gemini-imagegen

Generate images from text prompts by providing a description to the Skill, which uses the Gemini API to create visuals. Specify dimensions, output format (PNG or JPEG), and the Skill saves the generated image to your local disk for immediate use in marketing, UI mockups, or concept art.

Yes, image editing transforms styles or modifies elements within existing images using AI. Upload a source image and describe the changes you want; the Skill applies those edits and saves the result locally, enabling rapid iteration on design concepts.

You need a Gemini API key (set as GEMINI_API_KEY environment variable) to authenticate requests. The Skill uses the gemini-2.0-flash-exp model by default and requires the @google/generative-ai dependency, handling all setup so you can start generating images immediately.

Compose images by combining multiple source images into layouts or collages using the Skill's composition feature. Define your layout preferences, and the Skill generates presentation-ready composite assets saved as PNG or JPEG files to your specified output path.

Yes, automate image generation, editing, and composition to accelerate visual content workflows and reduce manual design time. The Skill integrates into local design workflows, enabling rapid prototyping of marketing visuals, UI mockups, and concept art without switching tools.

The Skill produces PNG or JPEG outputs and accepts options for custom width and height dimensions. Save results to any local path, and configure the Gemini model parameters to match your quality and performance needs for different asset types.