diff --git a/.gitignore b/.gitignore
new file mode 100644
index 00000000..71491fe2
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,32 @@
+# Dependencies
+node_modules/
+
+# Build output
+dist/
+
+# TypeScript cache
+*.tsbuildinfo
+
+# OS files
+.DS_Store
+Thumbs.db
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# Environment / secrets
+.env
+.env.local
+.env.*.local
+
+# npm
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+
+# Temporary files
+/tmp/
+*.tmp
diff --git a/README.md b/README.md
index 18a96fca..a85635c3 100644
--- a/README.md
+++ b/README.md
@@ -10,7 +10,7 @@ npx clawra@latest
 
 This will:
 1. Check OpenClaw is installed
-2. Guide you to get a fal.ai API key
+2. Guide you to select image provider(s) and enter API key(s)
 3. Install the skill to `~/.openclaw/skills/clawra-selfie/`
 4. Configure OpenClaw to use the skill
 5. Add selfie capabilities to your agent's SOUL.md
@@ -29,10 +29,19 @@ Clawra Selfie enables your OpenClaw agent to:
 | **Mirror** | Full-body shots, outfits | wearing, outfit, fashion |
 | **Direct** | Close-ups, locations | cafe, beach, portrait, smile |
 
+## Supported Providers
+
+| Provider | Model | Env Variable | API Key URL |
+|----------|-------|-------------|-------------|
+| **fal** (default) | Grok Imagine via fal.ai | `FAL_KEY` | [fal.ai/dashboard/keys](https://fal.ai/dashboard/keys) |
+| **openai** | gpt-image-1 | `OPENAI_API_KEY` | [platform.openai.com/api-keys](https://platform.openai.com/api-keys) |
+| **google** | gemini-2.5-flash-image | `GEMINI_API_KEY` | [aistudio.google.com/apikey](https://aistudio.google.com/apikey) |
+| **xai** | grok-imagine-image (direct) | `XAI_API_KEY` | [console.x.ai](https://console.x.ai) |
+
 ## Prerequisites
 
 - [OpenClaw](https://github.com/openclaw/openclaw) installed and configured
-- [fal.ai](https://fal.ai) account (free tier available)
+- At least one provider API key (see table above)
 
 ## Manual Installation
 
@@ -40,7 +49,7 @@ If you prefer manual setup:
 
 ### 1. Get API Key
 
-Visit [fal.ai/dashboard/keys](https://fal.ai/dashboard/keys) and create an API key.
+Choose a provider and get its API key from the table above.
 
 ### 2. Clone the Skill
 
@@ -59,6 +68,7 @@ Add to `~/.openclaw/openclaw.json`:
       "clawra-selfie": {
         "enabled": true,
         "env": {
+          "IMAGE_PROVIDER": "fal",
           "FAL_KEY": "your_fal_key_here"
         }
       }
@@ -67,6 +77,36 @@ Add to `~/.openclaw/openclaw.json`:
 }
 ```
 
+Set `IMAGE_PROVIDER` to your chosen provider (`fal`, `openai`, `google`, or `xai`) and include the corresponding API key:
+
+| IMAGE_PROVIDER | Required Env Key |
+|---------------|-----------------|
+| `fal` | `FAL_KEY` |
+| `openai` | `OPENAI_API_KEY` |
+| `google` | `GEMINI_API_KEY` |
+| `xai` | `XAI_API_KEY` |
+
+You can configure multiple providers at once:
+
+```json
+{
+  "skills": {
+    "entries": {
+      "clawra-selfie": {
+        "enabled": true,
+        "env": {
+          "IMAGE_PROVIDER": "openai",
+          "FAL_KEY": "your_fal_key",
+          "OPENAI_API_KEY": "your_openai_key",
+          "GEMINI_API_KEY": "your_gemini_key",
+          "XAI_API_KEY": "your_xai_key"
+        }
+      }
+    }
+  }
+}
+```
+
 ### 4. Update SOUL.md
 
 Add the selfie persona to `~/.openclaw/workspace/SOUL.md`:
@@ -101,7 +141,8 @@ This ensures consistent appearance across all generated images.
 
 ## Technical Details
 
-- **Image Generation**: xAI Grok Imagine via fal.ai
+- **Image Generation**: Multiple providers (fal.ai, OpenAI, Google Gemini, x.ai)
+- **Provider Selection**: Via `IMAGE_PROVIDER` env variable
 - **Messaging**: OpenClaw Gateway API
 - **Supported Platforms**: Discord, Telegram, WhatsApp, Slack, Signal, MS Teams
 
@@ -110,13 +151,24 @@ This ensures consistent appearance across all generated images.
 ```
 clawra/
 ├── bin/
-│   └── cli.js           # npx installer
+│   └── cli.js              # npx installer (multi-provider)
+├── scripts/
+│   ├── providers/           # Provider abstraction layer
+│   │   ├── types.ts         # Shared interface
+│   │   ├── fal.ts           # fal.ai provider
+│   │   ├── openai.ts        # OpenAI provider
+│   │   ├── google.ts        # Google Gemini provider
+│   │   ├── xai.ts           # x.ai direct provider
+│   │   └── index.ts         # Factory function
+│   ├── clawra-selfie.ts     # TypeScript implementation
+│   └── clawra-selfie.sh     # Bash implementation
 ├── skill/
-│   ├── SKILL.md         # Skill definition
-│   ├── scripts/         # Generation scripts
-│   └── assets/          # Reference image
+│   ├── SKILL.md             # Skill definition
+│   ├── scripts/             # Generation scripts (copy)
+│   └── assets/              # Reference image
 ├── templates/
-│   └── soul-injection.md # Persona template
+│   └── soul-injection.md    # Persona template
+├── tsconfig.json
 └── package.json
 ```
 
diff --git a/SKILL.md b/SKILL.md
index c09ce1db..d85beb3c 100644
--- a/SKILL.md
+++ b/SKILL.md
@@ -1,12 +1,23 @@
 ---
 name: clawra-selfie
-description: Edit Clawra's reference image with Grok Imagine (xAI Aurora) and send selfies to messaging channels via OpenClaw
+description: Generate and edit images using multiple AI providers (fal.ai, OpenAI, Google Gemini, x.ai) and send selfies to messaging channels via OpenClaw
 allowed-tools: Bash(npm:*) Bash(npx:*) Bash(openclaw:*) Bash(curl:*) Read Write WebFetch
 ---
 
 # Clawra Selfie
 
-Edit a fixed reference image using xAI's Grok Imagine model and distribute it across messaging platforms (WhatsApp, Telegram, Discord, Slack, etc.) via OpenClaw.
+Generate and edit images using multiple AI providers and distribute them across messaging platforms (WhatsApp, Telegram, Discord, Slack, etc.) via OpenClaw.
+
+## Supported Providers
+
+| Provider | Model | Env Variable | API Key URL |
+|----------|-------|-------------|-------------|
+| **fal** (default) | Grok Imagine (via fal.ai) | `FAL_KEY` | https://fal.ai/dashboard/keys |
+| **openai** | gpt-image-1 | `OPENAI_API_KEY` | https://platform.openai.com/api-keys |
+| **google** | gemini-2.5-flash-image | `GEMINI_API_KEY` | https://aistudio.google.com/apikey |
+| **xai** | grok-imagine-image (direct) | `XAI_API_KEY` | https://console.x.ai |
+
+Set the provider via the `IMAGE_PROVIDER` environment variable (default: `fal`).
 
 ## Reference Image
 
@@ -29,16 +40,24 @@ https://cdn.jsdelivr.net/gh/SumeLabs/clawra@main/assets/clawra.png
 ### Required Environment Variables
 
 ```bash
-FAL_KEY=your_fal_api_key          # Get from https://fal.ai/dashboard/keys
+# Pick ONE provider and set its API key:
+IMAGE_PROVIDER=fal               # Options: fal, openai, google, xai (default: fal)
+
+FAL_KEY=your_fal_api_key          # For provider: fal
+OPENAI_API_KEY=your_openai_key    # For provider: openai
+GEMINI_API_KEY=your_gemini_key    # For provider: google
+XAI_API_KEY=your_xai_key          # For provider: xai
+
 OPENCLAW_GATEWAY_TOKEN=your_token  # From: openclaw doctor --generate-gateway-token
 ```
 
 ### Workflow
 
 1. **Get user prompt** for how to edit the image
-2. **Edit image** via fal.ai Grok Imagine Edit API with fixed reference
-3. **Extract image URL** from response
-4. **Send to OpenClaw** with target channel(s)
+2. **Select provider** (from env var or default)
+3. **Generate/edit image** via selected provider
+4. **Extract image URL** from response
+5. **Send to OpenClaw** with target channel(s)
 
 ## Step-by-Step Instructions
 
@@ -49,6 +68,7 @@ Ask the user for:
 - **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)
+- **Provider** (optional): Which image provider to use?
 
 ## Prompt Modes
 
@@ -85,20 +105,13 @@ a close-up selfie taken by herself at a cozy cafe with warm lighting, direct eye
 | close-up, portrait, face, eyes, smile | `direct` |
 | full-body, mirror, reflection | `mirror` |
 
-### Step 2: Edit Image with Grok Imagine
+### Step 2: Generate/Edit Image
 
-Use the fal.ai API to edit the reference image:
+#### Provider: fal.ai (default)
 
