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 EvoLink's z-image-turbo API at approximately $0.0036 per image. Supports nine aspect ratios and runs via Python, PowerShell, or curl. Images are saved locally; the download URL expires after 24 hours but the local file persists.
At ~$0.0036 per image, it costs a fraction of mainstream AI image APIs like DALL-E or Stable Diffusion hosted services.
When to use it
- Generating a visual concept without a paid Midjourney or DALL-E subscription
- Creating illustration drafts for blog posts at minimal cost
- Batch producing reference images for a design mood board
- Quickly visualizing a product idea from a text description
- Generating social media images in specific aspect ratios like 9:16 or 16:9
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: generate image: a golden retriever puppy in a field of sunflowers
- 1Extracts the prompt from the trigger phrase after the colon
- 2Sets the aspect ratio to the default 1:1
- 3Calls the EvoLink z-image-turbo API with the prompt and size parameters
- 4Downloads the returned image and saves it locally
- 5Outputs MEDIA:<path> so the file is auto-attached to the conversation
Local image file of a golden retriever puppy in a sunflower field, attached to the conversation
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.