skills.rest
tamireslaeao-prog
tamireslaeao-progCOMMUNITY
Explore all skills by this author →
GitHub

nano-banana-pro

Generate or edit Gemini 3 Pro images from prompts and input images, saving PNG outputs.

Updated Jan 28, 2026
Search Tags:#composition#generate#gemini-3-pro#prompt#image-editing#multi-image#ai-visuals
One-click install
npx skills add https://github.com/tamireslaeao-prog/ONI_V30 --skill nano-banana-pro-tamireslaeao-prog
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/tamireslaeao-prog/ONI_V30/tree/main/moltbot-main/skills/nano-banana-pro
Command: npx skills add https://github.com/tamireslaeao-prog/ONI_V30 --skill nano-banana-pro-tamireslaeao-prog

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?

Generate or edit images via Gemini 3 Pro Image (Nano Banana Pro) to streamline image creation and editing workflows for designers, marketers, and AI enthusiasts.

Core Features & Use Cases

  • Generate images from prompts using Gemini 3 Pro Image API.
  • Edit a single image by applying new prompts and adjustments.
  • Create multi-image compositions up to 14 inputs for complex scenes and batch visuals.

Quick Start

Provide a prompt describing your image and run the Nano Banana Pro generate_image.py script to save the result as output.png.

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 with Gemini 3 Pro and save them as PNG?▼

To generate images with Gemini 3 Pro, provide a text prompt to the generate_image.py script, which processes the request and saves the output directly as a PNG file. You need a valid Gemini API key set via the GEMINI_API_KEY environment variable or the --api-key flag.

Can I combine multiple images into one composition using the Gemini API?▼

Yes, you can combine multiple images into a single composition using the Gemini API. This Skill supports multi-image compositions by accepting up to 14 input images alongside a prompt to generate complex scenes and batch visuals.

Does Gemini 3 Pro image editing support high resolution outputs like 4K?▼

Yes, Gemini 3 Pro image editing supports high resolution outputs. You can generate or edit images and specify 1K, 2K, or 4K output resolutions, which are then saved as ready-to-use PNG files for your design workflows.

What is needed to edit an existing image with a new prompt using Gemini?▼

To edit an existing image with a new prompt using Gemini, you need to provide the original image file and your adjustment prompt. The script processes these inputs to produce a modified image, which requires a valid Gemini API key to execute.

Are there limitations on the number of input images for multi-image compositions?▼

Yes, there are limitations on the number of input images for multi-image compositions. You can supply a maximum of 14 input images to create complex scenes or batch visuals, along with your text prompt and required API key.

Related Skills

Explore More Design & Creative Skills→
drshailesh88drshailesh88

nano-banana-pro

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

Community
Intermediate
Gundlapuriswathiii006Gundlapuriswathiii006

remove-image-background

Remove image backgrounds and output transparent PNG files.

Community
Intermediate
adamhjoujadamhjouj
4

nano-banana-pro

Generate or edit images via Google's Gemini 3 Pro Image API and save PNG outputs.

Community
Intermediate
pmcdowallpmcdowall

stable-diffusion-image-generation

Generates AI images from text prompts using HuggingFace Diffusers pipelines.

Community
Advanced