nano-banana-pro

Generate and edit images via the Nano Banana Pro API with PNG export.

1|Updated Apr 3, 2026

Search Tags:#image generation #image editing #gemini #text to image #png export #image to image #resolution control

Ready to run

npx skills add https://github.com/bobvarkey/openclaw-workspace --skill nano-banana-pro-bobvarkey

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/bobvarkey/openclaw-workspace/tree/main/skills/nano-banana-pro
Command: npx skills add https://github.com/bobvarkey/openclaw-workspace --skill nano-banana-pro-bobvarkey

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the friction of generating new images or making targeted edits to existing images through a single image-generation workflow.

Core Features & Use Cases

Text-to-Image Generation: Create fresh images from natural-language prompts for concepts, scenes, objects, and stylized art.
Image-to-Image Editing: Modify an existing image with instructions such as changing style, adjusting the sky, removing elements, or preserving text.
Resolution Control: Choose 1K, 2K, or 4K output depending on the stage of the work, from quick drafts to final deliverables.
Use Case: A user can draft an image at low resolution, iterate on the prompt until the result is right, then render the final version at 4K.

Quick Start

Ask for a new image or an edit, specify the filename, and provide an input image path when you want to modify an existing file.

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 from text prompts using Gemini?▼

To generate images from text prompts using Gemini, you provide a natural-language description and specify an output filename. The tool creates fresh visual assets from your concepts and exports the final response as a PNG file.

Can I edit an existing image by providing a text prompt?▼

Yes, you can edit an existing image by providing its file path and text instructions. This image-to-image modification lets you change styles, adjust elements like the sky, or remove objects while optionally preserving text.

Do I need a Gemini API key to use this image generation workflow?▼

Yes, this image generation workflow requires Gemini API access to function. You also need local file handling capabilities to manage your input reference images and save the output PNG files.

What is the best way to control output resolution for image generation?▼

The best way to control output resolution is selecting 1K, 2K, or 4K settings. You can draft at lower resolutions to iterate quickly on prompts, then render the finalized visual asset at 4K.

What file formats are supported for input and output images?▼

The supported file formats involve local image files for input and PNG exports for output. The tool processes your provided input image paths and exports the generated or modified images directly as PNG files.