Clawra 自拍

使用 xAI 的 Grok Imagine 模型编辑一张固定参考图像，并通过 OpenClaw 将其分发至多个消息平台（WhatsApp、Telegram、Discord、Slack 等）。

参考图像

该技能使用托管在 jsDelivr CDN 上的一张固定参考图像：

https://cdn.jsdelivr.net/gh/SumeLabs/clawra@main/assets/clawra.png

适用场景

• 用户说“send a pic”、“send me a pic”、“send a photo”、“send a selfie”
• 用户说“send a pic of you...”、“send a selfie of you...”
• 用户提问：“what are you doing?”、“how are you doing?”、“where are you?”
• 用户描述具体上下文，例如：“send a pic wearing...”、“send a pic at...”
• 用户希望 Clawra 以特定服饰、地点或情境出镜

快速参考

必需的环境变量

FAL_KEY=your_fal_api_key          # 从 https://fal.ai/dashboard/keys 获取
OPENCLAW_GATEWAY_TOKEN=your_token  # 来自：openclaw doctor --generate-gateway-token

工作流程

1. 获取用户提示：明确图像编辑需求
2. 编辑图像：调用 fal.ai Grok Imagine Edit API，基于固定参考图像执行编辑
3. 提取图像 URL：从 API 响应中解析生成图像的链接
4. 发送至 OpenClaw：指定目标渠道（channel(s)）完成分发

分步操作说明

步骤 1：收集用户输入

向用户询问以下信息：

• 用户上下文：图像中的人物正在做什么／穿着什么／位于何处？
• 模式（可选）：mirror 或 direct 自拍风格
• 目标渠道：图像应发送到哪里？（例如：#general、@username、渠道 ID）
• 平台（可选）：目标平台是哪个？（discord、telegram、whatsapp、slack）

提示模式

模式 1：镜像自拍（默认）

适用于：服饰展示、全身照、时尚类内容

make a pic of this person, but [user's context]. the person is taking a mirror selfie

示例：“wearing a santa hat” →

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

模式 2：直拍自拍

适用于：特写人像、场景定位、情绪表达

a close-up selfie taken by herself at [user's context], direct eye contact with the camera, looking straight into the lens, eyes centered and clearly visible, not a mirror selfie, phone held at arm's length, face fully visible

示例：“a cozy cafe with warm lighting” →

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 arm's length, face fully visible

模式选择逻辑

步骤 2：使用 Grok Imagine 编辑图像

调用 fal.ai API 编辑参考图像：

REFERENCE_IMAGE="https://cdn.jsdelivr.net/gh/SumeLabs/clawra@main/assets/clawra.png"

# 模式 1：镜像自拍
PROMPT="make a pic of this person, but . the person is taking a mirror selfie"

# 模式 2：直拍自拍
PROMPT="a close-up selfie taken by herself at , direct eye contact with the camera, looking straight into the lens, eyes centered and clearly visible, not a mirror selfie, phone held at arm's length, face fully visible"

# 使用 jq 构建 JSON 负载（正确处理转义）
JSON_PAYLOAD=$(jq -n 
  --arg image_url "$REFERENCE_IMAGE" 
  --arg prompt "$PROMPT" 
  '{image_url: $image_url, prompt: $prompt, num_images: 1, output_format: "jpeg"}')

curl -X POST "https://fal.run/xai/grok-imagine-image/edit" 
  -H "Authorization: Key $FAL_KEY" 
  -H "Content-Type: application/json" 
  -d "$JSON_PAYLOAD"

响应格式：

{
  "images": [
    {
      "url": "https://v3b.fal.media/files/...",
      "content_type": "image/jpeg",
      "width": 1024,
      "height": 1024
    }
  ],
  "revised_prompt": "Enhanced prompt text..."
}

步骤 3：通过 OpenClaw 发送图像

使用 OpenClaw 消息 API 发送编辑后的图像：

openclaw message send 
  --action send 
  --channel "" 
  --message "" 
  --media ""

