A professional-grade AI skill for generating high-quality images via Krea.ai using advanced models like Flux and Imagen.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install krea-api
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 krea-api 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 Krea.ai Image Generation Skill?
The Krea.ai Image Generation Skill is a robust technical interface designed to bridge the gap between AI agents and top-tier generative models. It allows for the seamless creation of visual assets using a variety of engines, including Flux for general high-quality output and Ideogram for superior text rendering. As a core component within the Openclaw Skills library, it emphasizes security and performance by utilizing a dependency-free approach and secure credential handling.
This skill is particularly valuable for developers who need to automate visual content creation without the overhead of complex library installations. By leveraging the Krea.ai API, users gain access to Google's Imagen 4 and other cutting-edge models through a unified and simplified workflow, making it an essential addition to any developer's Openclaw Skills toolkit.
Krea.ai Image Generation Skill Use Cases
- Automating the creation of marketing visuals and social media assets using specific models like Flux.
- Integrating high-fidelity image generation into larger AI agent workflows for automated design tasks.
- Generating images with precise text elements using the Ideogram 3.0 model integration.
- Rapidly prototyping visual concepts by switching between multiple AI models through a single command-line interface.
- Programmatically generating custom-sized imagery for web and mobile application development within the Openclaw Skills environment.
How Krea.ai Image Generation Skill Works
- The skill initializes by loading secure API credentials from a localized JSON file to ensure safe authentication.
- When a prompt is submitted, the skill performs input validation to ensure parameters like dimensions and steps fall within the Krea.ai API limits.
- An asynchronous POST request is sent to the Krea.ai generation endpoint, selecting the specific model requested by the user.
- The skill enters a polling phase, monitoring the job status until the image generation is complete.
- Once the job succeeds, the skill retrieves and returns the final image URLs to the user, providing a reliable outcome for Openclaw Skills automations.
Krea.ai Image Generation Skill Setup
To get started with this skill, follow these installation steps:
- Prepare the local credentials directory:
mkdir -p ~/.openclaw/credentials
- Create the credentials file using your Krea.ai API Key (format should be KEY_ID:SECRET):
echo '{"apiKey": "YOUR_KEY_ID:YOUR_SECRET"}' > ~/.openclaw/credentials/krea.json
- Apply secure file permissions to protect your secrets:
chmod 600 ~/.openclaw/credentials/krea.json
Krea.ai Image Generation Skill Data Schema & Taxonomy
The Krea.ai Image Generation Skill organizes its data and configuration as follows:
| Data Component | Format/Path | Purpose |
|---|---|---|
| Credentials | ~/.openclaw/credentials/krea.json |
Stores the API Key ID and Secret securely |
| Prompt Data | String (max 1800 chars) | The textual description for image generation |
| Parameters | JSON Object | Includes width, height, steps, and guidance scale |
| Model List | CLI Output | Dynamically lists supported models like flux, imagen-4, and ideogram-3.0 |
Data output is typically returned as a list of image URLs following successful job completion within the Openclaw Skills framework.
Krea.ai Image Generation Skill Advanced Features
- Multi-model support allowing users to toggle between Flux, Imagen 4, Ideogram 3.0, and fast preview models like nano-banana.
- Async job-based architecture that enables efficient polling and status tracking for long-running generation tasks.
- Zero-dependency implementation using only the Python standard library, ensuring maximum compatibility and security for Openclaw Skills.
- Flexible parameter control for power users, including custom seeds for reproducibility and adjustable guidance scales for prompt adherence.
- Built-in job history retrieval and model discovery tools directly accessible via the CLI.
SKILL.md
Loading
Related Openclaw Skills
FOSMVVM ViewModel Test Generator
A specialized generator for creating Swift ViewModel tests that validate data integrity, versioning, and multi-locale localization.
FOSMVVM ViewModel Generator
Automate the creation of type-safe, localized ViewModels and factories for SwiftUI using the FOSMVVM architecture.
FOSMVVM UI Tests Generator
Automates the creation of robust UI tests for FOSMVVM SwiftUI views using XCTest and the FOSTestingUI framework.
FOSMVVM SwiftUI View Generator
A specialized generator for creating standardized SwiftUI views that render FOSMVVM ViewModels with built-in state management and architectural alignment.
sam-tts
A retro robotic text-to-speech engine for AI agents that recreates the iconic Commodore 64 SAM voice.
Telegram Context
A toggle-enabled skill that retrieves recent Telegram message history to ensure conversational continuity across agent sessions.
METADATA
Featured*
