skills.rest
inference-sh
inference-shOFFICIAL
Explore all skills by this author →
WebsiteGitHub

nano-banana

Generate and edit images with Google Gemini models via inference.sh CLI.

688|95|Updated Jan 31, 2026
Search Tags:#image generation#image editing#gemini#google ai#text-to-image#ai art
One-click install
npx skills add https://github.com/inference-sh/skills --skill nano-banana-inference-sh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana
Source: https://github.com/inference-sh/skills/tree/main/tools/image/nano-banana
Command: npx skills add https://github.com/inference-sh/skills --skill nano-banana-inference-sh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows users to generate high-quality images using Google's Gemini native image models, offering advanced capabilities for creative and practical image generation needs.

Core Features & Use Cases

  • Text-to-Image Generation: Create images from detailed text descriptions.
  • Image Editing: Modify existing images based on new prompts.
  • Multi-Image Input/Output: Generate multiple image variations or edit multiple input images.
  • Use Case: Generate a photorealistic image of a "banana in space" or edit a landscape photo to "add a rainbow in the sky."

Quick Start

Use the nano-banana skill to generate an image from the prompt 'a banana in space, photorealistic'.

Frequently Asked Questions about nano-banana

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

FAQPage Schema
How do I generate AI images from text using Google Gemini?▼

To generate AI images from text using Google Gemini, you provide a detailed text prompt to the nano-banana Skill via the inference.sh CLI. It uses native Gemini models like `gemini-3-pro-image-preview` to create high-quality visual outputs from your descriptions.

Can I edit existing images with text prompts using Gemini models?▼

Yes, you can edit existing images with text prompts using Gemini models through the nano-banana Skill. It supports image editing by taking your original image and a new text description to apply modifications, such as adding elements to a landscape photo.

What Google Gemini models are available for text-to-image generation?▼

The available Google Gemini models for text-to-image generation are `google/gemini-3-pro-image-preview` and `google/gemini-2-5-flash-image`. These native Gemini applications power the image creation and editing capabilities within the inference.sh CLI environment.

Does the Gemini image generation Skill support multiple input images?▼

Yes, the Gemini image generation Skill supports multi-image inputs. You can provide multiple images simultaneously to generate variations or apply edits across several files, alongside supporting various aspect ratios and resolutions for diverse creation needs.

What are the limitations of using Gemini for AI art generation?▼

Using Gemini for AI art generation requires the inference.sh CLI environment and depends on specific preview or flash model availability. While it handles text-to-image and image editing, complex multi-image edits may be constrained by the selected model's processing limits and resolution supports.

Related Skills

Explore More Design & Creative Skills→
zzafergokzzafergok
1

gemini-skill

Access Google Gemini models via CLI or API for reasoning and multimodal tasks.

Community
Advanced
Bria-AIBria-AI
63

image-utils

Automate Pillow-based image resizing, cropping, compositing, and format conversion.

Official
Advanced
samuelmukotisamuelmukoti

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion models.

Community
Advanced
ihatesea69ihatesea69
3

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion models.

Community
Advanced