替代方式：直接调用 API

curl -X POST "http://localhost:18789/message" 
  -H "Authorization: Bearer $OPENCLAW_GATEWAY_TOKEN" 
  -H "Content-Type: application/json" 
  -d '{
    "action": "send",
    "channel": "",
    "message": "",
    "media": ""
  }'

完整脚本示例

#!/bin/bash
# grok-imagine-edit-send.sh

# 检查必需的环境变量
if [ -z "$FAL_KEY" ]; then
  echo "Error: FAL_KEY environment variable not set"
  exit 1
fi

# 固定参考图像
REFERENCE_IMAGE="https://cdn.jsdelivr.net/gh/SumeLabs/clawra@main/assets/clawra.png"

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

if [ -z "$USER_CONTEXT" ] || [ -z "$CHANNEL" ]; then
  echo "Usage: $0   [mode] [caption]"
  echo "Modes: mirror, direct, auto (default)"
  echo "Example: $0 'wearing a cowboy hat' '#general' mirror"
  echo "Example: $0 'a cozy cafe' '#general' direct"
  exit 1
fi

# 基于关键词自动检测模式
if [ "$MODE" == "auto" ]; then
  if echo "$USER_CONTEXT" | grep -qiE "outfit|wearing|clothes|dress|suit|fashion|full-body|mirror"; then
    MODE="mirror"
  elif echo "$USER_CONTEXT" | grep -qiE "cafe|restaurant|beach|park|city|close-up|portrait|face|eyes|smile"; then
    MODE="direct"
  else
    MODE="mirror"  # 默认
  fi
  echo "Auto-detected mode: $MODE"
fi

# 根据模式构建提示词
if [ "$MODE" == "direct" ]; then
  EDIT_PROMPT="a close-up selfie taken by herself at $USER_CONTEXT, direct eye contact with the camera, looking straight into the lens, eyes centered and clearly visible, not a mirror selfie, phone held at arm's length, face fully visible"
else
  EDIT_PROMPT="make a pic of this person, but $USER_CONTEXT. the person is taking a mirror selfie"
fi

echo "Mode: $MODE"
echo "Editing reference image with prompt: $EDIT_PROMPT"

# 编辑图像（使用 jq 实现正确的 JSON 转义）
JSON_PAYLOAD=$(jq -n 
  --arg image_url "$REFERENCE_IMAGE" 
  --arg prompt "$EDIT_PROMPT" 
  '{image_url: $image_url, prompt: $prompt, num_images: 1, output_format: "jpeg"}')

RESPONSE=$(curl -s -X POST "https://fal.run/xai/grok-imagine-image/edit" 
  -H "Authorization: Key $FAL_KEY" 
  -H "Content-Type: application/json" 
  -d "$JSON_PAYLOAD")

# 提取图像 URL
IMAGE_URL=$(echo "$RESPONSE" | jq -r '.images[0].url')

if [ "$IMAGE_URL" == "null" ] || [ -z "$IMAGE_URL" ]; then
  echo "Error: Failed to edit image"
  echo "Response: $RESPONSE"
  exit 1
fi

echo "Image edited: $IMAGE_URL"
echo "Sending to channel: $CHANNEL"

# 通过 OpenClaw 发送
openclaw message send 
  --action send 
  --channel "$CHANNEL" 
  --message "$CAPTION" 
  --media "$IMAGE_URL"

echo "Done!"

Node.js / TypeScript 实现

import { fal } from "@fal-ai/client";
import { exec } from "child_process";
import { promisify } from "util";

const execAsync = promisify(exec);

const REFERENCE_IMAGE = "https://cdn.jsdelivr.net/gh/SumeLabs/clawra@main/assets/clawra.png";

interface GrokImagineResult {
  images: Array<{
    url: string;
    content_type: string;
    width: number;
    height: number;
  }>;
  revised_prompt?: string;
}

type SelfieMode = "mirror" | "direct" | "auto";

