A comprehensive prompt template ecosystem for high-fidelity image generation and editing powered by the Nano Banana Pro model.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install nano-hub
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install nano-hub using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Nano Hub?
Nano Hub is a professional-grade image generation center within the Openclaw Skills ecosystem, specifically designed to harness the power of the fal-ai/nano-banana-pro model. It serves as a centralized repository for high-quality prompt templates that allow developers and creators to generate everything from hand-drawn infographics to complex character design sheets with minimal input.
This skill bridges the gap between raw AI potential and polished visual output by utilizing a structured workflow. It supports both text-to-image generation and sophisticated image editing, automatically switching modes based on user input. By integrating Nano Hub into your Openclaw Skills library, you gain access to an automated art director capable of maintaining style consistency across diverse visual formats.
Nano Hub Use Cases
- Creating hand-drawn style infographics and data visualizations.
- Generating professional character design sheets and reference materials.
- Designing high-conversion e-commerce product detail pages and marketing assets.
- Producing stylized creative content such as Ukiyo-e cards, pixel art, and LEGO-themed visuals.
- Performing AI-powered image editing and modification on existing uploaded assets.
How Nano Hub Works
- The process begins with an interactive requirement analysis where the skill asks the user to select an image style via a structured questionnaire.
- Based on the selection, the skill identifies the corresponding best-practice prompt template from its internal library.
- If the user provides a local image, the skill handles the upload process to generate a public URL for processing.
- A specialized sub-agent is deployed to synthesize the final, high-quality prompt by combining user intent with the selected template.
- The skill submits the generation task to the fal-ai/nano-banana-pro model with specified parameters like aspect ratio and resolution.
- An automated polling system checks the task status every 20 seconds, retrieving and displaying the final image once processing is complete.
Nano Hub Setup
To utilize Nano Hub within your Openclaw Skills environment, ensure the MCP service for Nano Banana Pro is active. For image editing features, ensure your CLI environment supports curl for automated asset handling:
# Example of how the skill handles image uploads internally
curl -s -F "reqtype=fileupload" -F "fileToUpload=@your_image.png" https://catbox.moe/user/api.php
No additional manual configuration of templates is required as the skill automatically references the built-in stack paths.
Nano Hub Data Schema & Taxonomy
The skill organizes its operations around several key parameters and template structures:
| Parameter | Type | Required | Description |
|---|---|---|---|
| prompt | string | Yes | The synthesized generation or editing instruction |
| image_urls | array | No | Public URLs for source images in editing mode |
| aspect_ratio | string | No | Supports ratios like 16:9, 9:16, 1:1, 3:2, etc. |
| resolution | string | No | Choice of 1K, 2K, or 4K output |
| num_images | integer | No | Number of variants (1-4) |
Templates are stored as Markdown references, ensuring that the sub-agent has full context of style constraints before generation.
Nano Hub Advanced Features
- Intelligent sub-agent delegation to isolate prompt engineering from the main conversational context.
- Dynamic mode switching between text-to-image (t2i) and image-to-image (i2i) based on input payloads.
- Support for ultra-high-resolution 4K generation through the fal-ai backend.
- Pre-configured aesthetic stacks for specialized outputs like Polaroid photography, minimal comic lines, and 8-bit pixel art.
- Automated task polling and error handling for asynchronous generation workflows.
SKILL.md
Loading
Related Openclaw Skills
Hailuo Voice Synthesis and Design
A professional-grade audio synthesis skill powered by the Minimax API for high-fidelity text-to-speech, voice cloning, and natural language voice design.
Image Model Evaluation
An automated benchmarking suite for evaluating image generation models across dimensions like prompt adherence, style, and character consistency.
Hailuo Video Generation (MiniMax 2.3)
An advanced video generation skill leveraging MiniMax Hailuo 2.3 to create cinematic AI videos from text prompts or static images.
Flux 2 Flash Image Generation
A high-performance AI skill for generating and editing photorealistic images with advanced text rendering and native editing capabilities.
Shuihu Story Picture Book Infographic Generator
An automated workflow that converts Water Margin story text into high-quality, hand-drawn cartoon infographics using the Nano Banana Pro model.
Novel to Script Converter
An AI-powered skill that transforms prose novels into professional-grade scripts for video production, dubbing, and storyboarding.
Featured*
