A sophisticated image generation assistant specializing in 17 curated 3D styles across characters, scenes, and commercial product designs.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install image-creator
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 image-creator 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 Image Creator?
The Image Creator is a powerful asset generation module designed for the Openclaw Skills ecosystem. It enables developers and creators to produce high-fidelity 3D art, ranging from collectible action figures and chibi characters to complex isometric city dioramas and architectural renders. By automating the prompt engineering process through 17 specialized templates, it ensures professional-grade output with minimal user input.
This skill is particularly optimized for commercial applications, offering dedicated workflows for brand store design, product advertisement creation, and sticker-bombed logos. It utilizes a minimalist interaction model to deliver assets rapidly, making it an essential component for any workflow requiring consistent, stylized visual content.
Image Creator Use Cases
- Creating marketing-ready 3D product renders and commercial advertisements with custom branding.
- Generating stylized 3D avatars, action figures, and chibi characters from reference photos.
- Visualizing architectural landmarks and isometric room designs for UI/UX or presentations.
- Transforming 2D assets like memes or logos into high-quality 3D models and low-poly art.
How Image Creator Works
- The skill analyzes user input and reference images using vision tools to extract character features, colors, and compositions.
- It routes the request to one of four core categories—Character, Scene, Product, or Style—based on detected triggers.
- A specialized prompt is constructed using proven templates that incorporate PBR (Physically Based Rendering) materials and studio lighting logic.
- If necessary, the skill performs a web search to fetch accurate brand colors or landmark details to ensure technical accuracy.
- The final image is generated and delivered through a structured asset wrapper for seamless integration into the agent's conversation.
Image Creator Setup
To integrate this capability into your AI agent, ensure the following tools are available in your environment:
# Required tools for the Image Creator workflow
# 1. gen_images: For the core generation process
# 2. images_understand: For analyzing reference uploads
# 3. web_search: For fetching real-world brand/landmark data
# 4. genui-form-wizard: For interactive style selection
Configure your agent to recognize triggers such as figure, diorama, product ad, or 3D generation to activate the Image Creator logic from the Openclaw Skills suite.
Image Creator Data Schema & Taxonomy
The Image Creator skill uses a structured XML-based delivery format to manage assets and metadata. This ensures that the AI agent can correctly parse and display the generated files.
| Tag | Description |
|---|---|
<deliver_assets> |
The root container for all generated output objects. |
<item> |
Represents a single generated image asset. |
<path> |
The local or remote path to the image file. |
reference_files |
Array used to pass user-provided images for style transfers. |
genui-form-wizard |
The UI schema used for presenting style options to the user. |
Image Creator Advanced Features
- Intelligent Style Routing: Automatically detects whether a user wants a character, a scene, or a product based on natural language triggers.
- Interactive Selection Wizard: Uses a form-based UI to help users choose between 17 different styles when requirements are vague.
- Brand-Aware Logic: Infers brand colors, headlines, and product selling points even when they aren't explicitly provided by the user.
- Multi-Asset Example Mode: Generates a range of variations when the user asks to see examples, showcasing the breadth of the Openclaw Skills visual capabilities.
- Physics-Based Prompting: Incorporates advanced material descriptors like matte PVC, transparent acrylic, and sub-surface scattering for hyper-realistic renders.
SKILL.md
Loading
Related Openclaw Skills
YouTube Transcript Fetcher
A robust transcript extraction utility that uses watch-page scraping and InnerTube API fallbacks to capture captions when other tools fail.
Text Tighten
A high-performance text optimization tool designed to sharpen writing, remove fluff, and improve structural clarity without losing original intent.
Seedance 2.0 Storyboard Director
A professional director skill for crafting movie-grade AI video prompts and cinematic storyboards from multimodal inputs.
OpenClaw Permissions Audit Skill
A security-focused utility to audit, review, and report on the permissions, API access, and communication channels utilized by an AI agent.
incident-response-team-setup
A comprehensive 7-phase framework for building, documenting, and validating an incident response team and its operational testing program.
Baby Words Tracker
A smart assistant skill for parents to track, categorize, and analyze their baby's vocabulary growth across multiple languages.
Featured*
