Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
What This Skill Does
Generates images from text prompts using Zhipu AI's CogView-4 model via API calls. Requires a Zhipu AI API key and communicates over HTTPS with input validation and JSON escaping built in.
Uses CogView-4, a model specifically trained on Chinese-language and culturally relevant content, making it more suitable than Western alternatives for prompts involving Chinese aesthetics or subjects.
When to use it
- Generate illustrations from text descriptions
- Create concept art for a project
- Produce reference images for design work
- Generate images of specific scenes or characters
- Quickly prototype visual ideas without design tools
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Generate an image of a mountain village at sunset
- 1Set ZHIPU_API_KEY environment variable
- 2Construct JSON payload with model cogview-4 and the prompt
- 3Send POST request to Zhipu AI images/generations endpoint via curl
- 4Parse response with jq to extract image URL
A URL pointing to the generated image of a mountain village at sunset
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.