Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
Security: Fix shell injection vulnerability in curl_heredoc.md
What This Skill Does
Generates images using the EvoLink z-image-turbo API at approximately $0.0036 per image. Submits a prompt, polls for completion, and saves the result locally. Supports nine aspect ratios and optional NSFW filtering.
At roughly $0.0036 per image, it costs significantly less than most competing text-to-image APIs while still supporting multiple aspect ratios and reproducible seeds.
When to use it
- Generate a product mockup image from a text description
- Create a custom illustration for a blog post
- Batch-generate concept art variants with a fixed seed
- Produce a 16:9 banner image for a presentation
- Quickly visualize a scene from a written story
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: generate image: a red fox sitting in a snowy forest at dusk
- 1Read EVOLINK_API_KEY from environment
- 2POST to /images/generations with model z-image-turbo, the prompt, and size 1:1
- 3Poll GET /tasks/{id} every 10 seconds until status is completed
- 4Download the image URL from results[0], detect format from URL
- 5Sanitize filename and save as evolink-<timestamp>.<ext>, then print MEDIA:<absolute_path>
Image saved locally as evolink-1741824000.webp and attached to the conversation
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.