How to Get Started with aliyun-image in Your AI Workflow

aliyun-image is a powerful AI agent skill that extends your assistant with new capabilities. Alibaba Cloud Bailian image generation, editing and translation. Vincent diagram: Generate images based on text, supporting complex text rendering. Image editing: single image editing, multi-image fusion, style transfer, object addition and deletion. Image Translation: Translate text in images, retaining original layout, supporting 11 source languages ​​and 14 target languages. Trigger words: Generate pictures, AI painting, Vincent pictures, image editing, picture retouching, background changing, style transfer, multi-picture fusion, image translation, picture translation. Models: qwen-image-plus (default), qwen-image-max, qwen-image-edit-plus (default), qwen-image-edit-max, qwen-mt-image. This guide walks you through installing aliyun-image, configuring it for your setup, and running your first commands — so you can start getting value in minutes.

Step-by-Step Guide

1. 1

   Install aliyun-image: npx clawhub@latest --dir ~/.claude/skills install aliyun-image

2. 2

   Restart your AI client (Claude Code, Cursor, Gemini CLI, or OpenClaw)

3. 3

   Type a natural language request related to design & creative to trigger aliyun-image

4. 4

   Review the output and refine your prompt for better results

5. 5

   Combine aliyun-image with other skills to build multi-step workflows

Example Prompts

Copy these prompts and use them with your AI agent after installing aliyun-image

More Use Cases for aliyun-image