 ```bash
 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 "$PROMPT" \
@@ -110,24 +123,114 @@ curl -X POST "https://fal.run/xai/grok-imagine-image/edit" \
   -d "$JSON_PAYLOAD"
 ```
 
-**Response Format:**
+**Response:**
 ```json
 {
-  "images": [
-    {
-      "url": "https://v3b.fal.media/files/...",
-      "content_type": "image/jpeg",
-      "width": 1024,
-      "height": 1024
-    }
-  ],
+  "images": [{ "url": "https://v3b.fal.media/files/...", "width": 1024, "height": 1024 }],
   "revised_prompt": "Enhanced prompt text..."
 }
 ```
 
+#### Provider: OpenAI
+
+```bash
+curl -X POST "https://api.openai.com/v1/images/generations" \
+  -H "Authorization: Bearer $OPENAI_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gpt-image-1",
+    "prompt": "A cute cat wearing a hat",
+    "n": 1,
+    "size": "1024x1024"
+  }'
+```
+
+**Response:**
+```json
+{
+  "data": [{ "b64_json": "..." }]
+}
+```
+
+> Note: OpenAI gpt-image-1 returns base64-encoded images. Save the `b64_json` field to a file.
+
+#### Provider: Google Gemini
+
+```bash
+curl -s -X POST \
+  "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:generateContent?key=$GEMINI_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "contents": [{"parts": [{"text": "A cute cat wearing a hat"}]}],
+    "generationConfig": {"responseModalities": ["IMAGE"]}
+  }'
+```
+
+**Response:**
+```json
+{
+  "candidates": [{
+    "content": {
+      "parts": [{ "inlineData": { "mimeType": "image/png", "data": "<BASE64>" } }]
+    }
+  }]
+}
+```
+
+> Note: Google Gemini returns base64 inline data. Decode the `data` field and save to a file.
+
+For image editing with Gemini, include the reference image as an `inlineData` part:
+```bash
+curl -s -X POST \
+  "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:generateContent?key=$GEMINI_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d "{
+    \"contents\": [{
+      \"parts\": [
+        {\"text\": \"Edit this person to be wearing a santa hat\"},
+        {\"inlineData\": {\"mimeType\": \"image/jpeg\", \"data\": \"<BASE64_IMAGE_DATA>\"}}
+      ]
+    }],
+    \"generationConfig\": {\"responseModalities\": [\"IMAGE\"]}
+  }"
+```
+
+#### Provider: x.ai (direct)
+
+```bash
+curl -X POST "https://api.x.ai/v1/images/generations" \
+  -H "Authorization: Bearer $XAI_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "grok-imagine-image",
+    "prompt": "A cute cat wearing a hat",
+    "n": 1
+  }'
+```
+
+For image editing, add `image_url`:
+```bash
+curl -X POST "https://api.x.ai/v1/images/generations" \
+  -H "Authorization: Bearer $XAI_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "grok-imagine-image",
+    "prompt": "Edit this to wear a santa hat",
+    "n": 1,
+    "image_url": "https://example.com/photo.jpg"
+  }'
+```
+
+**Response:**
+```json
+{
+  "data": [{ "url": "https://..." }]
+}
+```
+
 ### Step 3: Send Image via OpenClaw
 
-Use the OpenClaw messaging API to send the edited image:
+Use the OpenClaw messaging API to send the generated image:
 
 ```bash
 openclaw message send \
@@ -154,191 +257,69 @@ curl -X POST "http://localhost:18789/message" \
 
 ```bash
 #!/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"
+# Multi-provider image generation and send
 
+PROVIDER="${IMAGE_PROVIDER:-fal}"
 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!"
+CAPTION="${3:-Generated with Clawra}"
+
+# Route to provider
+case "$PROVIDER" in
+  fal)
+    curl -s -X POST "https://fal.run/xai/grok-imagine-image" \
+      -H "Authorization: Key $FAL_KEY" \
+      -H "Content-Type: application/json" \
+      -d "{\"prompt\": \"$USER_CONTEXT\", \"num_images\": 1}"
+    ;;
+  openai)
+    curl -s -X POST "https://api.openai.com/v1/images/generations" \
+      -H "Authorization: Bearer $OPENAI_API_KEY" \
+      -H "Content-Type: application/json" \
+      -d "{\"model\": \"gpt-image-1\", \"prompt\": \"$USER_CONTEXT\", \"n\": 1, \"size\": \"1024x1024\"}"
+    ;;
+  google)
+    curl -s -X POST \
+      "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:generateContent?key=$GEMINI_API_KEY" \
+      -H "Content-Type: application/json" \
+      -d "{\"contents\": [{\"parts\": [{\"text\": \"$USER_CONTEXT\"}]}], \"generationConfig\": {\"responseModalities\": [\"IMAGE\"]}}"
+    ;;
+  xai)
+    curl -s -X POST "https://api.x.ai/v1/images/generations" \
+      -H "Authorization: Bearer $XAI_API_KEY" \
+      -H "Content-Type: application/json" \
+      -d "{\"model\": \"grok-imagine-image\", \"prompt\": \"$USER_CONTEXT\", \"n\": 1}"
+    ;;
+esac
 ```
 
+For the full implementation with error handling, mode detection, and OpenClaw integration, see the scripts in `scripts/clawra-selfie.sh` or `scripts/clawra-selfie.ts`.
+
 ## Node.js/TypeScript Implementation
 
 ```typescript
-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!
+import { getProvider } from "./providers";
+
+// Generate image with any provider
+const provider = getProvider("openai"); // or "fal", "google", "xai"
+const result = await provider.generateImage({
+  prompt: "A sunset over the ocean",
+  numImages: 1,
+  aspectRatio: "16:9",
+  outputFormat: "jpeg",
+});
+
+console.log(result.images[0].url);
+
+// Edit image (fal, google, xai support editing)
+if (provider.editImage) {
+  const edited = await provider.editImage({
+    imageUrl: "https://example.com/photo.jpg",
+    prompt: "Add a santa hat",
+    numImages: 1,
   });
-
-  // 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;
+  console.log(edited.images[0].url);
 }
-
-// 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");
 ```
 
 ## Supported Platforms
@@ -354,20 +335,51 @@ OpenClaw supports sending to:
 | Signal | Phone number | `+1234567890` |
 | MS Teams | Channel reference | (varies) |
 
-## Grok Imagine Edit Parameters
+## Provider-Specific Parameters
+
+### fal.ai (Grok Imagine)
 
 | Parameter | Type | Default | Description |
 |-----------|------|---------|-------------|
-| `image_url` | string | required | URL of image to edit (fixed in this skill) |
-| `prompt` | string | required | Edit instruction |
+| `image_url` | string | - | URL of image to edit |
+| `prompt` | string | required | Generation/edit instruction |
 | `num_images` | 1-4 | 1 | Number of images to generate |
+| `aspect_ratio` | enum | "1:1" | 2:1, 16:9, 4:3, 1:1, 3:4, 9:16 |
 | `output_format` | enum | "jpeg" | jpeg, png, webp |
 
+### OpenAI (gpt-image-1)
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `model` | string | "gpt-image-1" | Model to use |
+| `prompt` | string | required | Image description |
+| `n` | 1-10 | 1 | Number of images |
+| `size` | enum | "1024x1024" | 1024x1024, 1536x1024, 1024x1536 |
+| `output_format` | enum | "png" | png, jpeg, webp |
+
+### Google Gemini
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `contents` | array | required | Prompt parts (text + optional image) |
+| `responseModalities` | array | ["IMAGE"] | Must include "IMAGE" |
+| `imageMimeType` | string | - | Output mime type |
+
+### x.ai (Grok Imagine Direct)
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `model` | string | "grok-imagine-image" | Model to use |
+| `prompt` | string | required | Image description |
+| `n` | number | 1 | Number of images |
+| `image_url` | string | - | Source image for editing |
+| `aspect_ratio` | enum | - | 1:1, 16:9, 9:16, etc. |
+
 ## Setup Requirements
 
