generate-image

The generate-image skill enables users to create and edit high-quality images using AI-powered models such as FLUX.2 Pro and Gemini 3 Pro. It addresses the challenge of producing custom visuals quickly without requiring advanced graphic design skills. By leveraging natural language prompts, users can generate illustrations, diagrams, infographics, and artistic images directly from descriptive text. Additionally, the skill allows for modifying existing images, offering flexibility to adjust colors, add or remove elements, or perform style transfers, making it a comprehensive solution for visual content creation.

Key features include seamless integration with OpenRouter's image generation models, support for multiple models with different performance and quality characteristics, and the ability to edit images based on user-provided instructions. Users can specify input images, select preferred models, and define custom output paths. The script handles API key management, error detection, and outputs images in standard PNG format. The skill supports both single-image generation and batch creation through repeated execution with varied prompts, catering to diverse workflow needs.

This skill is ideal for researchers, educators, content creators, and designers who require rapid prototyping of visual materials. It is particularly useful for producing scientific illustrations, posters, concept visualizations, and explanatory graphics. By simplifying the image creation process, it reduces reliance on manual design tools, enabling users to focus on creative and communicative aspects of their projects. Its flexibility and model selection options make it suitable for a broad audience, from hobbyists to professionals in technical and creative fields.