A comprehensive CLI-driven skill to generate, edit, and upscale AI imagery using over 50 industry-leading models.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install ai-image-gen-pro
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install ai-image-gen-pro using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is AI Image Generation?
The AI Image Generation skill is a powerhouse for developers and creators looking to integrate professional-grade generative AI into their workflows. By utilizing the inference.sh CLI, this extension provides a unified gateway to over 50 state-of-the-art models including FLUX.1, Google Gemini 3 Pro, xAI Grok Imagine, and Seedream. It is designed to be a core part of the Openclaw Skills ecosystem, offering a reliable and scalable alternative to individual API integrations.
This skill goes beyond simple text-to-image generation. It supports advanced techniques such as image-to-image transformations, inpainting, LoRA-based styling, and professional upscaling. Whether you are building automated design pipelines or interactive creative agents, this skill ensures you have the right model for every specific visual requirement, from ultra-fast drafts to 4K cinematic renders.
AI Image Generation Use Cases
- Creating hyper-realistic product mockups and marketing visuals for ecommerce.
- Generating cinematic concept art and character illustrations for game development.
- Producing social media graphics with accurate text rendering for branding.
- Automating high-fidelity image upscaling and restoration for legacy media assets.
- Prototyping UI/UX layouts and visual components via natural language prompts.
How AI Image Generation Works
- The user authenticates through the inference.sh CLI to access the global model registry.
- A specific model is selected based on the task requirements (e.g., FLUX for quality or P-Image for speed).
- The skill formats a JSON payload containing the prompt, aspect ratio, and any specific LoRA weights.
- The command is dispatched to the inference engine which processes the request using optimized hardware.
- The output, typically a high-resolution image URL or file path, is returned to the user or calling agent for further use.
AI Image Generation Setup
To get started with this component of Openclaw Skills, ensure the inference.sh CLI is installed and your session is active:
# Authenticate your CLI session
infsh login
# Run a test generation with the FLUX Dev model
infsh app run falai/flux-dev-lora --input '{"prompt": "a cat astronaut in space"}'
AI Image Generation Data Schema & Taxonomy
The skill utilizes a structured input schema to communicate with various model backends. Below is a standard representation of the data parameters used:
| Parameter | Type | Description |
|---|---|---|
| prompt | String | The primary text description for the generation. |
| aspect_ratio | String | The desired dimensions (e.g., 1:1, 16:9, 4:3). |
| image_url | String | Source URL for upscaling or image-to-image tasks. |
| input | JSON | A nested object containing model-specific hyperparameters. |
| direction | String | Alignment parameter for image stitching and layout tasks. |
AI Image Generation Advanced Features
- Support for LoRA integration to inject custom artistic styles into the FLUX ecosystem.
- Natural language image editing via the Reve model, allowing for intuitive modifications.
- Professional-grade 4K upscaling using Topaz Image Upscaler integration.
- Specialized text rendering capabilities for high-accuracy typography in AI art.
- Seamless orchestration with other Openclaw Skills like background removal and video generation.
SKILL.md
Loading
Related Openclaw Skills
Mindmap Generator
An automated skill designed to generate production-ready mindmaps, diagrams, and visual documentation from simple text prompts.
bearing-search
A specialized tool for searching bearing specifications, parsing model codes, and providing industrial selection recommendations.
HAI Agent Framework
An enterprise-grade AI agent framework featuring a robust hook system, automated memory extraction, and specialized core agents.
Incident Response Playbook
A structured AI framework for managing business and IT incidents through automated classification, communication, and post-mortem reporting.
OpenClaw Skill Quality Standard
A definitive quality framework for auditing and standardizing documentation to ensure peak performance for Openclaw Skills.
AI Video Generation
A comprehensive video production toolkit for generating, animating, and upscaling AI videos using over 40 industry-leading models.
Featured*
