A high-resolution AI text-to-image generation skill designed for Openclaw Skills, leveraging Volcano Engine APIs to render high-quality artwork directly in your agent's interface.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install spark-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 spark-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 Spark Image?
The Spark Image skill brings text-to-image capabilities directly to your AI assistants. Designed as a flexible plugin in the ecosystem of Openclaw Skills, it connects agents to robust Volcano Engine imaging backends. It translates user descriptions into beautiful illustrations, concept art, and detailed drawings.
With this tool, developers using Openclaw Skills can configure customized image resolutions, specify creative art styles, and manage multi-image batch runs. The output is directly rendered in base64 format, enabling clean, secure, and user-friendly visual generation workflows.
Spark Image Use Cases
- Generating custom marketing visuals, blog cover designs, and illustrations on demand.
- Empowering conversational AI bots to paint watercolors, oil paintings, Chinese ink styles, and sci-fi scenes.
- Expanding the creative capabilities of local agent assistants utilizing the catalog of Openclaw Skills.
- Processing complex design workflows by requesting up to 4 high-resolution images in parallel.
How Spark Image Works
- The AI agent detects an image generation request from triggering keywords like "generate a drawing" or "paint a picture".
- The agent structures the API payload containing the prompt, dimensions, style modifier, and target count.
- A POST request is securely routed to the Volcano Engine API gateway with Bearer Token authentication.
- The server yields base64-encoded PNG image strings along with usage points data.
- The agent parses the payload and renders the final artwork directly to the interface via image tags or download links, logging exact API billing details to the user.
Spark Image Setup
Install the skill through the command line:
openclaw skills install spark-image
Configure your environment variables with your API key from image.open-idea.net:
export IMAGE_GATEWAY_API_KEY="your_api_key_here"
Spark Image Data Schema & Taxonomy
API Payload Schema
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt |
string | Yes | The textual description of the image to generate |
width |
integer | Yes | Target width (must match supported size combinations) |
height |
integer | Yes | Target height (must match supported size combinations) |
style |
string | No | Style prompts (e.g., "oil painting style, heavy strokes") |
image_count |
integer | No | Number of images to generate (range: 1-4) |
Size & Point Pricing Structure
| Resolution | Points Cost |
|---|---|
| 2048 x 2048 | 56 |
| 2304 x 1728 / 1728 x 2304 | 54 |
| 2848 x 1600 / 1600 x 2848 | 61 |
| 2496 x 1664 / 1664 x 2496 | 56 |
| 3136 x 1344 | 57 |
Spark Image Advanced Features
- Multi-Image Batching: Support for generating 1 to 4 images simultaneously in a single call.
- Intelligent Style-Prompt Matching: Seamless interpretation of various art movements, textures, and composition instructions.
- Built-in Billing Feedback: Direct tracking of API point usage and balance remaining through specific HTTP headers, perfect for Openclaw Skills developers monitoring resource consumption.
- Leak-Proof Privacy Boundaries: Strictly prevents agent leakage of structural keys, schema specs, models, or tokens to the end-user.
SKILL.md
Loading
Related Openclaw Skills
Seal OCR (Sugon-Scnet)
A specialized OCR tool for recognizing, localizing, and extracting text and metadata from official seals on documents and invoices.
ADP Global Invoice Extraction Free
A zero-registration, high-precision AI document processing tool designed to extract structured JSON data from global invoices and receipts in over 100 languages.
Sugon-Scnet Document Intelligent OCR
An asynchronous document parsing skill powered by Sugon-Scnet for structured layout analysis, markdown conversion, and high-precision OCR of public files.
Bank Draft OCR
An AI-powered OCR tool to extract core metadata such as issue dates, payees, and transaction amounts from bank drafts and financial bills.
MD to PDF Conversion
An Openclaw skill that converts markdown files into beautifully formatted, styled PDF documents complete with syntax highlighting, tables, and full CJK character support.
opentui
A high-performance, Zig-native terminal UI framework with TypeScript bindings, Yoga Flexbox layouts, and declarative React/Solid wrappers.
Featured*
