openclaw-media-gen

What This Skill Does

The openclaw-media-gen skill serves as a unified interface for high-fidelity media production, leveraging the AIsa API to orchestrate both image and video generation workflows. This skill bridges the gap between text-based AI commands and visual output by integrating Gemini 3 Pro Image (gemini-3-pro-image-preview) for text-to-image synthesis and Qwen Wan 2.6 (wan2.6-t2v) for text-to-video generation. It simplifies complex API interactions into a developer-friendly command-line tool, handling authentication, request structure, and asynchronous task management for video rendering.

Installation

To integrate this skill into your OpenClaw environment, ensure you have the OpenClaw CLI tool installed. Execute the following command in your terminal: clawhub install openclaw/skills/skills/0xjordansg-yolo/openclaw-aisa-image-video-models-wan2-6-gemini-3-pro-image-nano-banana

Once installed, you must configure your environment variable by adding your API key: export AISA_API_KEY="your-key". The skill uses this key for both the image generation endpoints and the asynchronous video synthesis services.

Use Cases

This skill is ideal for content creators, developers, and automation engineers looking to automate visual assets production. You can use it to build rapid prototyping pipelines for social media content, create assets for digital storytelling, or integrate generative media into larger autonomous workflows. Because it utilizes asynchronous polling for video, it is perfectly suited for batch-processing workflows where multiple videos are queued for generation.

Example Prompts

1. "Generate a high-quality image of a cyberpunk city street at night, with neon reflections on wet pavement, cinematic lighting, 8k resolution."
2. "Create a 5-second video from this image: https://example.com/character.jpg, using the prompt 'the character turns their head slowly and smiles, soft studio lighting'."
3. "Check the status of my recent video generation request using the task ID: 12345-abc-67890."

Tips & Limitations

• Video Latency: Note that Wan 2.6 generation is an asynchronous process. Always use the video-status command to check the progress of your task instead of expecting an immediate response.
• Image Source: When generating video, the quality of your input img_url significantly influences the final result. High-resolution, clear subject images perform best.
• API Limits: Ensure your AIsa account has sufficient credits, as video generation via Wan 2.6 is compute-intensive and consumes more resources than static image generation.
• Error Handling: The script automates base64 decoding for images; ensure your local environment has write permissions to the directory specified in the --out parameter.