skills.rest
tiankong0101-byte
tiankong0101-byteCOMMUNITY
Explore all skills by this author →
GitHub

nano-banana-pro

Generate and edit images with Google's Nano Banana Pro model, exporting PNGs.

Updated May 17, 2026
Search Tags:#image generation#image editing#gemini#text-to-image#image-to-image#png export
One-click install
npx skills add https://github.com/tiankong0101-byte/skills-registry --skill nano-banana-pro-tiankong0101-byte
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/tiankong0101-byte/skills-registry/tree/main/skills/nano-banana-pro
Command: npx skills add https://github.com/tiankong0101-byte/skills-registry --skill nano-banana-pro-tiankong0101-byte

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 precise edits to existing images, so you can turn a visual idea into a finished PNG quickly.

Core Features & Use Cases

  • Text-to-Image Generation: Create original images from a natural-language prompt.
  • Image-to-Image Editing: Modify an existing image with targeted instructions such as changing backgrounds, removing objects, or adjusting style.
  • Resolution Control: Produce outputs in 1K, 2K, or 4K depending on the quality needed.
  • Use Case: A designer can draft a concept at low resolution, refine the prompt through iterations, and then produce a final high-resolution asset for delivery.

Quick Start

Use the nano-banana-pro skill to generate a 4K PNG of a serene Japanese garden with cherry blossoms and save it in my current working directory.

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 high-resolution images from text prompts?▼

To perform image-to-image editing, provide an existing image and targeted instructions like changing backgrounds or adjusting style. The model modifies the original visual and exports the updated asset as a PNG file.

Can I edit an existing image to change backgrounds or remove objects?▼

Yes, you can edit an existing image by providing targeted text instructions to change backgrounds, remove objects, or adjust style. The model processes the input image and exports the modified visual as a PNG.

Do I need google-genai and pillow to run text-to-image generation?▼

Yes, you need google-genai and pillow installed in your environment to run this image generation and editing skill. These dependencies handle the underlying model interaction and PNG export processing.

What is the best way to refine marketing visuals and product mockups iteratively?▼

The best way to refine marketing visuals and product mockups iteratively is to draft concepts at a lower resolution, refine your text prompts through multiple image-to-image cycles, and then generate the final 4K asset for delivery.

Does this image generation approach support PNG export to a specific directory?▼

Yes, this image generation approach supports PNG export directly to your current working directory. You can generate or edit visuals at 1K, 2K, or 4K resolutions and access the output file immediately.

Related Skills

Explore More Design & Creative Skills→
iliagermaniliagerman
1

nano-banana-pro

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

Community
Intermediate
iterationlayeriterationlayer
2

upscale-low-resolution-image

Upscale low-resolution image URLs by 4x to PNG via the Iteration Layer Image Transformation API.

Official
Intermediate
SheshiyerSheshiyer
4

nano-banana

Generate Gemini-native images via the inference.sh CLI from text prompts.

Community
Intermediate
hsliuustc0106hsliuustc0106
84

vllm-omni-image-gen

Generate and edit images from text prompts using vLLM-Omni diffusion models.

Community
Advanced