zenmux-image-generation

What This Skill Does

The zenmux-image-generation skill acts as a powerful interface between OpenClaw and the ZenMux API, specifically leveraging the Gemini 3 Pro (Nano Banana Pro) model. This skill enables users to create high-quality, professional-grade imagery directly from their command-line or automated agent workflows. Whether you need to generate visuals from scratch, transform existing photos into new styles, or blend multiple references into a single cohesive piece of art, this skill provides a streamlined, programmable pipeline for complex image generation tasks.

Installation

To integrate this capability into your OpenClaw environment, ensure you have your ZenMux credentials ready, as this skill requires a Pro or Elite account. Run the following command in your terminal to install the skill:

clawhub install openclaw/skills/skills/dadaniya99/zenmux-image-generation

Once installed, you must export your API key to your environment variables to authorize the API calls: export ZENMUX_API_KEY="your_key_here".

Use Cases

This skill is highly versatile for creative and professional applications. You can use it for rapid prototyping of character designs in game development, generating marketing assets from concept sketches, or automating the creation of social media imagery. The Multi-Image Fusion capability is particularly effective for character consistency, allowing you to map specific subjects into varied environmental contexts while retaining core visual features.

Example Prompts

1. "Generate a portrait of a futuristic astronaut standing on a neon-lit martian landscape using the default settings."
2. "Take my reference file headshot.png and apply a professional studio lighting effect using the ZenMux generator."
3. "Create a composite image using person.png and armor.png, ensuring the person is wearing the armor style shown in the second image."

Tips & Limitations

To get the best results, always be specific in your prompts regarding lighting, composition, and art style. While the model is highly capable, remember that multi-image fusion performance depends on the clarity of your input files. Ensure that reference images are high-resolution to avoid pixelation or confusion in the fusion process. This skill does not store your API keys persistently, so ensure your environment configuration is secure. Note that the output format defaults to PNG; if you need specific file sizes or extensions, you may need to post-process the output.