Generate and edit images via Google's Gemini API with Python.
npx skills add https://github.com/Kotrotsos/Content-Marketing --skill nanobanana-kotrotsos
Please help me install this Agent Skill. Skill: nanobanana Source: https://github.com/Kotrotsos/Content-Marketing/tree/main/.claude/skills/nanobanana Command: npx skills add https://github.com/Kotrotsos/Content-Marketing --skill nanobanana-kotrotsos
This Skill provides a CLI to generate and edit images using Google's Gemini API, helping you create visuals for articles, presentations, and marketing with less time and effort.
Example: nanobanana "A cat wearing a top hat in a library" to generate a hero image, or pass -i to edit an existing image. Output saved to your specified path or current directory.
High-intent search queries and answers about installing and using this skill.
Text-to-image generation with Gemini creates images directly from descriptive prompts. Use the nanobanana CLI with your prompt text, specify aspect ratio and size (1K, 2K, 4K), and the Gemini API generates the image to your chosen output path. Requires GEMINI_API_KEY or GOOGLE_API_KEY environment variable.
Yes, image editing with Gemini transforms existing images through style changes or reference-based modifications. Pass an input image with the -i flag along with your editing prompt to rework visuals for editorial or marketing use without regenerating from scratch.
Image generation with Gemini requires Python 3.10+, the google-genai and Pillow packages installed, and GEMINI_API_KEY or GOOGLE_API_KEY environment variables configured. These prerequisites enable API authentication and image processing.
Output controls let you specify aspect ratios and sizes (1K, 2K, 4K) before generation to match editorial layouts and content requirements. Pass these parameters via the CLI to ensure generated images fit your hero image, article illustration, or social media specifications.
Gemini-powered generation reduces iteration time for hero images and editorial illustrations by creating polished visuals from text prompts in seconds. This approach suits content planning workflows where rapid visual prototyping and refinement accelerate editorial timelines.
Gemini handles both text-to-image generation and image editing in a single workflow, eliminating the need to switch between specialized tools. For articles, presentations, and marketing campaigns, this unified approach streamlines visual content production within Python environments.
joonlabGenerate and edit images with Google Gemini models via a command-line interface.
canva-sdksResize Canva designs to five social media formats with PNG exports.
Dante-danCompress and convert image files to WebP, PNG, or JPEG formats.
SignmanalGenerate images from text prompts using Stable Diffusion and HuggingFace Diffusers.
