Best use case
```skill is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
---
Teams using ```skill should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/tongyi-wanxiang/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ```skill Compares
| Feature / Agent | ```skill | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
---
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
```skill
---
name: tongyi-wanxiang
description: 通义万相 (Tongyi Wanxiang) image generation via Alibaba Cloud DashScope API. Random prompt sampler + gallery.
homepage: https://help.aliyun.com/zh/model-studio/developer-reference/tongyi-wanxiang
metadata: {"openclaw":{"emoji":"🎨","requires":{"bins":["python3"],"env":["DASHSCOPE_API_KEY"]},"primaryEnv":"DASHSCOPE_API_KEY","install":[{"id":"python-brew","kind":"brew","formula":"python","bins":["python3"],"label":"Install Python (brew)"}]}}
---
# 通义万相 (Tongyi Wanxiang)
使用阿里云 DashScope API 生成图像,支持通义万相系列模型。
## 配置
设置 API Key(阿里云灵积模型服务):
```bash
export DASHSCOPE_API_KEY="sk-xxx"
```
获取 API Key: [阿里云灵积模型服务](https://dashscope.console.aliyun.com/)
## Run
```bash
python3 {baseDir}/scripts/gen.py
open ~/Projects/tmp/tongyi-wanxiang-*/index.html
```
### 使用示例
```bash
# 基础用法 - 自动生成随机 prompt
python3 {baseDir}/scripts/gen.py --count 4
# 指定 prompt
python3 {baseDir}/scripts/gen.py --prompt "一只穿着宇航服的龙虾在月球漫步" --count 2
# 使用不同尺寸
python3 {baseDir}/scripts/gen.py --size 1024*1024 --prompt "中国水墨画风格的山水"
python3 {baseDir}/scripts/gen.py --size 720*1280 --prompt "赛博朋克风格的城市夜景"
# 使用 wanx2.1-t2i-turbo 模型 (更快)
python3 {baseDir}/scripts/gen.py --model wanx2.1-t2i-turbo --prompt "油画风格的向日葵"
# 使用 wanx2.1-t2i-plus 模型 (更高质量)
python3 {baseDir}/scripts/gen.py --model wanx2.1-t2i-plus --prompt "精细的建筑设计图"
```
## 模型
| 模型 | 说明 | 速度 |
|------|------|------|
| `wanx2.1-t2i-turbo` | 标准模型,平衡质量和速度 | 快 |
| `wanx2.1-t2i-plus` | 高质量模型,更精细的细节 | 慢 |
## 参数
### 尺寸 (`--size`)
支持的分辨率:
- `1024*1024` (1:1 方形,默认)
- `720*1280` (9:16 竖屏)
- `1280*720` (16:9 横屏)
- `768*1024` (3:4)
- `1024*768` (4:3)
### 数量 (`--count`)
每次可生成 1-4 张图片,默认 4 张。
### 风格提示词
通义万相对中文提示词有很好的支持,建议使用中文描述:
- 风格:水墨画、油画、赛博朋克、极简主义、写实摄影
- 光线:金色时刻、柔和光线、霓虹灯光、戏剧性侧光
- 场景:古典建筑、未来城市、自然风景、室内空间
## Output
- `*.png` 图片文件
- `prompts.json` (prompt → 文件映射)
- `index.html` (缩略图画廊)
```Related Skills
mijia-control
Control and monitor Xiaomi Mijia smart home devices. Use this skill when the user wants to: 1) Switch device status (on/off, brightness, etc.) 2) List available home devices 3) Run automation scenes 4) Check environmental statistics.
weather
Get current weather and forecasts (no API key required).
wacli
Send WhatsApp messages to other people or search/sync WhatsApp history via the wacli CLI (not for normal user chats).
voice-call
Start voice calls via the Clawdbot voice-call plugin.
video-frames
Extract frames or short clips from videos using ffmpeg.
things-mac
Manage Things 3 via the `things` CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks Clawdbot to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
spotify-player
Terminal Spotify playback/search via spogo (preferred) or spotify_player.
sonoscli
Control Sonos speakers (discover/status/play/volume/group).
songsee
Generate spectrograms and feature-panel visualizations from audio with the songsee CLI.
trello
Manage Trello boards, lists, and cards via the Trello REST API.
tmux
Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.
summarize
Summarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”).