skills.rest
travis-burmaster
travis-burmasterCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

nano-banana-pro

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

Updated Feb 16, 2026
Search Tags:#png#image generation#image editing#gemini#text-to-image#google genai#multi-image composition
One-click install
npx skills add https://github.com/travis-burmaster/agentbox --skill nano-banana-pro-travis-burmaster
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/travis-burmaster/agentbox/tree/main/agentfork/skills/nano-banana-pro
Command: npx skills add https://github.com/travis-burmaster/agentbox --skill nano-banana-pro-travis-burmaster

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Creating or editing images programmatically requires wiring up API clients, handling image encoding, and managing output files. This Skill wraps Google's Gemini 3 Pro Image (Nano Banana Pro) API into a single script that generates new images from text prompts or edits and composes existing images. ## Core Features & Use Cases - Text-to-Image Generation: Create images from natural language prompts at 1K, 2K, or 4K resolution. - Image Editing & Composition: Edit a single image or combine up to 14 input images into one scene, with automatic resolution detection based on input dimensions. - Use Case: Ask your agent to generate a product mockup at 2K resolution, then refine it by passing the output back as an input image with new edit instructions. ## Quick Start Ask the agent to generate an image of your chosen subject and save it as a PNG file at your preferred resolution.

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 the Gemini API from a text prompt?▼

Run the generate_image.py script with uv, passing --prompt with your description and --filename for the output PNG. The script calls the gemini-3-pro-image-preview model and saves the result, printing a MEDIA line for chat attachment.

How do I combine multiple images into one with Gemini image editing?▼

Pass multiple input images using repeated -i flags along with a composition prompt. The script supports up to 14 input images and auto-detects output resolution from the largest input dimension.

What resolutions does Gemini 3 Pro Image support?▼

The script supports 1K, 2K, and 4K output resolutions via the --resolution flag, defaulting to 1K. When editing images, resolution is auto-detected from the largest input dimension unless explicitly set.

Why does image generation fail with a missing API key error?▼

The script requires a Gemini API key passed via --api-key or the GEMINI_API_KEY environment variable. You can also configure it in the openclaw.json config under the skill's apiKey or env settings.

What is the maximum number of input images for Gemini image composition?▼

Nano Banana Pro supports a maximum of 14 input images per request. The script validates this limit and exits with an error if more than 14 images are provided.

Related Skills

Explore More Design & Creative Skills→
renatoasserenatoasse
2.0k

image-fetcher

Acquires visual assets from web search, Playwright screenshots, and user files into a reference folder with metadata.

Community
Intermediate
m0shabanm0shaban

postiz

Schedule and publish social media content across 28+ platforms via CLI.

Community
Advanced
PicsArtPicsArt
4

prosumer-headshot-studio

Generates identity-locked professional headshot variants from a single selfie using image-to-image AI models.

Official
Intermediate
AetherWave-StudioAetherWave-Studio

aetherwave-image-generation

Generate images via Midjourney, DALL-E 4, Imagen 4, Flux, and Stable Diffusion.

Community
Intermediate