-### 1. Install fal.ai client (for Node.js usage)
+### 1. Install dependencies (for Node.js usage)
 ```bash
-npm install @fal-ai/client
+npm install @fal-ai/client  # only needed for fal provider
 ```
 
 ### 2. Install OpenClaw CLI
@@ -388,10 +400,11 @@ openclaw gateway start
 
 ## Error Handling
 
-- **FAL_KEY missing**: Ensure the API key is set in environment
-- **Image edit failed**: Check prompt content and API quota
+- **API key missing**: Ensure the correct key is set for your chosen provider
+- **Image generation failed**: Check prompt content and API quota
 - **OpenClaw send failed**: Verify gateway is running and channel exists
-- **Rate limits**: fal.ai has rate limits; implement retry logic if needed
+- **Base64 responses**: OpenAI and Google return base64 data; scripts auto-save to temp files
+- **Rate limits**: Each provider has its own rate limits; implement retry logic if needed
 
 ## Tips
 
@@ -399,14 +412,18 @@ openclaw gateway start
    - "wearing a santa hat"
    - "in a business suit"
    - "wearing a summer dress"
-   - "in streetwear fashion"
 
 2. **Direct mode context examples** (location/portrait focus):
    - "a cozy cafe with warm lighting"
    - "a sunny beach at sunset"
    - "a busy city street at night"
-   - "a peaceful park in autumn"
 
-3. **Mode selection**: Let auto-detect work, or explicitly specify for control
-4. **Batch sending**: Edit once, send to multiple channels
-5. **Scheduling**: Combine with OpenClaw scheduler for automated posts
+3. **Provider selection**:
+   - Use `fal` for quick Grok Imagine access via fal.ai proxy
+   - Use `openai` for GPT-image-1's strong prompt following
+   - Use `google` for Gemini's integrated image generation
+   - Use `xai` for direct x.ai access without fal.ai proxy
+
+4. **Mode selection**: Let auto-detect work, or explicitly specify for control
+5. **Batch sending**: Generate once, send to multiple channels
+6. **Scheduling**: Combine with OpenClaw scheduler for automated posts
diff --git a/bin/cli.js b/bin/cli.js
index 86f6d6c4..ed40f2e0 100755
--- a/bin/cli.js
+++ b/bin/cli.js
@@ -162,15 +162,23 @@ function copyDir(src, dest) {
   }
 }
 
+// Provider definitions
+const PROVIDERS = {
+  fal: { name: "fal.ai (Grok Imagine)", envKey: "FAL_KEY", url: "https://fal.ai/dashboard/keys" },
+  openai: { name: "OpenAI (gpt-image-1)", envKey: "OPENAI_API_KEY", url: "https://platform.openai.com/api-keys" },
+  google: { name: "Google Gemini", envKey: "GEMINI_API_KEY", url: "https://aistudio.google.com/apikey" },
+  xai: { name: "x.ai (Grok Imagine)", envKey: "XAI_API_KEY", url: "https://console.x.ai" },
+};
+
 // Print banner
 function printBanner() {
   console.log(`
-${c("magenta", "┌─────────────────────────────────────────┐")}
-${c("magenta", "│")}  ${c("bright", "Clawra Selfie")} - OpenClaw Skill Installer ${c("magenta", "│")}
-${c("magenta", "└─────────────────────────────────────────┘")}
+${c("magenta", "┌──────────────────────────────────────────────────────┐")}
+${c("magenta", "│")}  ${c("bright", "Clawra Selfie")} - Multi-Provider Skill Installer   ${c("magenta", "│")}
+${c("magenta", "└──────────────────────────────────────────────────────┘")}
 
 Add selfie generation superpowers to your OpenClaw agent!
-Uses ${c("cyan", "xAI Grok Imagine")} via ${c("cyan", "fal.ai")} for image editing.
+Supported providers: ${c("cyan", "fal.ai")}, ${c("cyan", "OpenAI")}, ${c("cyan", "Google Gemini")}, ${c("cyan", "x.ai")}
 `);
 }
 
@@ -207,40 +215,75 @@ async function checkPrerequisites() {
   return true;
 }
 
-// Get FAL API key
-async function getFalApiKey(rl) {
-  logStep("2/7", "Setting up fal.ai API key...");
+// Get API keys for selected providers
+async function getApiKeys(rl) {
+  logStep("2/7", "Setting up image provider API keys...");
 
-  const FAL_URL = "https://fal.ai/dashboard/keys";
+  log(`\nWhich image providers would you like to configure?`);
+  log(`You need at least one provider. You can add more later.\n`);
 
-  log(`\nTo use Grok Imagine, you need a fal.ai API key.`);
-  log(`${c("cyan", "→")} Get your key from: ${c("bright", FAL_URL)}\n`);
+  const providerIds = Object.keys(PROVIDERS);
+  for (let i = 0; i < providerIds.length; i++) {
+    const id = providerIds[i];
+    const p = PROVIDERS[id];
+    log(`  ${c("cyan", `${i + 1})`)} ${p.name} (${c("dim", p.envKey)})`);
+  }
+  log("");
 
-  const openIt = await ask(rl, "Open fal.ai in browser? (Y/n): ");
+  const selection = await ask(
+    rl,
+    `Enter provider numbers (comma-separated, default: 1): `
+  );
 
-  if (openIt.toLowerCase() !== "n") {
-    logInfo("Opening browser...");
-    if (!openBrowser(FAL_URL)) {
-      logWarn("Could not open browser automatically");
-      logInfo(`Please visit: ${FAL_URL}`);
-    }
+  const selectedNums = (selection || "1")
+    .split(",")
+    .map((s) => parseInt(s.trim(), 10) - 1)
+    .filter((n) => n >= 0 && n < providerIds.length);
+
+  if (selectedNums.length === 0) {
+    selectedNums.push(0); // default to fal
   }
 
-  log("");
-  const falKey = await ask(rl, "Enter your FAL_KEY: ");
+  const apiKeys = {};
 
-  if (!falKey) {
-    logError("FAL_KEY is required!");
-    return null;
+  for (const idx of selectedNums) {
+    const id = providerIds[idx];
+    const p = PROVIDERS[id];
+
+    log(`\n${c("bright", `Setting up ${p.name}...`)}`);
+    log(`${c("cyan", "→")} Get your key from: ${c("bright", p.url)}\n`);
+
+    const openIt = await ask(rl, `Open ${p.name} in browser? (Y/n): `);
+    if (openIt.toLowerCase() !== "n") {
+      logInfo("Opening browser...");
+      if (!openBrowser(p.url)) {
+        logWarn("Could not open browser automatically");
+        logInfo(`Please visit: ${p.url}`);
+      }
+    }
+
+    log("");
+    const key = await ask(rl, `Enter your ${p.envKey}: `);
+
+    if (!key) {
+      logWarn(`Skipping ${p.name} (no key provided)`);
+      continue;
+    }
+
+    if (key.length < 10) {
+      logWarn("That key looks too short. Make sure you copied the full key.");
+    }
+
+    apiKeys[id] = key;
+    logSuccess(`${p.name} API key received`);
   }
 
-  // Basic validation
-  if (falKey.length < 10) {
-    logWarn("That key looks too short. Make sure you copied the full key.");
+  if (Object.keys(apiKeys).length === 0) {
+    logError("At least one API key is required!");
+    return null;
   }
 
-  logSuccess("API key received");
-  return falKey;
+  return apiKeys;
 }
 
 // Install skill files
@@ -287,21 +330,31 @@ async function installSkill() {
 }
 
 // Update OpenClaw config
-async function updateOpenClawConfig(falKey) {
+async function updateOpenClawConfig(apiKeys) {
   logStep("4/7", "Updating OpenClaw configuration...");
 
   let config = readJsonFile(OPENCLAW_CONFIG) || {};
 
+  // Build env vars from all configured providers
+  const env = {};
+  for (const [providerId, key] of Object.entries(apiKeys)) {
+    const p = PROVIDERS[providerId];
+    if (p) {
+      env[p.envKey] = key;
+    }
+  }
+
+  // Set default provider to the first configured one
+  const defaultProvider = Object.keys(apiKeys)[0];
+  env.IMAGE_PROVIDER = defaultProvider;
+
   // Merge skill configuration
   const skillConfig = {
     skills: {
       entries: {
         [SKILL_NAME]: {
           enabled: true,
-          apiKey: falKey,
-          env: {
-            FAL_KEY: falKey,
-          },
+          env,
         },
       },
     },
@@ -322,6 +375,11 @@ async function updateOpenClawConfig(falKey) {
 
   writeJsonFile(OPENCLAW_CONFIG, config);
   logSuccess(`Updated: ${OPENCLAW_CONFIG}`);
+  logInfo(`Default provider: ${PROVIDERS[defaultProvider].name}`);
+
+  for (const [providerId] of Object.entries(apiKeys)) {
+    logInfo(`Configured: ${PROVIDERS[providerId].name}`);
+  }
 
   return true;
 }
@@ -437,12 +495,15 @@ ${c("cyan", "Identity set:")}
 ${c("cyan", "Persona updated:")}
   ${SOUL_MD}
 
+${c("cyan", "Switch provider:")}
+  Set IMAGE_PROVIDER to: fal, openai, google, or xai
+
 ${c("yellow", "Try saying to your agent:")}
   "Send me a selfie"
   "Send a pic wearing a cowboy hat"
   "What are you doing right now?"
 
