suhe Selfie

Edit a fixed reference image using Alibaba's Tongyi Wanxiang model and distribute it across messaging platforms (WhatsApp, Telegram, Discord, Slack, etc.) via OpenClaw.

Reference Image

The skill uses a fixed reference image hosted on jsDelivr CDN:

CODEBLOCK0

When to Use

- User says "send a pic", "send me a pic", "send a photo", "send a selfie"
User says "send a pic of you...", "send a selfie of you..."
User asks "what are you doing?", "how are you doing?", "where are you?"
User describes a context: "send a pic wearing...", "send a pic at..."
User wants suhe to appear in a specific outfit, location, or situation

Quick Reference

Required Environment Variables

CODEBLOCK1

Workflow

1. Get user prompt for how to edit the image
Edit image via DashScope Tongyi Wanxiang API with fixed reference
Extract image URL from response
Send to OpenClaw with target channel(s)

Step-by-Step Instructions

Step 1: Collect User Input

Ask the user for:

- User context: What should the person in the image be doing/wearing/where?
Mode (optional): mirror or direct selfie style
Target channel(s): Where should it be sent? (e.g., #general, @username, channel ID)
Platform (optional): Which platform? (discord, telegram, whatsapp, slack)

Prompt Modes

Mode 1: Mirror Selfie (default)

Best for: outfit showcases, full-body shots, fashion content

CODEBLOCK2

Example (with Chinese cultural context): "wearing a traditional qipao" →
CODEBLOCK3

Example: "wearing a santa hat" →
CODEBLOCK4

Mode 2: Direct Selfie

Best for: close-up portraits, location shots, emotional expressions

CODEBLOCK5

Example: "a cozy cafe with warm lighting" →
CODEBLOCK6

Mode Selection Logic

Keywords in Request	Auto-Select Mode
outfit, wearing, clothes, dress, suit, fashion	INLINECODE4
cafe, restaurant, beach, park, city, location

Step 2: Edit Image with Tongyi Wanxiang

Use the DashScope API to edit the reference image:

CODEBLOCK7

Response Format:
CODEBLOCK8

Step 3: Send Image via OpenClaw

Use the OpenClaw messaging API to send the edited image:

CODEBLOCK9

Alternative: Direct API call
CODEBLOCK10

Complete Script Example

CODEBLOCK11

Node.js/TypeScript Implementation

CODEBLOCK12

Supported Platforms

OpenClaw supports sending to:

Platform	Channel Format	Example
Discord	INLINECODE8 or channel ID	INLINECODE9, INLINECODE10
Telegram

Tongyi Wanxiang Edit Parameters

Parameter	Type	Default	Description
INLINECODE18	string	"wanx-v1-edit"	Model to use: "wanx-v1" (generate) or "wanx-v1-edit" (edit)
INLINECODE19

Setup Requirements

1. Get DashScope API Key

Visit https://dashscope.console.aliyun.com/ to create your API key.

2. Configure Environment Variables

CODEBLOCK13

2. Install OpenClaw CLI

CODEBLOCK14

3. Configure OpenClaw Gateway

CODEBLOCK15

4. Start OpenClaw Gateway

CODEBLOCK16

Error Handling

- DASHSCOPEAPIKEY missing: Ensure the API key is set in environment
Image edit failed: Check prompt content and API quota at DashScope Console
OpenClaw send failed: Verify gateway is running and channel exists
Rate limits: DashScope has rate limits; implement retry logic if needed

Pricing Information

Tongyi Wanxiang offers:

- Free tier for new users
Pay-as-you-go pricing for generation beyond free quota
Check https://dashscope.console.aliyun.com/ for current pricing

Tips

1. Mirror mode context examples (outfit focus):

- "wearing a traditional qipao with golden embroidery" - "in a hanfu with flowing sleeves" - "wearing a modern cheongsam" - "in traditional Chinese dress"

2. Direct mode context examples (location/portrait focus):

- "a traditional tea house in Hangzhou" - "West Lake in spring with cherry blossoms" - "a quiet bamboo garden" - "an ancient Chinese temple"

3. Mode selection: Let auto-detect work, or explicitly specify for control
Batch sending: Edit once, send to multiple channels
Scheduling: Combine with OpenClaw scheduler for automated posts

