skills.rest
x402agent
x402agentCOMMUNITY
Explore all skills by this author →
Website𝕏@clawddevsGitHub

nano-banana-pro

Generate or edit images with Gemini 3 Pro Image using prompts and input images.

Updated Mar 11, 2026
Search Tags:#editing#image#composition#gemini#generate#pro#api-key
One-click install
npx skills add https://github.com/x402agent/NanoSolana --skill nano-banana-pro-x402agent
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/x402agent/NanoSolana/tree/main/skills/nano-banana-pro
Command: npx skills add https://github.com/x402agent/NanoSolana --skill nano-banana-pro-x402agent

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?

Generate or edit images with Gemini 3 Pro Image using prompts and optional input images, enabling rapid visual prototyping and creative experiments.

Core Features & Use Cases

  • Generate images from text prompts using Gemini 3 Pro Image with configurable resolution and aspect ratio.
  • Edit and composite multiple input images (up to 14) into a single output, supporting up to 4K resolutions and various aspect ratios.
  • Provide an end-to-end workflow from prompt-driven generation to saving PNG outputs, with API-key authentication and local file handling.

Quick Start

Run the bundled generate_image.py script via uv to generate or edit images using a prompt and optional input images.

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?▼

Generate images from text prompts using Gemini by running the bundled script with the google-genai client. You provide a text prompt, configure resolution and aspect ratio, and the script saves the output as a PNG file.

Can I composite multiple images together with Gemini 3 Pro?▼

Composite multiple images with Gemini 3 Pro by supplying up to 14 input images in your script execution. The tool processes them simultaneously to edit and merge visual elements into a single high-resolution output up to 4K.

Do I need an API key to edit images locally with this tool?▼

An API key is required to edit images locally with this tool. The workflow uses API-key authenticated operations via the google-genai client to process your prompts and handle local file inputs securely.

What image resolutions and aspect ratios does Gemini 3 Pro support?▼

Gemini 3 Pro supports configurable resolutions up to 4K and various aspect ratios for image generation and editing. You set these parameters in the script to control the dimensions of the final PNG output.

How does local image handling work with the google-genai client and PIL?▼

Local image handling with the google-genai client and PIL works by loading input files via Pillow and passing them to the Gemini API. The script manages file I/O and applies robust error management to prevent processing failures.

Related Skills

Explore More Design & Creative Skills→
shane9coyshane9coy
1

nano-banana-pro

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

Community
Intermediate
corbintalbert9744-artcorbintalbert9744-art

photo-editor

Resize, crop, adjust, convert, and retouch images using Pillow, sharp, OpenCV, and rembg.

Community
Intermediate
qsimeonqsimeon
1

nano-banana-pro

Generates and edits images using the Gemini 3 Pro Image API.

Community
Intermediate
RedWoodOGRedWoodOG
174

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion and diffusers pipelines.

Community
Advanced