Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Added new Security Constraints section detailing restrictions on LoRA parameter URLs, API tokens, and input validation. - Clarified that only well-known platform identifiers are allowed for LoRA weights (no arbitrary/user-provided URLs). - Stated that third-party API tokens must not be accepted or forwarded in prediction inputs. - Emphasized input parameters must match the model's request schema, and model slugs should be validated before prediction.
What This Skill Does
Generates images from text prompts using 60+ AI models via the EachLabs Predictions API. Supports model families including Flux, GPT Image, Gemini, Imagen, Seedream, and Ideogram. Uses an async prediction flow: submit a job, poll for the result, then retrieve the output URL.
Access to 60+ models from multiple providers through a single API key and unified request schema eliminates the need to manage separate accounts and integrations for each model family.
When to use it
- Generate product mockup images from a description
- Create social media visuals from a text brief
- Prototype logo concepts with transparent backgrounds
- Produce illustrations for blog posts or presentations
- Generate training dataset images with specific visual styles
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Generate a photorealistic image of a red vintage Porsche 911 on a mountain road at golden hour, landscape format
- 1Validate the target model by calling GET /v1/model?slug=flux-2-turbo-text-to-image to confirm the slug and retrieve the request schema
- 2Submit a POST to /v1/prediction with the model slug, version 0.0.1, prompt, image_size set to landscape_16_9, and output_format png
- 3Poll GET /v1/prediction/{id} every few seconds until status is success or failed
- 4Extract the output image URL from the response and return it to the user
A URL pointing to the generated PNG image hosted on EachLabs infrastructure
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.