nano-banana
nano-banana is a CLI tool for generating AI images from text prompts, defaulting to Gemini 3.1 Flash with optional Pro model support. It handles multi-resolution output (512 to 4K), custom aspect ratios, reference images for style transfer, and automated green-screen transparency for assets. Perfect for UI mockups, game sprites, marketing materials, and video production.
nano-banana generates AI images from text prompts using Gemini models, supporting multi-resolution output and style transfer.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-04-02
nano-banana generates AI images from text prompts using Gemini models, supporting multi-resolution output and style transfer. nano-banana is a CLI tool for generating AI images from text prompts, defaulting to Gemini 3.1 Flash with optional Pro model support. It handles multi-resolution output (512 to 4K), custom aspect ratios, reference images for style transfer, and automated green-screen transparency for assets. Perfect for UI mockups, game sprites, marketing materials, and video production.
Use it when
- Yes.
- nano-banana lets you control image dimensions, resolution, and aspect ratios for specific use cases.
Verify before relying
Read SKILL.md below before installing (1 file). Open directory: indexed for reading, not audited.
Install
kingbootoshi/nano-banana-2-skill/nano-banana · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I generate an AI image from text with nano-banana?
nano-banana generates AI images from text prompts via CLI, defaulting to Gemini 3.1 Flash with optional Pro model support. Simply provide your text description and nano-banana handles image creation for UI mockups, game assets, marketing materials, and more.
Can nano-banana create sprite with transparent background?
Yes. nano-banana includes automated green-screen background removal to create transparent assets and sprites. This feature is ideal for game development and UI design where you need clean PNG files with transparency for layering and compositing.
What image dimensions and aspect ratios does nano-banana support?
nano-banana lets you control image dimensions, resolution, and aspect ratios for specific use cases. It supports multi-resolution output ranging from 512 pixels up to 4K, allowing you to generate images tailored to your exact project requirements.
Does nano-banana support style transfer between images?
Yes. nano-banana applies style transfer and image editing using reference images as guides. You can provide reference images to influence the visual style and appearance of your generated content.
How can I track AI image generation costs with nano-banana?
nano-banana includes cost tracking and monitoring across multiple generations. This helps you keep tabs on your AI image generation expenses and manage your budget effectively across different projects and sessions.
What license does nano-banana use?
nano-banana is released under the MIT license, making it freely available for commercial and personal use with minimal restrictions.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
nano-banana
AI image generation CLI. Default model: Gemini 3.1 Flash Image Preview (Nano Banana 2).
/init - First-Time Setup
When the user says "init", "setup nano-banana", or "install nano-banana", run these commands to get the CLI tool on their machine. No sudo required.
Prerequisites: Bun must be installed. If not: curl -fsSL https://bun.sh/install | bash
```bash
1. Clone the repo
git clone https://github.com/kingbootoshi/nano-banana-2-skill.git ~/tools/nano-banana-2
2. Install dependencies
cd ~/tools/nano-banana-2 && bun install
3. Link globally (creates nano-banana command via Bun - no sudo)
cd ~/tools/nano-banana-2 && bun link
4. Set up API key
mkdir -p
(truncated - see the full file via the links below)
File tree — 1 file
plugins/nano-banana/skills/nano-banana/SKILL.md
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Generate AI images from text prompts for UI mockups, game assets, and marketing materials”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Nano Banana creates images using Google's Gemini image generation models through a straightforward command-line interface. Specify resolution up to 4K, choose from multiple aspect ratios, and optionally enhance prompts for better results—images save locally with automatic notifications.
Tuzi Image Gen creates images from text prompts across multiple AI providers, with Tuzi as the default. Customize output with aspect ratios, quality presets, reference images, and model selection—supporting synchronous and async generation workflows.
Nano Banana One Shop provides unified image generation and editing across three Gemini model tiers. Select the right balance of speed and quality for your needs: the default Flash model for general use, Pro for highest-quality 4K output, or the 2.5 Flash variant for high-volume tasks. Supports text-to-image generation, single-image editing, and multi-image composition.
NanoBanana Image lets you create and modify images through AceDataCloud's Gemini-powered API, supporting multiple model variants from standard to pro-tier quality. Edit existing images with natural language instructions without masks, or generate new ones from text prompts with configurable aspect ratios and resolutions.
Create images from text descriptions or edit existing images with AI-powered generation. Supports resolutions from 512px to 4K, with a recommended workflow that starts at 1K for quick iteration before finalizing at higher resolutions. Requires a Gemini API key and the uv package manager.
Create and edit images using RunComfy's CLI with access to over a dozen AI models including FLUX 2, Google Nano Banana, OpenAI GPT Image 2, ByteDance Seedream, and others. The skill intelligently routes your request to the right model based on your intent—whether you need photoreal portraits, fast iteration, precise typography, or open-weights workflows—and provides the exact command to run.