-${c("dim", "Your agent now has selfie superpowers!")}
+${c("dim", "Your agent now has multi-provider selfie superpowers!")}
 `);
 }
 
@@ -485,9 +546,9 @@ async function main() {
       }
     }
 
-    // Step 2: Get FAL API key
-    const falKey = await getFalApiKey(rl);
-    if (!falKey) {
+    // Step 2: Get API keys (multi-provider)
+    const apiKeys = await getApiKeys(rl);
+    if (!apiKeys) {
       rl.close();
       process.exit(1);
     }
@@ -496,7 +557,7 @@ async function main() {
     await installSkill();
 
     // Step 4: Update OpenClaw config
-    await updateOpenClawConfig(falKey);
+    await updateOpenClawConfig(apiKeys);
 
     // Step 5: Write IDENTITY.md
     await writeIdentity();
diff --git a/package-lock.json b/package-lock.json
new file mode 100644
index 00000000..c91ce29a
--- /dev/null
+++ b/package-lock.json
@@ -0,0 +1,285 @@
+{
+  "name": "clawra",
+  "version": "1.1.1",
+  "lockfileVersion": 3,
+  "requires": true,
+  "packages": {
+    "": {
+      "name": "clawra",
+      "version": "1.1.1",
+      "license": "MIT",
+      "bin": {
+        "clawra": "bin/cli.js"
+      },
+      "devDependencies": {
+        "@fal-ai/client": "^1.2.0",
+        "@types/node": "^22.0.0",
+        "ts-node": "^10.9.2",
+        "typescript": "^5.7.0"
+      },
+      "engines": {
+        "node": ">=18.0.0"
+      }
+    },
+    "node_modules/@cspotcode/source-map-support": {
+      "version": "0.8.1",
+      "resolved": "https://registry.npmjs.org/@cspotcode/source-map-support/-/source-map-support-0.8.1.tgz",
+      "integrity": "sha512-IchNf6dN4tHoMFIn/7OE8LWZ19Y6q/67Bmf6vnGREv8RSbBVb9LPJxEcnwrcwX6ixSvaiGoomAUvu4YSxXrVgw==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@jridgewell/trace-mapping": "0.3.9"
+      },
+      "engines": {
+        "node": ">=12"
+      }
+    },
+    "node_modules/@fal-ai/client": {
+      "version": "1.9.0",
+      "resolved": "https://registry.npmjs.org/@fal-ai/client/-/client-1.9.0.tgz",
+      "integrity": "sha512-okIXfgrjiRlens0CGbg50LFR0cZYfIG+DehC5ObTQUwSziOzqlytkFDi98dqbgvtfu4Ecbtjz90rj5/EVSEZog==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@msgpack/msgpack": "^3.0.0-beta2",
+        "eventsource-parser": "^1.1.2",
+        "robot3": "^0.4.1"
+      },
+      "engines": {
+        "node": ">=18.0.0"
+      }
+    },
+    "node_modules/@jridgewell/resolve-uri": {
+      "version": "3.1.2",
+      "resolved": "https://registry.npmjs.org/@jridgewell/resolve-uri/-/resolve-uri-3.1.2.tgz",
+      "integrity": "sha512-bRISgCIjP20/tbWSPWMEi54QVPRZExkuD9lJL+UIxUKtwVJA8wW1Trb1jMs1RFXo1CBTNZ/5hpC9QvmKWdopKw==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=6.0.0"
+      }
+    },
+    "node_modules/@jridgewell/sourcemap-codec": {
+      "version": "1.5.5",
+      "resolved": "https://registry.npmjs.org/@jridgewell/sourcemap-codec/-/sourcemap-codec-1.5.5.tgz",
+      "integrity": "sha512-cYQ9310grqxueWbl+WuIUIaiUaDcj7WOq5fVhEljNVgRfOUhY9fy2zTvfoqWsnebh8Sl70VScFbICvJnLKB0Og==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/@jridgewell/trace-mapping": {
+      "version": "0.3.9",
+      "resolved": "https://registry.npmjs.org/@jridgewell/trace-mapping/-/trace-mapping-0.3.9.tgz",
+      "integrity": "sha512-3Belt6tdc8bPgAtbcmdtNJlirVoTmEb5e2gC94PnkwEW9jI6CAHUeoG85tjWP5WquqfavoMtMwiG4P926ZKKuQ==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@jridgewell/resolve-uri": "^3.0.3",
+        "@jridgewell/sourcemap-codec": "^1.4.10"
+      }
+    },
+    "node_modules/@msgpack/msgpack": {
+      "version": "3.1.3",
+      "resolved": "https://registry.npmjs.org/@msgpack/msgpack/-/msgpack-3.1.3.tgz",
+      "integrity": "sha512-47XIizs9XZXvuJgoaJUIE2lFoID8ugvc0jzSHP+Ptfk8nTbnR8g788wv48N03Kx0UkAv559HWRQ3yzOgzlRNUA==",
+      "dev": true,
+      "license": "ISC",
+      "engines": {
+        "node": ">= 18"
+      }
+    },
+    "node_modules/@tsconfig/node10": {
+      "version": "1.0.12",
+      "resolved": "https://registry.npmjs.org/@tsconfig/node10/-/node10-1.0.12.tgz",
+      "integrity": "sha512-UCYBaeFvM11aU2y3YPZ//O5Rhj+xKyzy7mvcIoAjASbigy8mHMryP5cK7dgjlz2hWxh1g5pLw084E0a/wlUSFQ==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/@tsconfig/node12": {
+      "version": "1.0.11",
+      "resolved": "https://registry.npmjs.org/@tsconfig/node12/-/node12-1.0.11.tgz",
+      "integrity": "sha512-cqefuRsh12pWyGsIoBKJA9luFu3mRxCA+ORZvA4ktLSzIuCUtWVxGIuXigEwO5/ywWFMZ2QEGKWvkZG1zDMTag==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/@tsconfig/node14": {
+      "version": "1.0.3",
+      "resolved": "https://registry.npmjs.org/@tsconfig/node14/-/node14-1.0.3.tgz",
+      "integrity": "sha512-ysT8mhdixWK6Hw3i1V2AeRqZ5WfXg1G43mqoYlM2nc6388Fq5jcXyr5mRsqViLx/GJYdoL0bfXD8nmF+Zn/Iow==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/@tsconfig/node16": {
+      "version": "1.0.4",
+      "resolved": "https://registry.npmjs.org/@tsconfig/node16/-/node16-1.0.4.tgz",
+      "integrity": "sha512-vxhUy4J8lyeyinH7Azl1pdd43GJhZH/tP2weN8TntQblOY+A0XbT8DJk1/oCPuOOyg/Ja757rG0CgHcWC8OfMA==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/@types/node": {
+      "version": "22.19.11",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-22.19.11.tgz",
+      "integrity": "sha512-BH7YwL6rA93ReqeQS1c4bsPpcfOmJasG+Fkr6Y59q83f9M1WcBRHR2vM+P9eOisYRcN3ujQoiZY8uk5W+1WL8w==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "undici-types": "~6.21.0"
+      }
+    },
+    "node_modules/acorn": {
+      "version": "8.15.0",
+      "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.15.0.tgz",
+      "integrity": "sha512-NZyJarBfL7nWwIq+FDL6Zp/yHEhePMNnnJ0y3qfieCrmNvYct8uvtiV41UvlSe6apAfk0fY1FbWx+NwfmpvtTg==",
+      "dev": true,
+      "license": "MIT",
+      "bin": {
+        "acorn": "bin/acorn"
+      },
+      "engines": {
+        "node": ">=0.4.0"
+      }
+    },
+    "node_modules/acorn-walk": {
+      "version": "8.3.4",
+      "resolved": "https://registry.npmjs.org/acorn-walk/-/acorn-walk-8.3.4.tgz",
+      "integrity": "sha512-ueEepnujpqee2o5aIYnvHU6C0A42MNdsIDeqy5BydrkuC5R1ZuUFnm27EeFJGoEHJQgn3uleRvmTXaJgfXbt4g==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "acorn": "^8.11.0"
+      },
+      "engines": {
+        "node": ">=0.4.0"
+      }
+    },
+    "node_modules/arg": {
+      "version": "4.1.3",
+      "resolved": "https://registry.npmjs.org/arg/-/arg-4.1.3.tgz",
+      "integrity": "sha512-58S9QDqG0Xx27YwPSt9fJxivjYl432YCwfDMfZ+71RAqUrZef7LrKQZ3LHLOwCS4FLNBplP533Zx895SeOCHvA==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/create-require": {
