A powerful multimodal skill for generating and editing images via TokenRouter compatible models within the OpenClaw ecosystem.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tokenrouter-images
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 tokenrouter-images 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 TokenRouter Image Generator?
The TokenRouter Image Generator is an essential addition to the library of Openclaw Skills, enabling developers to integrate high-fidelity image generation and editing directly into their AI agent workflows. By leveraging the Palebluedot Ai (PBD)-TokenRouter multimodal API, this skill allows for seamless text-to-image and image-to-image transformations using industry-leading models like Gemini and GPT-5.
This skill is designed for precision, offering granular control over image configuration including aspect ratios and resolutions up to 4K. Whether you are building automated media pipelines or enhancing agent-led design tasks, incorporating these types of Openclaw Skills ensures your AI can interact with and create visual content effectively.
TokenRouter Image Generator Use Cases
- Create unique visual assets from text prompts using various AI models.
- Perform precise image editing and filtering on existing media files.
- Automate media generation for social media, marketing, or UI mockups.
- Integrate visual content creation into complex Openclaw Skills workflows.
- Quickly prototype different visual styles using the draft-iterate-final methodology.
How TokenRouter Image Generator Works
- The agent verifies the presence of the TokenRouter API key and ensures the necessary outbound directory structure exists.
- Users provide a text prompt describing the desired image or requested edits, along with optional configuration parameters like aspect ratio or image size.
- The script calls the TokenRouter multimodal API using the specified model, such as google/gemini-2.5-flash-image.
- For image-to-image requests, the skill processes the input file to apply requested changes while preserving the original style.
- The generated image is saved to the designated outbound directory using a standardized timestamped filename.
- The resulting file path is returned to the agent, allowing it to be used by other Openclaw Skills in a larger automation chain.
TokenRouter Image Generator Setup
To use this skill, ensure you have a TokenRouter API key from https://www.tokenrouter.com. You can provide the key via the --api-key argument, an environment variable, or by letting the script auto-detect it from your config.
# Create the required directory
mkdir -p ~/.openclaw/media/outbound
# Optional: Set environment variable
export PBD_TOKENROUTER_API_KEY="sk-your-key-here"
# Run the generation script
uv run ~/.openclaw/workspace/skills/pbd-tokenrouter-image-generator/scripts/generate_image.py \
--prompt "A serene mountain landscape in a studio Ghibli style" \
--filename "~/.openclaw/media/outbound/mountain.png" \
--model google/gemini-2.5-flash-image
TokenRouter Image Generator Data Schema & Taxonomy
The skill manages generated media files and metadata using a structured approach to ensure compatibility with other Openclaw Skills.
| Component | Details |
|---|---|
| Output Directory | Files are stored in ~/.openclaw/media/outbound/ |
| Filename Pattern | Uses yyyy-mm-dd-hh-mm-ss-name.png for versioning |
| Supported Models | google/gemini-2.5-flash-image, openai/gpt-5-image, and more |
| Image Config | Supports image_size (1K, 2K, 4K) and aspect_ratio (1:1, 16:9, etc.) |
| API Modalities | Always sends ["image", "text"] to the multimodal endpoint |
TokenRouter Image Generator Advanced Features
- Multi-model support including Google Gemini and OpenAI GPT-5 via a unified interface.
- Capability for high-resolution 4K image outputs for professional-grade assets.
- Automated API key discovery from the OpenClaw configuration file (
openclaw.json). - Specialized prompt handling for precise image-to-image edits that maintain style consistency.
- Seamless integration into multi-agent workflows within the broader ecosystem of Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Seedream PPT Maker
An automated image-based PPT generator leveraging the Baoyu layout framework and Seedream 5.0 text-to-image technology.
Inheritance Mapping Selector
A specialized architectural tool for selecting the optimal database persistence strategy for object-oriented inheritance hierarchies.
Enterprise Base Pattern Catalog
A comprehensive reference for the 11 fundamental enterprise patterns used to build robust, maintainable software architectures.
Explicit AI Video Generator Free
Generate professional 1080p MP4 videos from text prompts using an automated cloud-based AI rendering pipeline.
Visual Content Generator Claw
An AI-driven visual asset specialist designed to rapidly generate posters, social media images, video covers, and digital human backgrounds.
Video Maker Free Export
A powerful AI video editing skill that transforms raw clips into polished 1080p MP4 exports through simple text commands and remote GPU rendering.
Featured*
