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

FAL_KEY=your_fal_api_key          # Get from https://fal.ai/dashboard/keys
OPENCLAW_GATEWAY_TOKEN=your_token  # From: openclaw doctor --generate-gateway-token

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

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

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

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

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

# Mode 1: Mirror Selfie
PROMPT="make a pic of this person, but <USER_CONTEXT>. the person is taking a mirror selfie"

# Mode 2: Direct Selfie
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"

# Build JSON payload with jq (handles escaping properly)
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"

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

openclaw message send \
  --action send \
  --channel "<TARGET_CHANNEL>" \
  --message "<CAPTION_TEXT>" \
  --media "<IMAGE_URL>"

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

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

# Check required environment variables
if [ -z "$FAL_KEY" ]; then
  echo "Error: FAL_KEY environment variable not set"
  exit 1
fi

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

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

if [ -z "$USER_CONTEXT" ] || [ -z "$CHANNEL" ]; then
  echo "Usage: $0 <user_context> <channel> [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

# Auto-detect mode based on keywords
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"  # default
  fi
  echo "Auto-detected mode: $MODE"
fi

# Construct the prompt based on mode
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"

# Edit image (using jq for proper JSON escaping)
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")

# Extract image 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"

# Send via OpenClaw
openclaw message send \
  --action send \
  --channel "$CHANNEL" \
  --message "$CAPTION" \
  --media "$IMAGE_URL"

echo "Done!"

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"; // default
}

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<string> {
  // Configure fal.ai client
  fal.config({
    credentials: process.env.FAL_KEY!
  });

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

  // Construct the prompt
  const editPrompt = buildPrompt(userContext, actualMode);

  // Edit reference image with Grok Imagine
  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}`);

  // Send via OpenClaw
  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;
}

// Usage Examples

// Mirror mode (auto-detected from "wearing")
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"

// Direct mode (auto-detected from "cafe")
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..."

// Explicit mode override
editAndSend("casual street style", "#fashion", "direct");

npm install @fal-ai/client

npm install -g openclaw

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

openclaw gateway start