+      "version": "1.1.1",
+      "resolved": "https://registry.npmjs.org/create-require/-/create-require-1.1.1.tgz",
+      "integrity": "sha512-dcKFX3jn0MpIaXjisoRvexIJVEKzaq7z2rZKxf+MSr9TkdmHmsU4m2lcLojrj/FHl8mk5VxMmYA+ftRkP/3oKQ==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/diff": {
+      "version": "4.0.4",
+      "resolved": "https://registry.npmjs.org/diff/-/diff-4.0.4.tgz",
+      "integrity": "sha512-X07nttJQkwkfKfvTPG/KSnE2OMdcUCao6+eXF3wmnIQRn2aPAHH3VxDbDOdegkd6JbPsXqShpvEOHfAT+nCNwQ==",
+      "dev": true,
+      "license": "BSD-3-Clause",
+      "engines": {
+        "node": ">=0.3.1"
+      }
+    },
+    "node_modules/eventsource-parser": {
+      "version": "1.1.2",
+      "resolved": "https://registry.npmjs.org/eventsource-parser/-/eventsource-parser-1.1.2.tgz",
+      "integrity": "sha512-v0eOBUbiaFojBu2s2NPBfYUoRR9GjcDNvCXVaqEf5vVfpIAh9f8RCo4vXTP8c63QRKCFwoLpMpTdPwwhEKVgzA==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=14.18"
+      }
+    },
+    "node_modules/make-error": {
+      "version": "1.3.6",
+      "resolved": "https://registry.npmjs.org/make-error/-/make-error-1.3.6.tgz",
+      "integrity": "sha512-s8UhlNe7vPKomQhC1qFelMokr/Sc3AgNbso3n74mVPA5LTZwkB9NlXf4XPamLxJE8h0gh73rM94xvwRT2CVInw==",
+      "dev": true,
+      "license": "ISC"
+    },
+    "node_modules/robot3": {
+      "version": "0.4.1",
+      "resolved": "https://registry.npmjs.org/robot3/-/robot3-0.4.1.tgz",
+      "integrity": "sha512-hzjy826lrxzx8eRgv80idkf8ua1JAepRc9Efdtj03N3KNJuznQCPlyCJ7gnUmDFwZCLQjxy567mQVKmdv2BsXQ==",
+      "dev": true,
+      "license": "BSD-2-Clause"
+    },
+    "node_modules/ts-node": {
+      "version": "10.9.2",
+      "resolved": "https://registry.npmjs.org/ts-node/-/ts-node-10.9.2.tgz",
+      "integrity": "sha512-f0FFpIdcHgn8zcPSbf1dRevwt047YMnaiJM3u2w2RewrB+fob/zePZcrOyQoLMMO7aBIddLcQIEK5dYjkLnGrQ==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "@cspotcode/source-map-support": "^0.8.0",
+        "@tsconfig/node10": "^1.0.7",
+        "@tsconfig/node12": "^1.0.7",
+        "@tsconfig/node14": "^1.0.0",
+        "@tsconfig/node16": "^1.0.2",
+        "acorn": "^8.4.1",
+        "acorn-walk": "^8.1.1",
+        "arg": "^4.1.0",
+        "create-require": "^1.1.0",
+        "diff": "^4.0.1",
+        "make-error": "^1.1.1",
+        "v8-compile-cache-lib": "^3.0.1",
+        "yn": "3.1.1"
+      },
+      "bin": {
+        "ts-node": "dist/bin.js",
+        "ts-node-cwd": "dist/bin-cwd.js",
+        "ts-node-esm": "dist/bin-esm.js",
+        "ts-node-script": "dist/bin-script.js",
+        "ts-node-transpile-only": "dist/bin-transpile.js",
+        "ts-script": "dist/bin-script-deprecated.js"
+      },
+      "peerDependencies": {
+        "@swc/core": ">=1.2.50",
+        "@swc/wasm": ">=1.2.50",
+        "@types/node": "*",
+        "typescript": ">=2.7"
+      },
+      "peerDependenciesMeta": {
+        "@swc/core": {
+          "optional": true
+        },
+        "@swc/wasm": {
+          "optional": true
+        }
+      }
+    },
+    "node_modules/typescript": {
+      "version": "5.9.3",
+      "resolved": "https://registry.npmjs.org/typescript/-/typescript-5.9.3.tgz",
+      "integrity": "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw==",
+      "dev": true,
+      "license": "Apache-2.0",
+      "bin": {
+        "tsc": "bin/tsc",
+        "tsserver": "bin/tsserver"
+      },
+      "engines": {
+        "node": ">=14.17"
+      }
+    },
+    "node_modules/undici-types": {
+      "version": "6.21.0",
+      "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-6.21.0.tgz",
+      "integrity": "sha512-iwDZqg0QAGrg9Rav5H4n0M64c3mkR59cJ6wQp+7C4nI0gsmExaedaYLNO44eT4AtBBwjbTiGPMlt2Md0T9H9JQ==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/v8-compile-cache-lib": {
+      "version": "3.0.1",
+      "resolved": "https://registry.npmjs.org/v8-compile-cache-lib/-/v8-compile-cache-lib-3.0.1.tgz",
+      "integrity": "sha512-wa7YjyUGfNZngI/vtK0UHAN+lgDCxBPCylVXGp0zu59Fz5aiGtNXaq3DhIov063MorB+VfufLh3JlF2KdTK3xg==",
+      "dev": true,
+      "license": "MIT"
+    },
+    "node_modules/yn": {
+      "version": "3.1.1",
+      "resolved": "https://registry.npmjs.org/yn/-/yn-3.1.1.tgz",
+      "integrity": "sha512-Ux4ygGWsu2c7isFWe8Yu1YluJmqVhxqK2cLXNQA5AcC3QfbGNpM7fu0Y8b/z16pXLnFxZYvWhd3fhBY9DLmC6Q==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=6"
+      }
+    }
+  }
+}
diff --git a/package.json b/package.json
index aff645bf..4d50b1fb 100644
--- a/package.json
+++ b/package.json
@@ -1,7 +1,7 @@
 {
   "name": "clawra",
   "version": "1.1.1",
-  "description": "Add selfie superpowers to your OpenClaw agent using xAI Grok Imagine",
+  "description": "Add selfie superpowers to your OpenClaw agent with multi-provider image generation (fal.ai, OpenAI, Google Gemini, x.ai)",
   "bin": {
     "clawra": "./bin/cli.js"
   },
@@ -20,6 +20,10 @@
     "xai",
     "aurora",
     "fal.ai",
+    "openai",
+    "gemini",
+    "google",
+    "imagen",
     "selfie",
     "ai-agent",
     "image-generation",
@@ -42,4 +46,4 @@
     "ts-node": "^10.9.2",
     "typescript": "^5.7.0"
   }
-}
+}
\ No newline at end of file
diff --git a/scripts/clawra-selfie.sh b/scripts/clawra-selfie.sh
index 72d176d5..e7caafa1 100755
--- a/scripts/clawra-selfie.sh
+++ b/scripts/clawra-selfie.sh
@@ -1,14 +1,18 @@
 #!/bin/bash
-# grok-imagine-send.sh
-# Generate an image with Grok Imagine and send it via OpenClaw
+# clawra-selfie.sh
+# Generate an image with multiple AI providers and send it via OpenClaw
 #
-# Usage: ./grok-imagine-send.sh "<prompt>" "<channel>" ["<caption>"]
+# Supported providers (set via IMAGE_PROVIDER env var):
+#   fal    - fal.ai / Grok Imagine    (requires FAL_KEY)
+#   openai - OpenAI gpt-image-1       (requires OPENAI_API_KEY)
+#   google - Google Gemini             (requires GEMINI_API_KEY)
+#   xai    - x.ai direct              (requires XAI_API_KEY)
 #
-# Environment variables required:
-#   FAL_KEY - Your fal.ai API key
+# Usage: ./clawra-selfie.sh "<prompt>" "<channel>" ["<caption>"] [aspect_ratio] [output_format]
 #
 # Example:
-#   FAL_KEY=your_key ./grok-imagine-send.sh "A sunset over mountains" "#art" "Check this out!"
+#   FAL_KEY=your_key ./clawra-selfie.sh "A sunset over mountains" "#art" "Check this out!"
+#   IMAGE_PROVIDER=openai OPENAI_API_KEY=xxx ./clawra-selfie.sh "A sunset" "#art"
 
