aliyun-image
阿里云百炼图像生成、编辑与翻译。文生图：根据文本生成图像，支持复杂文字渲染。图像编辑：单图编辑、多图融合、风格迁移、物体增删。图像翻译：翻译图像中的文字，保留原始排版，支持11种源语言和14种目标语言。触发词：生成图片、AI作画、文生图、图像编辑、修图、换背景、风格迁移、多图融合、图像翻译、图片翻译。模型：qwen-image-plus(默认)、qwen-image-max、qwen-image-edit-plus(默认)、qwen-image-edit-max、qwen-mt-image。
Why use this skill?
Power your AI agent with Aliyun Image. Generate high-quality art, edit photos, and translate text within images effortlessly. Simple setup for your workflow.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/stanleychanh/aliyun-imageWhat This Skill Does
The aliyun-image skill is a comprehensive toolkit for image manipulation powered by Alibaba Cloud's Bailian platform. It provides seamless access to Qwen’s multimodal capabilities, covering text-to-image synthesis, advanced image editing, and intelligent image translation. Whether you need to generate high-fidelity artistic illustrations from natural language prompts, perform complex object-aware editing such as background replacement or style transfer, or translate text embedded within images while preserving typography and layout, this skill handles it all with professional-grade performance.
Installation
To integrate this skill into your OpenClaw agent, use the following terminal command:
clawhub install openclaw/skills/skills/stanleychanh/aliyun-image
After installation, ensure you have your DASHSCOPE_API_KEY set as an environment variable to authorize your agent to communicate with the Alibaba Cloud APIs.
Use Cases
- Creative Content Production: Generating unique assets for social media, blogs, or marketing campaigns from scratch.
- Image Retouching: Modifying existing assets by adding/removing objects or changing backgrounds for e-commerce.
- Localization: Translating international posters, menus, or documentation images while maintaining the original design, font style, and structural layout.
- Style Synthesis: Applying aesthetic styles to standard photos to create consistent visual themes.
Example Prompts
- "生成图片：一只赛博朋克风格的橘猫坐在霓虹灯下的咖啡馆里。"
- "图像编辑：查看这张照片，请把背景换成夏威夷的海滩，并保持猫咪的姿态不变。"
- "图像翻译：把这张英文产品说明书翻译成中文，注意保留原始排版和图片布局。"
Tips & Limitations
- Model Selection: By default, the skill uses the 'Plus' series for a balance of speed and quality. If you require maximum detail and resolution, explicitly ask the agent to use the 'Max' series (e.g., 'Use the highest quality model for this image').
- Negative Prompting: The skill automatically applies standard negative prompts to prevent common AI artifacts like limb distortion, though you can override these via parameter overrides if necessary.
- API Handling: Image translation is an asynchronous operation. The agent will automatically handle the polling process, but be aware that processing time may vary based on image complexity and resolution. Ensure high-quality input images (under 10MB) for the best results.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-stanleychanh-aliyun-image": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, external-api