generate-image

Image generation from text prompts uses AI models to create visuals based on your description. This Skill automates that process by accepting a text prompt, sending it to AI models like Flux or Gemini, and saving the output as a PNG file suitable for documents and presentations.

Yes, image editing with AI text instructions lets you modify existing images by describing the changes you want. This Skill supports editing by accepting both an input image and textual instructions, encoding them for processing, and outputting the edited result as PNG.

This Skill supports multiple models through OpenRouter, including Gemini 3 Pro image preview, Flux.2 Pro, and generation-only variants. Model selection depends on your use case—some excel at diagrams and infographics, others at detailed scientific illustrations.

Yes, an OpenRouter API key is required to use this Skill. The key authenticates your requests to the AI models and enables access to image generation and editing capabilities for diagrams, infographics, and visual explanations.

This Skill saves all generated and edited images as PNG files, a format well-suited for scientific diagrams, infographics, and visuals in documents and presentations while maintaining quality and clarity.

Yes, this Skill is designed for scientific visuals including diagrams, schematics, infographics, concept visualizations, and technical illustrations. It automates generation and editing workflows for scientific documentation and visual explanations.