 set -euo pipefail
 
@@ -30,13 +34,6 @@ log_error() {
     echo -e "${RED}[ERROR]${NC} $1"
 }
 
-# Check required environment variables
-if [ -z "${FAL_KEY:-}" ]; then
-    log_error "FAL_KEY environment variable not set"
-    echo "Get your API key from: https://fal.ai/dashboard/keys"
-    exit 1
-fi
-
 # Check for jq
 if ! command -v jq &> /dev/null; then
     log_error "jq is required but not installed"
@@ -55,9 +52,10 @@ fi
 # Parse arguments
 PROMPT="${1:-}"
 CHANNEL="${2:-}"
-CAPTION="${3:-Generated with Grok Imagine}"
+CAPTION="${3:-Generated with Clawra}"
 ASPECT_RATIO="${4:-1:1}"
 OUTPUT_FORMAT="${5:-jpeg}"
+PROVIDER="${IMAGE_PROVIDER:-fal}"
 
 if [ -z "$PROMPT" ] || [ -z "$CHANNEL" ]; then
     echo "Usage: $0 <prompt> <channel> [caption] [aspect_ratio] [output_format]"
@@ -65,51 +63,222 @@ if [ -z "$PROMPT" ] || [ -z "$CHANNEL" ]; then
     echo "Arguments:"
     echo "  prompt        - Image description (required)"
     echo "  channel       - Target channel (required) e.g., #general, @user"
-    echo "  caption       - Message caption (default: 'Generated with Grok Imagine')"
+    echo "  caption       - Message caption (default: 'Generated with Clawra')"
     echo "  aspect_ratio  - Image ratio (default: 1:1) Options: 2:1, 16:9, 4:3, 1:1, 3:4, 9:16"
     echo "  output_format - Image format (default: jpeg) Options: jpeg, png, webp"
     echo ""
+    echo "Environment:"
+    echo "  IMAGE_PROVIDER   - Provider to use (default: fal)"
+    echo "                     Options: fal, openai, google, xai"
+    echo "  FAL_KEY          - Required for provider: fal"
+    echo "  OPENAI_API_KEY   - Required for provider: openai"
+    echo "  GEMINI_API_KEY   - Required for provider: google"
+    echo "  XAI_API_KEY      - Required for provider: xai"
+    echo ""
     echo "Example:"
     echo "  $0 \"A cyberpunk city at night\" \"#art-gallery\" \"AI Art!\""
+    echo "  IMAGE_PROVIDER=openai $0 \"A sunset\" \"#photos\""
     exit 1
 fi
 
-log_info "Generating image with Grok Imagine..."
+log_info "Provider: $PROVIDER"
+log_info "Generating image..."
 log_info "Prompt: $PROMPT"
 log_info "Aspect ratio: $ASPECT_RATIO"
 
-# Generate image via fal.ai
-RESPONSE=$(curl -s -X POST "https://fal.run/xai/grok-imagine-image" \
-    -H "Authorization: Key $FAL_KEY" \
-    -H "Content-Type: application/json" \
-    -d "{
-        \"prompt\": $(echo "$PROMPT" | jq -Rs .),
-        \"num_images\": 1,
-        \"aspect_ratio\": \"$ASPECT_RATIO\",
-        \"output_format\": \"$OUTPUT_FORMAT\"
-    }")
-
-# Check for errors in response
-if echo "$RESPONSE" | jq -e '.error' > /dev/null 2>&1; then
-    ERROR_MSG=$(echo "$RESPONSE" | jq -r '.error // .detail // "Unknown error"')
-    log_error "Image generation failed: $ERROR_MSG"
-    exit 1
-fi
+# ============================================================================
+# Provider: fal.ai (Grok Imagine)
+# ============================================================================
+generate_fal() {
+    if [ -z "${FAL_KEY:-}" ]; then
+        log_error "FAL_KEY environment variable not set"
+        echo "Get your API key from: https://fal.ai/dashboard/keys"
+        exit 1
+    fi
+
+    RESPONSE=$(curl -s -X POST "https://fal.run/xai/grok-imagine-image" \
+        -H "Authorization: Key $FAL_KEY" \
+        -H "Content-Type: application/json" \
+        -d "{
+            \"prompt\": $(echo "$PROMPT" | jq -Rs .),
+            \"num_images\": 1,
+            \"aspect_ratio\": \"$ASPECT_RATIO\",
+            \"output_format\": \"$OUTPUT_FORMAT\"
+        }")
+
+    # Check for error (ensure it's not null/empty)
+    ERROR_VAL=$(echo "$RESPONSE" | jq -r '.error // .detail // empty')
+    if [ -n "$ERROR_VAL" ]; then
+        log_error "fal.ai image generation failed: $ERROR_VAL"
+        exit 1
+    fi
+
+    # Try multiple response paths: images[0].url, data[0].url
+    IMAGE_URL=$(echo "$RESPONSE" | jq -r '.images[0].url // .data[0].url // empty')
+    REVISED_PROMPT=$(echo "$RESPONSE" | jq -r '.revised_prompt // empty')
+
+    if [ -z "$IMAGE_URL" ]; then
+        log_warn "Could not extract image URL from fal.ai response"
+        log_warn "Response: $(echo "$RESPONSE" | head -c 500)"
+    fi
+}
+
+# ============================================================================
+# Provider: OpenAI (gpt-image-1)
+# ============================================================================
+generate_openai() {
+    if [ -z "${OPENAI_API_KEY:-}" ]; then
+        log_error "OPENAI_API_KEY environment variable not set"
+        echo "Get your API key from: https://platform.openai.com/api-keys"
+        exit 1
+    fi
+
+    # Map aspect ratio to OpenAI size
+    case "$ASPECT_RATIO" in
+        16:9|2:1|20:9|19.5:9|3:2) SIZE="1536x1024" ;;
+        9:16|1:2|9:19.5|9:20|2:3|3:4) SIZE="1024x1536" ;;
+        *) SIZE="1024x1024" ;;
+    esac
+
+    RESPONSE=$(curl -s -X POST "https://api.openai.com/v1/images/generations" \
+        -H "Authorization: Bearer $OPENAI_API_KEY" \
+        -H "Content-Type: application/json" \
+        -d "{
+            \"model\": \"gpt-image-1\",
+            \"prompt\": $(echo "$PROMPT" | jq -Rs .),
+            \"n\": 1,
+            \"size\": \"$SIZE\"
+        }")
+
+    if echo "$RESPONSE" | jq -e '.error' > /dev/null 2>&1; then
+        ERROR_MSG=$(echo "$RESPONSE" | jq -r '.error.message // .error // "Unknown error"')
+        log_error "OpenAI image generation failed: $ERROR_MSG"
+        exit 1
+    fi
+
+    # OpenAI gpt-image-1 returns base64 – save to temp file
+    B64_DATA=$(echo "$RESPONSE" | jq -r '.data[0].b64_json // empty')
+    URL_DATA=$(echo "$RESPONSE" | jq -r '.data[0].url // empty')
 
