A specialized image generation skill that leverages the SiliconFlow API to provide high-performance AI art creation within China without needing a VPN.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install china-image-gen
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 china-image-gen 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 China Image Generator (china-image-gen)?
The China Image Generator is a powerful Openclaw Skills extension designed for developers and creators who need reliable text-to-image capabilities within the Chinese network environment. By utilizing the SiliconFlow API infrastructure, this skill bypasses the need for global proxies or VPNs, offering direct connectivity and support for local payment methods like Alipay and WeChat.
It provides access to a suite of industry-leading models, including FLUX.1 for photorealism, Kolors for superior Chinese prompt comprehension, and Stable Diffusion 3 (SD3) for precise text rendering. Whether you are building internal tools or creative workflows, this skill ensures low-latency image generation with professional-grade output.
China Image Generator (china-image-gen) Use Cases
- Creating photorealistic marketing assets using FLUX.1-dev for maximum quality.
- Generating character art and portraits with Kolors for native Chinese language prompt accuracy.
- Designing social media banners (3:4 or 16:9) with accurate text placement using SD3.
- Rapid prototyping and testing of visual concepts using the free FLUX.1-schnell model.
- Building localized AI applications that require direct network access in China.
How China Image Generator (china-image-gen) Works
- The user provides a natural language description or a specific prompt for an image.
- The skill analyzes the request to select the optimal model based on speed, quality, or language requirements.
- The prompt is automatically optimized or translated (e.g., converting Chinese descriptions to English for better FLUX performance).
- A secure POST request is sent to the SiliconFlow API via curl using the configured SILICONFLOW_API_KEY.
- The skill parses the JSON response to extract the CDN-hosted image URL.
- The resulting image link is presented to the user along with technical metadata and a 1-hour expiration warning.
China Image Generator (china-image-gen) Setup
First, obtain an API key by registering at cloud.siliconflow.cn using a Chinese phone number. Then, configure your environment:
# Set the environment variable directly
export SILICONFLOW_API_KEY="your_api_key_here"
# Or add it to your OpenClaw environment configuration
echo 'SILICONFLOW_API_KEY="your_api_key_here"' >> ~/.openclaw/.env
Ensure curl is installed on your system to handle the API interactions.
China Image Generator (china-image-gen) Data Schema & Taxonomy
The skill processes inputs and generates outputs according to the following schema:
| Attribute | Description | Typical Values |
|---|---|---|
| Model | The AI engine used | FLUX.1-schnell, Kolors, SD3 |
| Image Size | Output dimensions | 1024x1024, 1280x720, 1080x1920 |
| Output | Temporary Image URL | [https://cdn.siliconflow.cn/generated/](https://cdn.siliconflow.cn/generated/)... |
| Metadata | Generation details | Inference time, Seed, and Step count |
Note: Generated URLs are valid for 1 hour. Users are encouraged to download images immediately using curl -o output.png "URL".
China Image Generator (china-image-gen) Advanced Features
- Multi-model routing: Automatically switches between FLUX.1-dev for quality and Kolors for Chinese semantic understanding.
- Prompt Engineering: Built-in optimization logic for adding style keywords like 'photorealistic', 'cyberpunk', or 'Chinese ink painting'.
- Seed Control: Allows for reproducible image generation by fixing the seed value across identical prompts.
- Negative Prompting: Supports complex negative prompts in Kolors and SD3 to filter out anatomical distortions or unwanted artifacts.
- Cost-Efficiency: Optimized to prefer the FLUX.1-schnell model for rapid, low-cost iterations.
SKILL.md
Loading
Related Openclaw Skills
Ubuntu Encyclopedia
A documentation-first workflow agent for Ubuntu system administration, maintenance, and expert-level troubleshooting.
Skill Usage Analyzer
A powerful utility designed to parse SKILL.md files and generate actionable, human-friendly usage guides for any AI agent skill.
TikTok Live Reply Scripts
A specialized AI skill designed to generate real-time, high-conversion objection handling scripts for TikTok Shop live selling sessions.
Feishu Voice Reply
Generate and send native Feishu voice messages with integrated playback bars using high-quality Edge TTS synthesis.
Content Scrubber
A deterministic redaction engine that prevents private infrastructure details from leaking into public messaging channels.
Research Agent
A sophisticated AI research specialist that transforms vague inquiries into comprehensive, source-backed analysis reports and comparison matrices.
Featured*
