skills.rest
HalseyYang
HalseyYangCOMMUNITY
Explore all skills by this author →
GitHub

nano-banana-pro

Generate and edit images with the Gemini 3 Pro Image API at up to 4K resolution.

1|Updated Jul 13, 2026
Search Tags:#png#image generation#image editing#gemini#text-to-image#ai art#4k
One-click install
npx skills add https://github.com/HalseyYang/Skills-HY --skill nano-banana-pro-halseyyang
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/HalseyYang/Skills-HY/tree/main/nano-banana-pro
Command: npx skills add https://github.com/HalseyYang/Skills-HY --skill nano-banana-pro-halseyyang

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Creating or modifying images normally requires design software or manual editing skills. This Skill lets you generate new images from text prompts or edit existing images using Google's Nano Banana Pro (Gemini 3 Pro Image) API directly from your working directory. ## Core Features & Use Cases - Text-to-Image Generation: Create images from natural language prompts at 1K, 2K, or 4K resolution. - Image Editing: Pass an existing image with editing instructions via --input-image to modify it; resolution auto-detects from the input size. - Draft-to-Final Workflow: Iterate quickly at 1K drafts, then render the locked prompt at 4K for final output. - Use Case: You need a product mockup for a presentation. Generate a 1K draft, refine the prompt over a few iterations, then produce the final 4K PNG saved to your current directory. ## Quick Start Ask the AI to generate an image of your described subject and save it as a PNG file, optionally specifying 4K resolution or an input image to edit.

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 an image with Gemini 3 Pro Image?▼

Run the generate_image.py script with a --prompt describing the image and a --filename for the output PNG. The script calls the Gemini API and saves the generated image to your current directory.

How do I edit an existing image with AI?▼

Pass the image path with --input-image along with editing instructions in --prompt. The script sends both the image and instructions to the Gemini API and saves the edited result as a new PNG.

What resolutions does Gemini image generation support?▼

The script supports 1K (~1024px), 2K (~2048px), and 4K (~4096px) via the --resolution flag. When editing, resolution auto-detects from the input image dimensions if not explicitly set.

Do I need an API key for Gemini image generation?▼

Yes, a Gemini API key is required. Provide it with the --api-key argument or set the GEMINI_API_KEY environment variable; the script exits with an error if neither is found.

Why did image generation fail with no image in the response?▼

The API may return only text if the prompt is rejected or malformed. The script reports this as an error; rephrase the prompt and retry, keeping edits as small incremental changes.

Related Skills

Explore More Design & Creative Skills→
nexu-ionexu-io
93.2k

create-image-campaign

Generate image campaign assets and creative prompts from a structured marketing brief.

Official
Intermediate
co-r-eco-r-e

nanobanana-image

Generate slide images via the Gemini API and insert them into MDX content.

Official
Advanced
alavida-aialavida-ai

Image Generation

Generate brand-aligned visual assets with structured prompts and Replicate MCP.

Official
Advanced
taracodlabstaracodlabs
799

stable-diffusion-image-generation

Generate images from text prompts using Stable Diffusion via HuggingFace Diffusers or Inference API.

Official
Intermediate