generate-image

Generating scientific illustrations from text prompts requires providing a descriptive text prompt to an AI model. This Skill automates that process by sending your custom instructions to OpenRouter models to produce detailed visual schematics and abstract artwork.

Editing existing images and applying style transfers is supported by providing an input image alongside custom instructions. The Skill modifies visuals by changing colors, adding elements, or transferring styles based on your specific text guidance.

API access to OpenRouter models is required for AI image generation. The Skill relies on connecting to models such as Gemini or Flux through your API access to automate the creation and modification of high-quality visual content.

The best way to create an infographic using AI is to use prompt-based generation for abstract illustrations or edit existing diagrams. This Skill streamlines designing scientific infographics by automating visual component generation and modification.

Generating visual explanations for scientific diagrams is fully supported. The Skill uses AI models to automate the creation of detailed schematics and visual explanations from your descriptive prompts and input images.

Using input images with custom instructions to modify diagrams is a core feature. The Skill processes your provided image and text instructions to add new components, alter colors, or apply visual enhancements to existing scientific diagrams.