A high-performance AI image generation skill supporting DALL-E, Stable Diffusion, and Midjourney for creative visual workflows.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install jpeng-image-generator
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 jpeng-image-generator 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 jpeng-image-generator?
The jpeng-image-generator is a versatile tool designed to bridge the gap between text prompts and high-fidelity visual assets. As a key component of the Openclaw Skills ecosystem, it allows developers and creators to programmatically generate, edit, and iterate on images using industry-leading models like DALL-E 3 and SDXL.
Whether you are building automated thumbnail generators or integrating AI art into your development pipeline, this skill provides a unified interface for multiple providers including OpenAI, Stability AI, and Replicate. It simplifies complex tasks like inpainting and creating variations into straightforward CLI commands.
jpeng-image-generator Use Cases
- Creating high-quality thumbnails or illustrations for technical blog posts and documentation.
- Generating multiple variations of an existing design to explore different creative directions.
- Performing AI-driven inpainting to edit specific elements within an image using masks.
- Automating the creation of visual assets for marketing and digital storefronts.
How jpeng-image-generator Works
- The user provides a text-based prompt or an existing image file along with specific parameters like dimensions or style presets.
- The skill authenticates with the configured provider (OpenAI, Stability AI, or Replicate) using the environment variables provided.
- The request is processed by the AI model, which interprets the prompt and generates the visual data.
- The skill saves the resulting image to the local file system and returns a structured JSON response containing the file path and any revised prompts.
jpeng-image-generator Setup
To get started with this entry in the Openclaw Skills directory, export the API keys for your preferred providers:
# OpenAI DALL-E
export OPENAI_API_KEY="sk-xxx"
# Stability AI
export STABILITY_API_KEY="sk-xxx"
# Replicate (for SDXL, etc.)
export REPLICATE_API_TOKEN="r8_xxx"
Ensure you have the required Python environment set up to execute the generation scripts provided in the package.
jpeng-image-generator Data Schema & Taxonomy
The skill produces structured outputs and follows a predictable file organization for generated assets:
| Attribute | Description |
|---|---|
| success | Boolean indicating if the generation was successful. |
| image_path | The local relative path to the generated or edited PNG/JPG file. |
| revised_prompt | The actual prompt used by the model (useful for DALL-E's internal optimizations). |
| output-dir | Optional directory used for bulk variation tasks. |
jpeng-image-generator Advanced Features
- Negative Prompting: Exclude specific elements like "blurry" or "low quality" to ensure professional results.
- Style Presets: Quickly apply specific aesthetics such as "cyberpunk" or "photorealistic" without complex prompt engineering.
- Masked Inpainting: Precise image editing by providing a mask file to define exactly where the AI should add or change content.
- Multi-Provider Support: Seamlessly switch between DALL-E, SDXL, and other models within the same Openclaw Skills workflow.
SKILL.md
Loading
Related Openclaw Skills
Openclaw Workspace Governance
A system-level architecture upgrade designed to manage complexity, reduce data drift, and establish authoritative truth in multi-agent Openclaw environments.
KimiClaw
KimiClaw enables developers to power their OpenClaw environment and Claude Code CLI using the free, Anthropic-compatible Kimi K2.5 coding model.
Context Stabilizer
A powerful tool for maintaining character, world-building, and plot consistency in long-form AI-generated content.
LiteBrowse Skill
LiteBrowse is a specialized low-token webpage research skill designed to extract only the most relevant content from long or cluttered pages.
Onfleet
A powerful integration for Onfleet that enables AI agents to manage organizations, track deliveries, and optimize last-mile logistics operations.
WeChat Publisher Setup Agent Team
Deploy a specialized AI agent team to automate visual design, layout beautification, and API-based publishing for WeChat Official Accounts.
Featured*
