nanobanana

The Nanobanana skill enables users to generate and edit high-quality images using Google's Gemini 3 Pro Image model, also known as Nano Banana Pro. It solves the challenge of creating visually compelling images from text prompts or enhancing existing images without the need for advanced graphic design skills. By providing a simple interface through Python scripts or API calls, Nanobanana streamlines the process of producing both artistic and photorealistic visuals, making advanced image generation accessible to developers, designers, and content creators.

Nanobanana offers a variety of features that cover multiple image generation and editing needs. Users can create images from text prompts, edit existing images by modifying elements such as backgrounds, colors, or objects, and generate visuals in various aspect ratios including standard, widescreen, and cinematic formats. The skill supports high-resolution outputs up to 4K, enabling detailed and professional-quality images. Additionally, it includes a Google Search grounding option to improve factual accuracy for images involving real-world subjects. Batch generation functionality and Python API access allow for programmatic control and automation, catering to both single-image and large-scale image creation workflows.

This skill is ideal for developers, digital artists, marketers, and educators who require rapid and versatile image creation. Common use cases include producing marketing visuals, concept art, illustrations, social media content, and prototype designs. Its flexibility in editing and high-resolution capabilities also make it suitable for professional presentations, product photography, and creative experimentation. Nanobanana targets users who need reliable, high-quality AI-generated images without investing in extensive manual graphic design effort.