skills.rest
letta-ai
letta-aiOFFICIAL
Explore all skills by this author →
Website𝕏@letta_aiGitHub

nano-banana-pro

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

327|85|Updated Jan 29, 2026
Search Tags:#image#composition#generate#prompt#image-editing#Gemini-3-Pro
One-click install
npx skills add https://github.com/letta-ai/lettabot --skill nano-banana-pro-letta-ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/letta-ai/lettabot/tree/main/.skills/nano-banana-pro
Command: npx skills add https://github.com/letta-ai/lettabot --skill nano-banana-pro-letta-ai

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 creation and editing of images using Gemini 3 Pro, facilitating quick visualization and concept exploration without requiring professional design tools.

Core Features & Use Cases

  • Generate new imagery from prompts using Gemini 3 Pro Image.
  • Edit existing images by applying prompts and an input image.
  • Combine multiple images into a single scene with several inputs to create concept art, marketing visuals, or product previews.
  • Works with local scripts via the uv runner to streamline image workflows.

Quick Start

Install and configure the nano-banana-pro skill, then run:

  • uv run {baseDir}/scripts/generate_image.py --prompt "a futuristic city skyline at sunset" --filename "output.png" --resolution 1K
  • If you want to edit an image, provide -i /path/to/input.png with a prompt and the same command.

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 using the Gemini 3 Pro Image API?▼

To generate images with Gemini 3 Pro, run the Python script via uv with a text prompt, output filename, and resolution to create new imagery from your descriptions.

Can I edit an existing image with a prompt using Gemini 3 Pro?▼

Yes, you can edit an existing image by providing the input file path with the -i flag alongside your text prompt to apply modifications using Gemini 3 Pro.

What is multi-image composition and how does it work for marketing visuals?▼

Multi-image composition combines several input images into a single scene using Gemini 3 Pro, allowing you to generate concept art, marketing visuals, or product previews.

Do I need an API key to run the image generation scripts?▼

Yes, you must configure a GEMINI_API_KEY before executing the script with the uv runner to authenticate your image generation and editing requests.

What Python dependencies are required for image editing with Gemini?▼

You need the google-genai and pillow Python libraries installed in your environment to handle the Gemini API interactions and image processing tasks.

Can I specify the output resolution when generating new imagery?▼

Yes, provide the desired resolution parameter like 1K in the command line arguments when running the generation script to control the output image dimensions.

Related Skills

Explore More Design & Creative Skills→
joonlabjoonlab
8

nano-banana-pro

Generate and edit images with Google Gemini models via a command-line interface.

Community
Intermediate
rmjamesrmjames
1

image-processor

Resize and crop raster and SVG images with ImageMagick and SVGO.

Community
Advanced
marmikcfcmarmikcfc

nano-banana-image-gen

Generate images from text prompts via the Nano Banana API on Orthogonal.

Community
Intermediate
danfrdndanfrdn

gemini-imagegen

Generate and edit images using the Gemini API with text prompts.

Community
Intermediate