A sophisticated CLI skill for generating and editing raster images using Google Gemini AI models.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install yummy-gen-image
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 yummy-gen-image 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 yummy-gen-image?
The yummy-gen-image skill provides a streamlined interface for AI agents to interact with Gemini image generation and editing capabilities. As part of the broader Openclaw Skills collection, it allows for seamless text-to-image creation, style transfers, and complex multi-image compositing through simple command-line arguments. By wrapping the yummycli utility, it ensures that developers can programmatically control image output parameters like resolution and aspect ratio with minimal friction.
This skill is designed for high-performance creative automation, enabling agents to transform user prompts into high-quality visual assets. Whether you are building social media content, designing presentation materials, or performing advanced image edits using reference photos, this skill provides the necessary technical bridge to Gemini's powerful multimodal models.
yummy-gen-image Use Cases
- Creating realistic photos or illustrations from text-only descriptions
- Editing existing images to apply new artistic styles or watercolor effects
- Blending multiple reference images into a single cohesive poster or illustration
- Generating high-resolution 4K images for print-grade deliverables
- Automating the creation of mobile wallpapers and widescreen banners using specific aspect ratio controls
How yummy-gen-image Works
- The user provides a text prompt and optionally one or more local image files as references.
- The skill identifies the appropriate Gemini model (Flash or Pro) based on user requirements or default settings.
- The system maps specific intent (like 'vertical' or '4K') to precise CLI flags for aspect ratio and image size.
- The yummycli command is executed, sending the request to the Gemini API.
- The generated image is saved directly to the local file system with either a user-defined or an automatically generated filename.
yummy-gen-image Setup
To use this skill, ensure you have the prerequisite yummy-shared skill configured. You must also have your Gemini API key available in your environment.
Install the required CLI tool via npm:
npm install -g @yummysource/yummycli
Ensure your GEMINI_API_KEY is exported to your environment before calling the skill within the Openclaw Skills framework.
yummy-gen-image Data Schema & Taxonomy
The skill utilizes standardized flags to manage image metadata and output specifications. Below is the mapping of supported parameters:
| Parameter | Type | Description |
|---|---|---|
--prompt |
String | The text description of the desired image. |
--input-image |
Path | Local path to a reference image (can be used multiple times). |
--aspect-ratio |
String | The desired shape (e.g., 1:1, 16:9, 9:16). |
--image-size |
String | Resolution toggle (e.g., 512, 1K, 2K, 4K). |
--model |
String | Specific Gemini model identifier. |
--output |
Path | Custom destination path for the resulting file. |
yummy-gen-image Advanced Features
- Support for multi-image reference editing to composite different subjects and backgrounds
- Intelligent model mapping for Gemini-3.1-flash and Gemini-3-pro to optimize for speed or quality
- Specialized aspect ratio support including ultra-wide 21:9 and vertical mobile formats
- Granular resolution control ranging from lightweight 512px previews to professional 4K outputs
- Direct integration with Openclaw Skills workflows for automated asset generation pipelines
SKILL.md
Loading
Related Openclaw Skills
Online OCR Skill
A cloud-based image-to-text recognition skill that utilizes the OCR.space API to process multiple languages without requiring local Tesseract installations.
Core Capabilities Assistant
A comprehensive suite for managing AI agent memory, Obsidian note workflows, and automated Git synchronization.
x402 Crypto Market Structure
Real-time crypto market intelligence and orderflow analysis for professional trading and automated agent workflows.
4steps to Wisdom Communication Workflow
A structured five-step cognitive framework designed to synchronize thinking and execution between humans and AI agents.
Robotaxi Tracker
A specialized skill for extracting and comparing live autonomous vehicle fleet data across US cities from Robotaxi Tracker.
MiniMax TTS Text-to-Speech
A professional-grade text-to-speech skill for generating high-fidelity audio from text using MiniMax's advanced AI models.
Featured*
