An advanced AI image generation and editing skill for OpenClaw that leverages the Gemini Image API with automated model failover for maximum reliability.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install nanobanana-pro-fallback
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 nanobanana-pro-fallback 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 Banana Pro Fallback?
Nano Banana Pro Fallback is a specialized utility designed to bring robust image generation and editing capabilities to the Openclaw Skills ecosystem. By utilizing the Gemini Image API, it allows users to create high-quality visuals from text prompts or perform complex image-to-image transformations.
The skill is engineered for reliability in production environments. If a generation request fails on the primary model, it automatically attempts the request using a secondary model in a fallback chain. This ensures that your automated workflows remain uninterrupted. It is a perfect example of how Openclaw Skills can extend the utility of AI agents by providing direct access to state-of-the-art multimodal capabilities.
Nano Banana Pro Fallback Use Cases
- High-resolution text-to-image generation for creative projects.
- Image editing and modification using natural language instructions.
- Multi-image composition where up to 14 source images are combined into a single scene.
- Automated image generation within broader agentic workflows requiring high availability.
How Nano Banana Pro Fallback Works
- The user provides a text prompt and optional source images via the command line interface.
- The skill initializes using the uv package manager to ensure all dependencies are correctly isolated and available.
- It authenticates with the Gemini Image API using the provided GEMINI_API_KEY.
- The script attempts to generate the image using the primary model (e.g., gemini-2.5-flash-image).
- If the primary model is unavailable or encounters an error, the script automatically cycles to the next model in the fallback chain (e.g., gemini-2.0-flash-exp).
- The final image is saved to the local file system at the specified resolution (1K, 2K, or 4K).
- A MEDIA: reference is printed, allowing OpenClaw to automatically recognize and attach the output to the chat interface.
Nano Banana Pro Fallback Setup
This skill requires the uv tool for execution. Ensure it is installed on your system:
brew install uv
Configure your API key as an environment variable or within your OpenClaw configuration file:
export GEMINI_API_KEY='your-api-key-here'
To run the skill, use the wrapper script or the direct uv run command as follows:
uv run {baseDir}/scripts/generate_image.py --prompt 'a sunset over a digital city' --filename 'cityscape.png' --resolution 2K
Nano Banana Pro Fallback Data Schema & Taxonomy
The skill manages inputs and outputs through a structured CLI interface and local file storage. This organization makes it highly compatible with other Openclaw Skills.
| Attribute | Specification |
|---|---|
| Supported Models | gemini-2.5-flash-image, gemini-2.0-flash-exp-image-generation |
| Output Formats | Standard image files (PNG/JPG) |
| Resolution Options | 1K (default), 2K, 4K |
| Input Limit | Up to 14 images for multi-image composition |
| Meta Signaling | Outputs MEDIA: [path] for automated agent integration |
Nano Banana Pro Fallback Advanced Features
- Automatic fallback logic ensures 99.9% uptime by switching between different model versions dynamically.
- Full support for image-to-image workflows, allowing for fine-grained editing of existing assets.
- Multi-image processing capabilities for complex scene creation and composition tasks.
- Custom model chaining via the NANOBANANA_FALLBACK_MODELS environment variable for power users who want to define their own failover priority.
- Native integration with OpenClaw for automatic attachment of generated media to agent responses.
SKILL.md
Loading
Related Openclaw Skills
clawpet
An interactive virtual pet companion for AI agents that manages adoption, real-time status tracking, and AI image generation.
catime
A CLI-based utility that enables AI agents to retrieve and share hourly cat artwork generated by Google Gemini.
Claude Code Orchestrator (tmux-first)
A robust orchestration framework for running Claude Code in observable tmux sessions with automated progress tracking and completion callbacks.
Claude Code Orchestrator
A tmux-based orchestration tool for managing long-running Claude Code development tasks with high visibility and automated callbacks.
Request Approval
A critical safety tool that pauses AI agent execution to request human authorization before performing high-risk or destructive operations.
WBS Planner
A hierarchical project management framework that decomposes complex goals into executable tasks for AI agents and human teams.
METADATA
Featured*
