sketch
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: generate a PNG of a futuristic cityscape at sunset, widescreen format
- 1Sets prompt to 'futuristic cityscape at sunset' and aspect_ratio to '16:9'
- 2Calls xAI /v1/images/generations endpoint with model grok-imagine-image-pro
- 3Receives base64-encoded image data in response
- 4Decodes and saves PNG to ~/.openclaw/media/generated_<timestamp>_0.png
- 5Returns the file path to the user
PNG file saved at ~/.openclaw/media/generated_1710000000_0.png
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.