-# Extract image URL
-IMAGE_URL=$(echo "$RESPONSE" | jq -r '.images[0].url // empty')
+    if [ -n "$URL_DATA" ]; then
+        IMAGE_URL="$URL_DATA"
+    elif [ -n "$B64_DATA" ]; then
+        TMPFILE=$(mktemp /tmp/clawra-openai-XXXXXX."$OUTPUT_FORMAT")
+        echo "$B64_DATA" | base64 -d > "$TMPFILE"
+        IMAGE_URL="$TMPFILE"
+        log_info "Saved to temp file: $TMPFILE"
+    else
+        log_error "OpenAI response contained neither url nor b64_json"
+        echo "Response: $RESPONSE"
+        exit 1
+    fi
+
+    REVISED_PROMPT=$(echo "$RESPONSE" | jq -r '.data[0].revised_prompt // empty')
+}
 
+# ============================================================================
+# Provider: Google Gemini (gemini-2.5-flash-image)
+# ============================================================================
+generate_google() {
+    if [ -z "${GEMINI_API_KEY:-}" ]; then
+        log_error "GEMINI_API_KEY environment variable not set"
+        echo "Get your API key from: https://aistudio.google.com/apikey"
+        exit 1
+    fi
+
+    local MODEL="gemini-2.5-flash-image"
+
+    RESPONSE=$(curl -s -X POST \
+        "https://generativelanguage.googleapis.com/v1beta/models/${MODEL}:generateContent?key=${GEMINI_API_KEY}" \
+        -H "Content-Type: application/json" \
+        -d "{
+            \"contents\": [{
+                \"parts\": [{\"text\": $(echo "$PROMPT" | jq -Rs .)}]
+            }],
+            \"generationConfig\": {
+                \"responseModalities\": [\"IMAGE\"]
+            }
+        }")
+
+    if echo "$RESPONSE" | jq -e '.error' > /dev/null 2>&1; then
+        ERROR_MSG=$(echo "$RESPONSE" | jq -r '.error.message // .error // "Unknown error"')
+        log_error "Google Gemini image generation failed: $ERROR_MSG"
+        exit 1
+    fi
+
+    # Extract base64 image data from Gemini response
+    B64_DATA=$(echo "$RESPONSE" | jq -r '.candidates[0].content.parts[] | select(.inlineData) | .inlineData.data // empty' | head -1)
+
+    if [ -z "$B64_DATA" ]; then
+        log_error "Google Gemini returned no image data"
+        echo "Response: $RESPONSE"
+        exit 1
+    fi
+
+    TMPFILE=$(mktemp /tmp/clawra-gemini-XXXXXX."$OUTPUT_FORMAT")
+    echo "$B64_DATA" | base64 -d > "$TMPFILE"
+    IMAGE_URL="$TMPFILE"
+    log_info "Saved to temp file: $TMPFILE"
+
+    REVISED_PROMPT=""
+}
+
+# ============================================================================
+# Provider: x.ai direct (grok-imagine-image)
+# ============================================================================
+generate_xai() {
+    if [ -z "${XAI_API_KEY:-}" ]; then
+        log_error "XAI_API_KEY environment variable not set"
+        echo "Get your API key from: https://console.x.ai"
+        exit 1
+    fi
+
+    RESPONSE=$(curl -s -X POST "https://api.x.ai/v1/images/generations" \
+        -H "Authorization: Bearer $XAI_API_KEY" \
+        -H "Content-Type: application/json" \
+        -d "{
+            \"model\": \"grok-imagine-image\",
+            \"prompt\": $(echo "$PROMPT" | jq -Rs .),
+            \"n\": 1
+        }")
+
+    if echo "$RESPONSE" | jq -e '.error' > /dev/null 2>&1; then
+        ERROR_MSG=$(echo "$RESPONSE" | jq -r '.error.message // .error // "Unknown error"')
+        log_error "x.ai image generation failed: $ERROR_MSG"
+        exit 1
+    fi
+
+    IMAGE_URL=$(echo "$RESPONSE" | jq -r '.data[0].url // empty')
+    REVISED_PROMPT=""
+}
+
+# ============================================================================
+# Route to the correct provider
+# ============================================================================
+IMAGE_URL=""
+REVISED_PROMPT=""
+
+case "$PROVIDER" in
+    fal)    generate_fal ;;
+    openai) generate_openai ;;
+    google) generate_google ;;
+    xai)    generate_xai ;;
+    *)
+        log_error "Unknown provider: $PROVIDER"
+        echo "Supported providers: fal, openai, google, xai"
+        exit 1
+        ;;
+esac
+
+# Validate result
 if [ -z "$IMAGE_URL" ]; then
     log_error "Failed to extract image URL from response"
-    echo "Response: $RESPONSE"
     exit 1
 fi
 
 log_info "Image generated successfully!"
 log_info "URL: $IMAGE_URL"
 
-# Get revised prompt if available
-REVISED_PROMPT=$(echo "$RESPONSE" | jq -r '.revised_prompt // empty')
 if [ -n "$REVISED_PROMPT" ]; then
     log_info "Revised prompt: $REVISED_PROMPT"
 fi
@@ -118,22 +287,15 @@ fi
 log_info "Sending to channel: $CHANNEL"
 
 if [ "$USE_CLI" = true ]; then
-    # Use OpenClaw CLI
     openclaw message send \
         --action send \
         --channel "$CHANNEL" \
         --message "$CAPTION" \
         --media "$IMAGE_URL"
 else
-    # Direct API call to local gateway
     GATEWAY_URL="${OPENCLAW_GATEWAY_URL:-http://localhost:18789}"
     GATEWAY_TOKEN="${OPENCLAW_GATEWAY_TOKEN:-}"
 
-    HEADERS="-H \"Content-Type: application/json\""
-    if [ -n "$GATEWAY_TOKEN" ]; then
-        HEADERS="$HEADERS -H \"Authorization: Bearer $GATEWAY_TOKEN\""
-    fi
-
     curl -s -X POST "$GATEWAY_URL/message" \
         -H "Content-Type: application/json" \
         ${GATEWAY_TOKEN:+-H "Authorization: Bearer $GATEWAY_TOKEN"} \
@@ -154,9 +316,11 @@ jq -n \
     --arg url "$IMAGE_URL" \
     --arg channel "$CHANNEL" \
     --arg prompt "$PROMPT" \
+    --arg provider "$PROVIDER" \
     '{
         success: true,
         image_url: $url,
         channel: $channel,
-        prompt: $prompt
+        prompt: $prompt,
+        provider: $provider
     }'
diff --git a/scripts/clawra-selfie.ts b/scripts/clawra-selfie.ts
index e15f644a..4b336910 100644
--- a/scripts/clawra-selfie.ts
+++ b/scripts/clawra-selfie.ts
@@ -1,43 +1,45 @@
 /**
- * Grok Imagine to OpenClaw Integration
+ * Clawra Selfie – Multi-Provider Image Generation & Editing
  *
- * Generates images using xAI's Grok Imagine model via fal.ai
- * and sends them to messaging channels via OpenClaw.
+ * Generates or edits images using multiple AI providers and sends them
+ * to messaging channels via OpenClaw.
+ *
+ * Supported providers (set via IMAGE_PROVIDER env var):
+ *   - fal    (fal.ai / Grok Imagine)    – requires FAL_KEY
+ *   - openai (OpenAI gpt-image-1)       – requires OPENAI_API_KEY
+ *   - google (Google Gemini)             – requires GEMINI_API_KEY
+ *   - xai    (x.ai direct)              – requires XAI_API_KEY
  *
  * Usage:
- *   npx ts-node grok-imagine-send.ts "<prompt>" "<channel>" ["<caption>"]
+ *   npx ts-node clawra-selfie.ts <prompt> <channel> [caption] [aspect_ratio] [output_format] [provider]
  *
  * Environment variables:
- *   FAL_KEY - Your fal.ai API key
- *   OPENCLAW_GATEWAY_URL - OpenClaw gateway URL (default: http://localhost:18789)
- *   OPENCLAW_GATEWAY_TOKEN - Gateway auth token (optional)
+ *   IMAGE_PROVIDER             - Provider to use (default: fal)
+ *   FAL_KEY / OPENAI_API_KEY / GEMINI_API_KEY / XAI_API_KEY
+ *   OPENCLAW_GATEWAY_URL       - OpenClaw gateway URL (default: http://localhost:18789)
+ *   OPENCLAW_GATEWAY_TOKEN     - Gateway auth token (optional)
  */
 
 import { exec } from "child_process";
 import { promisify } from "util";
 
+import {
+  getProvider,
+  PROVIDER_ENV_KEYS,
+  AVAILABLE_PROVIDERS,
+} from "./providers";
+import type {
+  AspectRatio,
+  OutputFormat,
+  ProviderName,
+  GenerateImageResult,
+} from "./providers";
+
 const execAsync = promisify(exec);
 
