openclaw-media-gen

What This Skill Does

The openclaw-media-gen skill serves as a high-performance unified interface for generating high-fidelity images and professional-grade videos within the OpenClaw environment. By leveraging the AIsa API, this skill abstracts the complexities of interacting with multiple backend models, specifically Gemini 3 Pro for image synthesis and Qwen Wan 2.6 (Tongyi Wanxiang) for video generation. It is designed to provide developers and creators with a cost-effective, streamlined workflow for multimedia production, significantly undercutting official pricing from major platforms like Bailian while maintaining enterprise-level quality.

Installation

To integrate this capability into your OpenClaw agent, execute the following command in your terminal: clawhub install openclaw/skills/skills/bowen-dotcom/aisa-media-gen-en-skill After installation, ensure you have your AIsa API key ready. Set it as an environment variable in your session: export AISA_API_KEY="your_key_here" This allows the agent to authenticate seamlessly with the underlying AIsa infrastructure for both synchronous image requests and asynchronous video rendering tasks.

Use Cases

This skill is perfect for developers building automated content pipelines, social media managers generating rapid visual assets, and creators looking to prototype cinematic video shots. Because it supports both static imagery and complex text-to-video, it is ideal for generating consistent visual narratives, storyboarding, or creating engaging promotional material without needing to switch between different service providers or manage multiple disparate API keys.

Example Prompts

1. "Generate a high-resolution image of a futuristic cyberpunk city at night with neon signs reflecting on wet pavement."
2. "Create a 5-second video clip using a reference image of a forest: simulate a slow camera push-in with gentle wind moving the leaves, keeping the lighting cinematic."
3. "Generate a professional product photography image of a minimalist ceramic coffee cup on a wooden table, soft natural sunlight."

Tips & Limitations

• Cost Efficiency: Always monitor your usage, as video generation follows an async task model and incurs costs based on resolution settings.
• Async Handling: Remember that video generation requires the X-DashScope-Async: enable header; if the task takes time, ensure your script is prepared to poll for completion.
• Pricing: Take advantage of the contract pricing if you are running production workloads, as this is significantly cheaper than official retail rates.
• Limitations: The skill depends strictly on AIsa's availability; if the upstream API experiences downtime, video generation tasks will be queued or rejected.