nano-banana-pro

To generate high-resolution images, use this Skill to send text prompts or input images to the Gemini 3 Pro Image API. It supports text-to-image and image-to-image workflows at 1K, 2K, and 4K resolutions, saving outputs as PNG files.

Yes, editing existing images requires a Gemini API key, which you must provide via the --api-key command line argument or the GEMINI_API_KEY environment variable. The API key authenticates your requests to the Gemini 3 Pro Image service.

Yes, you can control the output resolution when generating images from text prompts. The Skill explicitly supports 1K, 2K, and 4K resolution settings, allowing you to match the image quality to your specific creative workflow requirements.

The best way to modify an existing image is to provide the input image alongside an editing prompt. The Skill processes both inputs through the Gemini 3 Pro Image API, applies the requested changes, and saves the refined visual as a PNG file.

AI-assisted image generation and saving support PNG file format for outputs. The Skill saves the generated or edited high-resolution images directly to your current working directory and returns the full file path.

Yes, this workflow requires installing specific Python dependencies, namely the google-genai and pillow libraries. These packages handle the Gemini API communication and image processing required for the generation and editing tasks.