yollomi-ai-api

What This Skill Does

The yollomi-ai-api skill serves as a high-performance, unified gateway for AI media generation within the OpenClaw ecosystem. By abstracting the complexity of various generative AI backends, this skill allows users to trigger image and video synthesis through a single, consistent API interface. Whether you need to generate high-fidelity illustrations, cinematic video sequences, or perform utility tasks like background removal, the skill acts as a bridge between the agent and Yollomi’s specialized model suite.

Installation

To integrate this skill into your environment, execute the following command in your terminal: clawhub install openclaw/skills/skills/anichikage/yollomi Ensure that you have set the YOLLOMI_API_KEY environment variable within your configuration. For custom infrastructure setups, you may optionally configure the YOLLOMI_BASE_URL to point to a proxy or private deployment.

Use Cases

This skill is designed for creators, developers, and power users who require programmatic access to generative AI. Common use cases include:

• Content Creation: Batch generating high-quality assets for websites, social media, or game development.
• Automation Workflows: Integrating automated background removal into an image processing pipeline.
• Prototyping: Quickly iterating on video concepts using different model identifiers (such as the Kling series) directly from a command line or agentic flow.
• Asset Management: Using the list-models endpoint to dynamically adapt workflows to the latest available AI models without manual code changes.

Example Prompts

1. "Generate a 16:9 cinematic landscape image of a futuristic cyberpunk city using the Flux model."
2. "Remove the background from the image at https://example.com/product.png and return the result."
3. "Create a video of a golden retriever playing in a park using the kling-2-1 model."

Tips & Limitations

• Efficiency: Always check your remaining credits by monitoring the JSON response fields to avoid service interruptions.
• Aspect Ratios: While 1:1 is the default, remember to specify 16:9 or 9:16 when requesting images to ensure optimal composition for your specific media requirements.
• Dependencies: The skill requires an active internet connection to communicate with the Yollomi API. Be mindful of potential latency during high-demand periods, as video generation naturally takes longer than standard image synthesis.