skills.rest
zkywalker
zkywalkerCOMMUNITY
Explore all skills by this author →
GitHub

nanobanana

Converts Chinese image descriptions into optimized English prompts for Gemini API and generates images.

118|Updated Mar 6, 2026
Search Tags:#image generation#prompt optimization#gemini api#text-to-image#ai art#chinese to english
One-click install
npx skills add https://github.com/zkywalker/nanobanana --skill nanobanana-zkywalker
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nanobanana
Source: https://github.com/zkywalker/nanobanana/tree/main
Command: npx skills add https://github.com/zkywalker/nanobanana --skill nanobanana-zkywalker

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill bridges the gap between Chinese image descriptions and the Gemini API, automatically optimizing prompts for high-quality image generation.

Core Features & Use Cases

  • Smart Prompt Optimization: Translates and enhances Chinese descriptions into effective English prompts for Gemini.
  • Intent-Aware Enhancement: Detects image intent (photo, illustration, etc.) and applies domain-specific improvements.
  • In-Image Text Preservation: Ensures text meant to appear in the image is rendered correctly.
  • Use Case: Describe an image in Chinese, and Nanobanana will generate a detailed, optimized English prompt and create the image using the Gemini API, handling everything from basic descriptions to complex scene requests.

Quick Start

Use the nanobanana skill to generate an image from the Chinese description '一只橘猫趴在键盘上打盹'.

Frequently Asked Questions about nanobanana

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

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

This Skill translates and optimizes Chinese descriptions into high-quality English prompts for the Gemini API, recognizing intent and generating the image automatically.

What is the best way to optimize Chinese descriptions for text-to-image generation?▼

The best way to optimize Chinese descriptions for text-to-image generation is applying intent-aware enhancements that detect image types like photos or illustrations and apply domain-specific improvements.

Can I just optimize the prompt without generating the image?▼

Yes, you can just optimize the prompt without generating the image. The Skill supports prompt-only optimization to translate and enhance your Chinese text into an English prompt for the Gemini API.

Does the Gemini API preserve in-image text when generating AI art from Chinese prompts?▼

Yes, the Gemini API preserves in-image text when generating AI art from Chinese prompts. The Skill ensures any text meant to appear in the image is rendered correctly during generation.

Do I need the Pillow library to generate images from Chinese descriptions?▼

You need the Pillow library and the google-genai dependency installed to process and generate images from Chinese descriptions using this Skill.

Related Skills

Explore More Design & Creative Skills→
lucking7lucking7

ce-gemini-imagegen

Generate and edit images using the Gemini API with Python scripts.

Community
Advanced
kienhaminhkienhaminh

gemini-image-gen

Generate and edit images from text prompts using Gemini 2.5 Flash Image.

Community
Advanced
Lucent-SnowLucent-Snow
5

ai-image-generator

Generate detailed digital images from descriptive prompts via AI APIs.

Community
Intermediate
Umbral-BotUmbral-Bot

nano-banana-image-briefs

Convert approved content drafts into visual briefs and editable image-generation prompts.

Official
Advanced