function detectMode(userContext: string): "mirror" | "direct" {
  const mirrorKeywords = /outfit|wearing|clothes|dress|suit|fashion|full-body|mirror/i;
  const directKeywords = /cafe|restaurant|beach|park|city|close-up|portrait|face|eyes|smile/i;

  if (directKeywords.test(userContext)) return "direct";
  if (mirrorKeywords.test(userContext)) return "mirror";
  return "mirror"; // 默认
}

function buildPrompt(userContext: string, mode: "mirror" | "direct"): string {
  if (mode === "direct") {
    return `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 arm's length, face fully visible`;
  }
  return `make a pic of this person, but ${userContext}. the person is taking a mirror selfie`;
}

async function editAndSend(
  userContext: string,
  channel: string,
  mode: SelfieMode = "auto",
  caption?: string
): Promise {
  // 配置 fal.ai 客户端
  fal.config({
    credentials: process.env.FAL_KEY!
  });

  // 确定模式
  const actualMode = mode === "auto" ? detectMode(userContext) : mode;
  console.log(`Mode: ${actualMode}`);

  // 构建提示词
  const editPrompt = buildPrompt(userContext, actualMode);

  // 使用 Grok Imagine 编辑参考图像
  console.log(`Editing image: "${editPrompt}"`);

  const result = await fal.subscribe("xai/grok-imagine-image/edit", {
    input: {
      image_url: REFERENCE_IMAGE,
      prompt: editPrompt,
      num_images: 1,
      output_format: "jpeg"
    }
  }) as { data: GrokImagineResult };

  const imageUrl = result.data.images[0].url;
  console.log(`Edited image URL: ${imageUrl}`);

  // 通过 OpenClaw 发送
  const messageCaption = caption || `Edited with Grok Imagine`;

  await execAsync(
    `openclaw message send --action send --channel "${channel}" --message "${messageCaption}" --media "${imageUrl}"`
  );

  console.log(`Sent to ${channel}`);
  return imageUrl;
}

// 使用示例

// 镜像模式（由 “wearing” 自动识别）
editAndSend(
  "wearing a cyberpunk outfit with neon lights",
  "#art-gallery",
  "auto",
  "Check out this AI-edited art!"
);
// → Mode: mirror
// → Prompt: "make a pic of this person, but wearing a cyberpunk outfit with neon lights. the person is taking a mirror selfie"

// 直拍模式（由 “cafe” 自动识别）
editAndSend(
  "a cozy cafe with warm lighting",
  "#photography",
  "auto"
);
// → Mode: direct
// → Prompt: "a close-up selfie taken by herself at a cozy cafe with warm lighting, direct eye contact..."

// 显式指定模式
editAndSend("casual street style", "#fashion", "direct");

支持的平台

OpenClaw 支持向以下平台发送：

Grok Imagine Edit 参数说明

配置要求

1. 安装 fal.ai 客户端（Node.js 使用）

npm install @fal-ai/client

2. 安装 OpenClaw CLI

npm install -g openclaw

3. 配置 OpenClaw 网关

openclaw config set gateway.mode=local
openclaw doctor --generate-gateway-token

4. 启动 OpenClaw 网关

openclaw gateway start

错误处理

• FAL_KEY 缺失：请确认环境变量已正确定义
• 图像编辑失败：检查提示词内容及 API 配额是否充足
• OpenClaw 发送失败：确认网关服务正在运行且目标渠道存在
• 速率限制：fal.ai 存在调用频率限制；如需，可实现重试逻辑

使用技巧

1. 镜像模式上下文示例（侧重服饰）：

   • "wearing a santa hat"
   • "in a business suit"
   • "wearing a summer dress"
   • "in streetwear fashion"

2. 直拍模式上下文示例（侧重地点／人像）：

   • "a cozy cafe with warm lighting"
   • "a sunny beach at sunset"
   • "a busy city street at night"
   • "a peaceful park in autumn"

3. 模式选择：可依赖自动检测，也可显式指定以获得更精确控制

4. 批量发送：一次编辑，多渠道分发

5. 定时发布：结合 OpenClaw 调度器实现自动化推送