openclaw-media-gen

Generate images and videos via the AIsa API using Gemini 3 Pro and Wan 2.6.

23|6|Updated Jan 30, 2026
One-click install
npx skills add https://github.com/AIsa-team/OpenClaw-Skills --skill openclaw-media-gen
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: openclaw-media-gen
Source: https://github.com/AIsa-team/OpenClaw-Skills/tree/main/media-gen
Command: npx skills add https://github.com/AIsa-team/OpenClaw-Skills --skill openclaw-media-gen

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

OpenClaw Media Gen provides a streamlined capability to generate imagery and short videos via the AIsa API, reducing the friction of sourcing or creating media assets for demos, marketing, and tutorials.

Core Features & Use Cases

  • Image generation via Gemini 3 Pro: create high-quality visuals from natural language prompts.
  • Video generation via Wan 2.6: asynchronously synthesize short videos from prompts with optional reference imagery.
  • Use Case: rapidly produce marketing visuals or tutorial assets for product launches and demos without a design team.

Quick Start

  1. Install Python 3 and ensure it is available in your environment.
  2. Export your API key: export AISA_API_KEY="your-key"
  3. Generate an image: python scripts/media_gen_client.py image --prompt "A futuristic city at dusk" --out output.png
  4. Create a video: python scripts/media_gen_client.py video-create --prompt "cinematic close-up, dynamic lighting" --img-url "https://example.com/reference.jpg" --duration 5

Frequently Asked Questions about openclaw-media-gen

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images and videos using a single API key?

You can generate images and videos with a single API key by configuring the AISA_API_KEY in your Python 3 environment and running the media generation script with your natural language prompts. This enables rapid creation of marketing visuals and tutorial assets.

Can I use a reference image to generate a short video from a prompt?

Yes, you can generate a video from a prompt using a reference image. The video generation process accepts an optional reference image URL and asynchronously synthesizes short videos using the Wan 2.6 endpoint.

What do I need to set up before generating advertising visuals with this API?

To generate advertising visuals, you need Python 3 installed, a valid AISA_API_KEY exported in your environment, and access to the Gemini 3 Pro and Wan 2.6 endpoints for image and video generation respectively.

How does natural language image generation work for product demos?

Natural language image generation for product demos works by issuing text prompts to the Gemini 3 Pro endpoint, which creates high-quality visuals suitable for product launches and quick prototyping without needing a design team.

What are the limitations of asynchronous video generation via the AIsa API?

The AIsa API asynchronously synthesizes short videos from prompts, meaning video generation is not instantaneous. It requires valid endpoints and is designed for short video formats suitable for social media visuals.