skills.rest
NikiforovAll
NikiforovAllCOMMUNITY
Explore all skills by this author →
Website𝕏@nikiforovallGitHub

nano-banana

Run inline Python scripts with uv to generate Gemini images.

137|20|Updated Jun 13, 2025
Search Tags:#python#uv#Gemini#scripting#image-generation#ai-art
One-click install
npx skills add https://github.com/NikiforovAll/claude-code-rules --skill nano-banana-nikiforovall
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana
Source: https://github.com/NikiforovAll/claude-code-rules/tree/main/plugins/handbook-nano-banana/skills/nano-banana
Command: npx skills add https://github.com/NikiforovAll/claude-code-rules --skill nano-banana-nikiforovall

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables rapid Python-based scripting to drive Gemini image generation, enabling quick iterations and automated asset production without heavy project setup.

Core Features & Use Cases

  • Inline Python scripting: Write and execute small scripts directly with uv run.
  • Image generation flow: Generate and save assets using Gemini models.
  • Directives & dependencies: Use runtime directives to manage packages and SDKs.

Quick Start

Run a simple image generation script with uv run -: uv run - << 'EOF'

/// script

dependencies = ["google-genai", "pillow"]

///

from google import genai from google.genai import types

client = genai.Client() response = client.models.generate_content( model="gemini-2.5-flash-image", contents=["A cute banana character with sunglasses"], config=types.GenerateContentConfig( response_modalities=['IMAGE'] ) ) for part in response.parts: if part.inline_data is not None: image = part.as_image() image.save("tmp/generated.png") print("Saved: tmp/generated.png") EOF

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 with Python and Gemini without setting up a full project?▼

Python scripting with Gemini enables rapid image generation using uv run with inline dependencies. Write a script declaring google-genai and pillow in a heredoc, call the Gemini API with image generation parameters like aspect_ratio and response_modalities, and save outputs directly to tmp/ without project scaffolding.

Can I run Python scripts with inline dependencies using uv?▼

Yes, uv run accepts scripts via heredocs with embedded dependency declarations using PEP 723 script metadata. Dependencies like google-genai and pillow are fetched and installed at runtime, allowing stateless execution of one-off Python tasks without a virtual environment or package file.

What's the best way to automate Gemini image generation workflows?▼

Automate image generation by chaining Python scripts that call Gemini's generate_content API with configurable parameters—aspect_ratio, image_size, response_modalities—and save results to tmp/. Stateless execution enables iterative generate-refine-save cycles without state management overhead.

Does Gemini support configurable image generation options like aspect ratio?▼

Gemini image generation supports configuration through GenerateContentConfig, including response_modalities set to IMAGE and parameters like aspect_ratio and image_size. These options control output format and dimensions during the API call.

Can I use Python scripting for lightweight tasks without dependency management overhead?▼

Python scripting with uv eliminates dependency management by declaring packages inline within scripts. Runtime directives fetch and execute dependencies on demand, ideal for lightweight one-off tasks, iterative workflows, and rapid prototyping without persistent environments.

Where are generated images saved when using this workflow?▼

Generated images are saved to tmp/ with status reporting providing output paths. The workflow extracts inline_data from Gemini responses, converts to PIL Image objects, and persists them locally for retrieval or downstream processing.

Related Skills

Explore More Design & Creative Skills→
weorbitantweorbitant
1

gemini-imagegen

Generate and edit images from text prompts using the Gemini AI API.

Official
Advanced
ItsJupiter000ItsJupiter000

photo-editor

Process and enhance images with Python libraries like Pillow and OpenCV.

Community
Intermediate
iliagermaniliagerman
1

nano-banana-pro

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

Community
Intermediate
InverterNetworkInverterNetwork

comfyui

Execute generative AI workflows via the ComfyUI REST and WebSocket API.

Official
Advanced