skills.rest
Nymbo
NymboCOMMUNITY
Explore all skills by this author →
𝕏@nymboqtGitHub

nano-banana

Generate and edit images via the Gemini API from prompts and references.

Updated Aug 23, 2026
Search Tags:#gemini#image-generation#mockups#image-editing#style-transfer#logos#AI-art
One-click install
npx skills add https://github.com/Nymbo/Skills --skill nano-banana-nymbo
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana
Source: https://github.com/Nymbo/Skills/tree/main/nano-banana
Command: npx skills add https://github.com/Nymbo/Skills --skill nano-banana-nymbo

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires Pillow, google-generativeai, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Generate and edit images using Google's Gemini API. This supports text-to-image, image editing, multi-turn refinement, and composition from multiple references.

Core Features & Use Cases

  • Text-to-Image: Generate images from prompts.
  • Image Editing: Edit existing images via prompts.
  • Multi-Turn Refinement: Refine images across turns.
  • Multi-Reference Composition: Combine multiple references.

Quick Start

Generate an image using prompt "A cat wearing a wizard hat" and save to output.png.

Frequently Asked Questions about nano-banana

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images from text prompts using the Gemini API?▼

Text-to-image generation with Gemini API converts your written prompts into images by calling the gemini-2.5-flash-image or gemini-3-pro-image-preview models. Specify your prompt, configure aspect_ratio and image_size options, and the API returns generated visuals saved to your output file.

Can I edit existing images with Gemini instead of generating from scratch?▼

Yes, image editing with Gemini API modifies existing images based on text instructions. Upload your reference image and describe the edits you want; the model processes both the image and prompt to produce refined output without regenerating from text alone.

What's the best way to combine multiple reference images into one composition?▼

Multi-reference composition lets you submit up to 14 reference images alongside a prompt to guide the Gemini API's output. This approach works for logos, stickers, and product mockups where you're blending visual elements from multiple sources into a cohesive result.

Does this Skill support refining images across multiple turns?▼

Yes, multi-turn refinement lets you iteratively improve images in a conversation flow. Generate an initial image, review the output, then submit follow-up prompts to adjust composition, style, or details without restarting from scratch.

What image formats and sizes does Gemini API support?▼

The Gemini API accepts configurable image_size and aspect_ratio parameters to control output dimensions. Support includes standard web and print formats; exact size constraints depend on your chosen model variant and authentication via GEMINI_API_KEY.

Do I need Pillow installed to use image generation with Gemini?▼

Yes, Pillow is a required dependency for image processing. It handles image manipulation, format conversion, and file I/O operations alongside the google-generativeai library that connects to the Gemini API.

Related Skills

Explore More Design & Creative Skills→
GPTtangGPTtang
4

image-gen

Generate images via OpenAI, Google, and DashScope APIs with text prompts.

Community
Intermediate
adminsairolotech-bitadminsairolotech-bit

photo-editor

Automate image resizing, cropping, filtering, and optimization with Pillow and sharp.

Community
Advanced
buda-aibuda-ai
25

batch-image-generator

Generate multiple images from prompts with consistent styling.

Official
Advanced
truongnattruongnat

ai-design-pro

Generate AI-enhanced design assets using Midjourney, DALL-E, and Stable Diffusion.

Community
Advanced