A sophisticated AI tool for text-to-image generation and complex multi-image remixing powered by Google Gemini models.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install gemini-image-remix
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 gemini-image-remix 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 Gemini Image Remix?
Gemini Image Remix is a high-performance tool built to integrate Google's cutting-edge vision models into your creative pipeline. As a key component of the Openclaw Skills library, it allows users to transition seamlessly between rapid prototyping with Gemini 2.5 Flash and high-fidelity artistic production using Gemini 3.0 Pro.
This tool goes beyond simple text-to-image requests by enabling deep image-to-image modifications. Users can provide multiple reference images to guide style, composition, and character consistency, making it an essential utility for developers building visual AI agents or designers looking for automated remixing capabilities.
Gemini Image Remix Use Cases
- Creating custom marketing visuals and assets from natural language descriptions.
- Performing style transfers, such as converting a photograph into a pencil sketch or oil painting.
- Compositing complex scenes by merging elements from up to 14 different source images.
- Modifying existing images by providing specific instructions like changing backgrounds or character outfits.
- Generating high-resolution (up to 4K) AI art with specific aspect ratios for various digital platforms.
How Gemini Image Remix Works
- The user provides a text prompt and optional reference images through the command-line interface.
- The system validates the environment, ensuring the GEMINI_API_KEY is active and the uv environment is ready.
- The skill processes the input parameters, including model selection, resolution, and aspect ratio.
- Input images are uploaded and processed by the selected Gemini model to act as visual context.
- The Gemini model generates a new image or modifies the existing ones based on the provided instructions.
- The final output is saved to the local file system as a high-quality PNG file.
Gemini Image Remix Setup
To get started with this Openclaw Skills utility, ensure you have the necessary dependencies installed:
# Install the uv package manager
brew install uv
# Set your Gemini API key environment variable
export GEMINI_API_KEY='your_api_key_here'
You can then run your first generation command:
uv run scripts/remix.py --prompt "a futuristic city" --filename "city.png"
Gemini Image Remix Data Schema & Taxonomy
The skill utilizes a structured CLI interface to manage image metadata and generation parameters:
| Parameter | Argument | Description |
|---|---|---|
--prompt |
-p |
The text description or specific modification instructions. |
--filename |
-f |
The destination path for the output PNG file. |
--input-image |
-i |
File path(s) for reference images (supports up to 14). |
--resolution |
-r |
Desired output quality: 1K, 2K, or 4K. |
--aspect-ratio |
-a |
Format of the output (e.g., 1:1, 16:9, 9:16). |
--model |
-m |
Choice of model: gemini-2.5-flash-image or gemini-3-pro-image-preview. |
Gemini Image Remix Advanced Features
- Multi-Image Reference: Leverage up to 14 input images to provide complex context for a single generation.
- Model Flexibility: Support for both the fast Gemini 2.5 Flash and the advanced Gemini 3.0 Pro (Nano Banana Pro).
- High Resolution Support: Capability to generate assets in 1K, 2K, or 4K resolutions.
- Precise Framing: Granular control over aspect ratios to fit specific UI or social media requirements.
- Seamless Integration: Designed to work within broader Openclaw Skills workflows for automated content creation.
SKILL.md
Loading
Related Openclaw Skills
Predicate Snapshot Engine
An ML-powered DOM pruning engine that reduces browser prompt tokens by 95% for more efficient AI agents.
Tellermcp MCP Skill
A Model Context Protocol server that enables AI agents to interact with Teller Protocol for arbitrage discovery and on-chain transaction building.
Tellermcp MCP Skill
An MCP server that enables AI agents to discover arbitrage opportunities, fetch borrow terms, and build on-chain transactions for the Teller protocol.
Tellermcp MCP Skill
A Model Context Protocol server that empowers AI agents to manage Teller protocol lending, borrowing, and delta-neutral arbitrage opportunities.
RDA Message Board Controller
A Python-powered skill to send scrolling text messages and musical alerts to RDA MSG Board LED matrix displays.
SearXNG Connect
A privacy-centric skill for connecting AI agents to self-hosted SearXNG instances for untracked, ad-free web searching.
Featured*