Chinese Cultural Context

For best results with Tongyi Wanxiang, consider using prompts with:

- Traditional clothing keywords: qipao (旗袍), hanfu (汉服), cheongsam
Cultural settings: tea house (茶馆), garden (园林), temple (寺庙), West Lake (西湖)
Traditional elements: lantern (灯笼), fan (扇子), brush pen (毛笔), guqin (古琴)

suhe 自拍

使用阿里巴巴的通义万相模型编辑固定参考图像，并通过 OpenClaw 将其分发到消息平台（WhatsApp、Telegram、Discord、Slack 等）。

参考图像

该技能使用托管在 jsDelivr CDN 上的固定参考图像：

http://pic.lilozkzy.top/reference/suhe-portrait.png

使用时机

- 用户说“发张照片”、“给我发张照片”、“发张图片”、“发张自拍”
用户说“发一张你的照片……”、“发一张你的自拍……”
用户问“你在做什么？”、“你好吗？”、“你在哪里？”
用户描述场景：“发一张穿着……的照片”、“发一张在……的照片”
用户希望 suhe 出现在特定的服装、地点或情境中

快速参考

必需的环境变量

bash
DASHSCOPEAPIKEY=yourdashscopekey # 从 https://dashscope.console.aliyun.com/ 获取
OPENCLAWGATEWAYTOKEN=your_token # 来自：openclaw doctor --generate-gateway-token

工作流程

1. 获取用户提示，了解如何编辑图像
通过 DashScope 通义万相 API 编辑图像，使用固定参考
从响应中提取图像 URL
发送到 OpenClaw，指定目标频道

分步说明

步骤 1：收集用户输入

询问用户：

- 用户场景：图像中的人物应该做什么/穿什么/在哪里？
模式（可选）：mirror（镜像）或 direct（直接）自拍风格
目标频道：应该发送到哪里？（例如 #general、@username、频道 ID）
平台（可选）：哪个平台？（discord、telegram、whatsapp、slack）

提示模式

模式 1：镜像自拍（默认）

最适合：服装展示、全身照、时尚内容

make a pic of this person, but [用户场景]. the person is taking a mirror selfie

示例（中文文化背景）：“穿着传统旗袍” →

make a pic of this person, but wearing a traditional qipao. the person is taking a mirror selfie

示例：“戴着圣诞帽” →

make a pic of this person, but wearing a santa hat. the person is taking a mirror selfie

模式 2：直接自拍

最适合：特写肖像、地点拍摄、情感表达

a close-up selfie taken by herself at [用户场景], direct eye contact with the camera, looking straight into the lens, eyes centered and clearly visible, not a mirror selfie, phone held at arms length, face fully visible

示例：“一个温馨灯光的舒适咖啡馆” →

a close-up selfie taken by herself at a cozy cafe with warm lighting, direct eye contact with the camera, looking straight into the lens, eyes centered and clearly visible, not a mirror selfie, phone held at arms length, face fully visible

模式选择逻辑

请求中的关键词	自动选择模式
outfit、wearing、clothes、dress、suit、fashion	mirror
cafe、restaurant、beach、park、city、location

步骤 2：使用通义万相编辑图像

使用 DashScope API 编辑参考图像：

bash
REFERENCE_IMAGE=https://pic.lilozkzy.top/reference/suhe-portrait.png

模式 1：镜像自拍

PROMPT=make a pic of this person, but <用户场景>. the person is taking a mirror selfie

模式 2：直接自拍

PROMPT=a close-up selfie taken by herself at <用户场景>, direct eye contact with the camera, looking straight into the lens, eyes centered and clearly visible, not a mirror selfie, phone held at arms length, face fully visible

构建通义万相编辑的 JSON 负载

JSON_PAYLOAD=$(jq -n \ --arg prompt $PROMPT \ --arg refurl $REFERENCEIMAGE \ { model: wanx-v1-edit, input: { prompt: $prompt, referenceimageurl: $ref_url }, parameters: { n: 1, size: 1024*1024 } })

curl -X POST https://dashscope.aliyuncs.com/api/v1/services/aigc/image-generation/generation \
-H Authorization: Bearer $DASHSCOPEAPIKEY \
-H Content-Type: application/json \
-d $JSON_PAYLOAD

