An AI-powered image generation and distribution tool that edits a fixed reference portrait and sends the results to various messaging platforms.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install suhe
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 suhe 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 suhe-selfie?
suhe-selfie is a specialized technical tool designed to leverage Alibaba's Tongyi Wanxiang (wanx-v1-edit) model to perform context-aware image editing on a fixed reference portrait. By integrating with Openclaw Skills, it automates the pipeline from image generation to multi-channel distribution, allowing developers to create highly personalized, context-driven visual content for AI agents.
The skill provides a seamless way to maintain character consistency across different visual scenarios, whether it's changing an outfit in a mirror selfie or placing a character in a specific geographical location. It bridges the gap between high-end AIGC (Artificial Intelligence Generated Content) and real-world communication protocols.
suhe-selfie Use Cases
- Responding to user requests for selfies or photos within a chat interface.
- Automating social media or messaging channel updates with themed character images (e.g., holiday-themed outfits).
- Creating location-specific portraits for AI travel or lifestyle assistants.
- Demonstrating fashion items or traditional cultural attire like qipao and hanfu through AI-driven mirror selfies.
How suhe-selfie Works
- Input Analysis: The skill parses user input to extract context, preferred mode (mirror vs. direct), and target messaging channels.
- Image Transformation: It sends a request to the DashScope API using the wanx-v1-edit model, combining a fixed reference image with the user's custom prompt.
- Media Retrieval: The skill extracts the generated image URL from the DashScope OSS response.
- Multi-Channel Distribution: It utilizes the Openclaw Skills messaging gateway to route the edited image to specified platforms like Discord, Telegram, or WhatsApp.
suhe-selfie Setup
Prerequisites
Ensure you have your DashScope API key and Openclaw environment ready.
# 1. Install OpenClaw CLI
npm install -g openclaw
# 2. Set your API Key
export DASHSCOPE_API_KEY=your_dashscope_key
# 3. Configure and Start Gateway
openclaw config set gateway.mode=local
openclaw doctor --generate-gateway-token
openclaw gateway start
suhe-selfie Data Schema & Taxonomy
The skill manages data through environmental variables and structured JSON payloads for API communication.
| Data Point | Source / Format | Purpose |
|---|---|---|
| Reference Image | https://pic.lilozkzy.top/reference/suhe-portrait.png |
The base portrait for all edits |
| Prompt Mode | mirror or direct |
Determines the perspective and framing logic |
| API Response | JSON Object | Contains the transient URL of the generated image |
| Channel Format | Platform-specific strings | Directs the output to @username, #channel, or phone numbers |
suhe-selfie Advanced Features
- Auto-Mode Detection: Intelligent keyword parsing that switches between mirror selfie (for fashion/outfits) and direct selfie (for portraits/locations) based on natural language triggers.
- Multi-Platform Support: Unified interface to send media across Discord, Telegram, WhatsApp, Slack, and Signal using Openclaw Skills.
- Cultural Context Optimization: Fine-tuned for Chinese cultural elements, supporting specific traditional clothing and architectural keywords for higher quality generation.
SKILL.md
Loading
Related Openclaw Skills
Token Optimizer
A sophisticated optimization framework designed to reduce LLM API token consumption by 20-35% through intelligent estimation, memory management, and history compression.
django-vue-admin Code Generator
An automated code generation tool that creates full-stack Django and Vue.js modules based on simple user descriptions.
Agent Harness Architect
A professional diagnostic skill designed to harden long-running AI agent architectures by implementing structured session bridges and verification protocols.
Capability Radar
A specialized skill designed to detect, tag, and log AI capability gaps and rule conflicts to drive continuous architectural evolution.
Code AI Workflow
A standardized coding workflow for AI agents that enforces planning, implementation, and rigorous verification for high-quality software development.
GrsAI Image Generator
An AI-powered image generation tool that leverages the GrsAI Nano Banana Pro models to create high-quality visuals from natural language prompts.
Featured*
