skills.rest
ain3sh
ain3shCOMMUNITY
Explore all skills by this author →
Website𝕏@ain3shGitHub

nano-banana-pro

Generate and edit images via Gemini 3 Pro Image API with resolution mapping.

12|1|Updated Jan 19, 2026
Search Tags:#images#generate#text-to-image#image-to-image#gemini-3-pro#image-editing
One-click install
npx skills add https://github.com/ain3sh/.agents --skill nano-banana-pro-ain3sh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/ain3sh/.agents/tree/main/skills/generate-image
Command: npx skills add https://github.com/ain3sh/.agents --skill nano-banana-pro-ain3sh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai>=1.0.0, pillow>=10.0.0, and includes scripts (resource) components.

What problem does it solve?

This Skill enables rapid generation and editing of images using Gemini 3 Pro, reducing iterative workload and enabling creators to prototype visuals quickly.

Core Features & Use Cases

  • Prompt-driven image generation: Create high-quality images from textual prompts with controllable resolutions (1K, 2K, 4K).
  • Image editing with prompts: Modify existing images by applying editing instructions and optional input images.
  • Iterative creative workflows: Support fast draft → iterate → final cycles with deterministic filename conventions and flexible prompts.

Quick Start

Use the nano-banana-pro skill to generate an image from a prompt, with a filename and optional input image; for example: uv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt "A serene futuristic city at dusk" --filename "2025-11-23-14-23-05-city.png" --resolution 4K Or to edit an existing image: uv run ~/.codex/skills/nano-banana-pro/scripts/generate_image.py --prompt "change to watercolor style" --filename "city-watercolor.png" --input-image "city-input.png" --resolution 2K

Frequently Asked Questions about nano-banana-pro

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

FAQPage Schema
How do I generate images from text prompts using Gemini 3 Pro?▼

To generate images from text prompts using Gemini 3 Pro, provide a descriptive prompt, specify an output filename, and select a resolution like 1K, 2K, or 4K. The system processes the prompt to produce high-quality image assets for rapid creative workflows.

Can I edit an existing image with a text prompt?▼

Yes, you can edit an existing image by passing an input image file along with editing instructions as a prompt. This image-to-image workflow applies textual changes to your existing asset at your chosen resolution.

What resolutions are supported for text-to-image generation?▼

Text-to-image generation supports 1K, 2K, and 4K resolutions. You can map your desired output quality by specifying the resolution parameter during the image creation process.

Do I need an API key to use Gemini 3 Pro for image generation?▼

Yes, you need an API key to use Gemini 3 Pro for image generation. The system enforces API key management through environment variable integration to authenticate and execute your image creation requests.

What Python dependencies are required for prompt-driven image editing?▼

Prompt-driven image editing requires the google-genai and pillow Python dependencies. These libraries handle the Gemini 3 Pro API calls and image processing tasks needed to execute your workflows.

Related Skills

Explore More Design & Creative Skills→
ClaudioCeppi83ClaudioCeppi83

nano-banana-pro

Generate and edit images via the Gemini 3 Pro Image API.

Community
Intermediate
evolv3aievolv3ai
3

sharp

Resize, convert, and optimize images with the Sharp library in Node.js.

Community
Intermediate
menoncellomenoncello
3

orchestrator-agent

Orchestrate subagents, commands, MCP servers, and skills with parallel execution.

Community
Intermediate
nesihaver-ILnesihaver-IL

nano-banana-pro

Generate branded visuals with Gemini 3 Pro Image API using configurable aspect ratios and resolutions.

Community
Intermediate