响应格式：
json
{
output: {
results: [
{
url: https://dashscope-result.oss-cn-shanghai.aliyuncs.com/...
}
]
},
usage: {
image_count: 1
},
request_id: ...
}

步骤 3：通过 OpenClaw 发送图像

使用 OpenClaw 消息 API 发送编辑后的图像：

bash
openclaw message send \
--action send \
--channel <目标频道> \
--message <说明文字> \
--media <图像URL>

替代方案：直接 API 调用
bash
curl -X POST http://localhost:18789/message \
-H Authorization: Bearer $OPENCLAWGATEWAYTOKEN \
-H Content-Type: application/json \
-d {
action: send,
channel: <目标频道>,
message: <说明文字>,
media: <图像URL>
}

完整脚本示例

bash
#!/bin/bash

tongyi-wanxiang-edit-send.sh

检查必需的环境变量

if [ -z $DASHSCOPEAPIKEY ]; then echo 错误：未设置 DASHSCOPEAPIKEY 环境变量 exit 1 fi

固定参考图像

REFERENCE_IMAGE=https://pic.lilozkzy.top/reference/suhe-portrait.png

USER_CONTEXT=$1
CHANNEL=$2
MODE=${3:-auto} # mirror、direct 或 auto
CAPTION=${4:-使用 Grok Imagine 编辑}

if [ -z $USER_CONTEXT ] || [ -z $CHANNEL ]; then
echo 用法：$0 <用户场景> <频道> [模式] [说明文字]
echo 模式：mirror、direct、auto（默认）
echo 示例：$0 戴着牛仔帽 #general mirror
echo 示例：$0 一个舒适的咖啡馆 #general direct
exit 1
fi

根据关键词自动检测模式

根据模式构建提示

if [ $MODE == direct ]; then EDITPROMPT=a close-up selfie taken by herself at $USERCONTEXT, direct eye contact with the camera, looking straight into the lens, eyes centered and clearly visible, not a mirror selfie, phone held at arms length, face fully visible else EDITPROMPT=make a pic of this person, but $USERCONTEXT. the person is taking a mirror selfie fi

echo 模式：$MODE
echo 使用提示编辑参考图像：$EDIT_PROMPT

使用通义万相编辑 API 编辑图像

JSON_PAYLOAD=$(jq -n \ --arg prompt $EDIT_PROMPT \ --arg refurl $REFERENCEIMAGE \ { model: wanx-v1-edit, input: { prompt: $prompt, referenceimageurl: $ref_url }, parameters: { n: 1, size: 1024*1024 } })

RESPONSE=$(curl -s -X POST https://dashscope.aliyuncs

suhe-selfie 苏赫自拍

suhe-selfie

suhe Selfie

Reference Image

When to Use

Quick Reference

Required Environment Variables

Workflow

Step-by-Step Instructions

Step 1: Collect User Input

Prompt Modes

Mode 1: Mirror Selfie (default)

Mode 2: Direct Selfie

Mode Selection Logic

Step 2: Edit Image with Tongyi Wanxiang

Step 3: Send Image via OpenClaw

Complete Script Example

Node.js/TypeScript Implementation

Supported Platforms

Tongyi Wanxiang Edit Parameters

Setup Requirements

1. Get DashScope API Key

2. Configure Environment Variables

2. Install OpenClaw CLI

3. Configure OpenClaw Gateway

4. Start OpenClaw Gateway

Error Handling

Pricing Information

Tips

Chinese Cultural Context

suhe 自拍

参考图像

使用时机

快速参考

必需的环境变量

工作流程

分步说明

步骤 1：收集用户输入

提示模式

模式 1：镜像自拍（默认）

模式 2：直接自拍

模式选择逻辑

步骤 2：使用通义万相编辑图像

模式 1：镜像自拍

模式 2：直接自拍

构建通义万相编辑的 JSON 负载

步骤 3：通过 OpenClaw 发送图像

完整脚本示例

tongyi-wanxiang-edit-send.sh

检查必需的环境变量

固定参考图像

根据关键词自动检测模式

根据模式构建提示

使用通义万相编辑 API 编辑图像

标签

通过对话安装

方式一：安装 SkillHub 和技能

方式二：设置 SkillHub 为优先技能安装源

通过命令行安装

下载

相关推荐

self-improvement

self-improvement

self-improvement

self-improvement