+// ---------------------------------------------------------------------------
 // Types
-interface GrokImagineInput {
-  prompt: string;
-  num_images?: number;
-  aspect_ratio?: AspectRatio;
-  output_format?: OutputFormat;
-}
-
-interface GrokImagineImage {
-  url: string;
-  content_type: string;
-  file_name?: string;
-  width: number;
-  height: number;
-}
-
-interface GrokImagineResponse {
-  images: GrokImagineImage[];
-  revised_prompt?: string;
-}
+// ---------------------------------------------------------------------------
 
 interface OpenClawMessage {
   action: "send";
@@ -46,29 +48,13 @@ interface OpenClawMessage {
   media?: string;
 }
 
-type AspectRatio =
-  | "2:1"
-  | "20:9"
-  | "19.5:9"
-  | "16:9"
-  | "4:3"
-  | "3:2"
-  | "1:1"
-  | "2:3"
-  | "3:4"
-  | "9:16"
-  | "9:19.5"
-  | "9:20"
-  | "1:2";
-
-type OutputFormat = "jpeg" | "png" | "webp";
-
 interface GenerateAndSendOptions {
   prompt: string;
   channel: string;
   caption?: string;
   aspectRatio?: AspectRatio;
   outputFormat?: OutputFormat;
+  provider?: ProviderName;
   useClaudeCodeCLI?: boolean;
 }
 
@@ -77,87 +63,24 @@ interface Result {
   imageUrl: string;
   channel: string;
   prompt: string;
+  provider: string;
   revisedPrompt?: string;
 }
 
-// Check for fal.ai client
-let falClient: any;
-try {
-  const { fal } = require("@fal-ai/client");
-  falClient = fal;
-} catch {
-  // Will use fetch instead
-  falClient = null;
-}
-
-/**
- * Generate image using Grok Imagine via fal.ai
- */
-async function generateImage(
-  input: GrokImagineInput
-): Promise<GrokImagineResponse> {
-  const falKey = process.env.FAL_KEY;
-
-  if (!falKey) {
-    throw new Error(
-      "FAL_KEY environment variable not set. Get your key from https://fal.ai/dashboard/keys"
-    );
-  }
-
-  // Use fal client if available
-  if (falClient) {
-    falClient.config({ credentials: falKey });
-
-    const result = await falClient.subscribe("xai/grok-imagine-image", {
-      input: {
-        prompt: input.prompt,
-        num_images: input.num_images || 1,
-        aspect_ratio: input.aspect_ratio || "1:1",
-        output_format: input.output_format || "jpeg",
-      },
-    });
-
-    return result.data as GrokImagineResponse;
-  }
-
-  // Fallback to fetch
-  const response = await fetch("https://fal.run/xai/grok-imagine-image", {
-    method: "POST",
-    headers: {
-      Authorization: `Key ${falKey}`,
-      "Content-Type": "application/json",
-    },
-    body: JSON.stringify({
-      prompt: input.prompt,
-      num_images: input.num_images || 1,
-      aspect_ratio: input.aspect_ratio || "1:1",
-      output_format: input.output_format || "jpeg",
-    }),
-  });
-
-  if (!response.ok) {
-    const error = await response.text();
-    throw new Error(`Image generation failed: ${error}`);
-  }
+// ---------------------------------------------------------------------------
+// OpenClaw integration
+// ---------------------------------------------------------------------------
 
-  return response.json();
-}
-
-/**
- * Send image via OpenClaw
- */
 async function sendViaOpenClaw(
   message: OpenClawMessage,
   useCLI: boolean = true
 ): Promise<void> {
   if (useCLI) {
-    // Use OpenClaw CLI
     const cmd = `openclaw message send --action send --channel "${message.channel}" --message "${message.message}" --media "${message.media}"`;
     await execAsync(cmd);
     return;
   }
 
-  // Direct API call
   const gatewayUrl =
     process.env.OPENCLAW_GATEWAY_URL || "http://localhost:18789";
   const gatewayToken = process.env.OPENCLAW_GATEWAY_TOKEN;
@@ -182,36 +105,43 @@ async function sendViaOpenClaw(
   }
 }
 
-/**
- * Main function: Generate image and send to channel
- */
-async function generateAndSend(options: GenerateAndSendOptions): Promise<Result> {
+// ---------------------------------------------------------------------------
+// Main logic
+// ---------------------------------------------------------------------------
+
+async function generateAndSend(
+  options: GenerateAndSendOptions
+): Promise<Result> {
   const {
     prompt,
     channel,
-    caption = "Generated with Grok Imagine",
+    caption = "Generated with Clawra",
     aspectRatio = "1:1",
     outputFormat = "jpeg",
+    provider: providerName,
     useClaudeCodeCLI = true,
   } = options;
 
-  console.log(`[INFO] Generating image with Grok Imagine...`);
+  // Resolve provider
+  const provider = getProvider(providerName);
+  console.log(`[INFO] Provider: ${provider.name}`);
+  console.log(`[INFO] Generating image...`);
   console.log(`[INFO] Prompt: ${prompt}`);
   console.log(`[INFO] Aspect ratio: ${aspectRatio}`);
 
   // Generate image
-  const imageResult = await generateImage({
+  const imageResult: GenerateImageResult = await provider.generateImage({
     prompt,
-    num_images: 1,
-    aspect_ratio: aspectRatio,
-    output_format: outputFormat,
+    numImages: 1,
+    aspectRatio,
+    outputFormat,
   });
 
   const imageUrl = imageResult.images[0].url;
   console.log(`[INFO] Image generated: ${imageUrl}`);
 
-  if (imageResult.revised_prompt) {
-    console.log(`[INFO] Revised prompt: ${imageResult.revised_prompt}`);
+  if (imageResult.revisedPrompt) {
+    console.log(`[INFO] Revised prompt: ${imageResult.revisedPrompt}`);
   }
 
   // Send via OpenClaw
@@ -234,35 +164,42 @@ async function generateAndSend(options: GenerateAndSendOptions): Promise<Result>
     imageUrl,
     channel,
     prompt,
-    revisedPrompt: imageResult.revised_prompt,
+    provider: provider.name,
+    revisedPrompt: imageResult.revisedPrompt,
   };
 }
 
+// ---------------------------------------------------------------------------
 // CLI entry point
+// ---------------------------------------------------------------------------
+
 async function main() {
   const args = process.argv.slice(2);
 
   if (args.length < 2) {
     console.log(`
-Usage: npx ts-node grok-imagine-send.ts <prompt> <channel> [caption] [aspect_ratio] [output_format]
+Usage: npx ts-node clawra-selfie.ts <prompt> <channel> [caption] [aspect_ratio] [output_format] [provider]
 
 Arguments:
   prompt        - Image description (required)
   channel       - Target channel (required) e.g., #general, @user
-  caption       - Message caption (default: 'Generated with Grok Imagine')
+  caption       - Message caption (default: 'Generated with Clawra')
   aspect_ratio  - Image ratio (default: 1:1) Options: 2:1, 16:9, 4:3, 1:1, 3:4, 9:16
   output_format - Image format (default: jpeg) Options: jpeg, png, webp
+  provider      - Image provider (default: fal) Options: ${AVAILABLE_PROVIDERS.join(", ")}
 
 Environment:
-  FAL_KEY       - Your fal.ai API key (required)
+  IMAGE_PROVIDER   - Default provider (overridden by provider argument)
+${AVAILABLE_PROVIDERS.map((p) => `  ${PROVIDER_ENV_KEYS[p].padEnd(17)}- Required for provider: ${p}`).join("\n")}
 
 Example:
-  FAL_KEY=your_key npx ts-node grok-imagine-send.ts "A cyberpunk city" "#art" "Check this out!"
+  FAL_KEY=xxx npx ts-node clawra-selfie.ts "A cyberpunk city" "#art" "Check this!"
+  IMAGE_PROVIDER=openai OPENAI_API_KEY=xxx npx ts-node clawra-selfie.ts "A sunset" "#photos"
 `);
     process.exit(1);
   }
 
-  const [prompt, channel, caption, aspectRatio, outputFormat] = args;
+  const [prompt, channel, caption, aspectRatio, outputFormat, provider] = args;
 
   try {
     const result = await generateAndSend({
@@ -271,6 +208,7 @@ Example:
       caption,
       aspectRatio: aspectRatio as AspectRatio,
       outputFormat: outputFormat as OutputFormat,
+      provider: provider as ProviderName,
     });
 
     console.log("\n--- Result ---");
@@ -283,11 +221,8 @@ Example:
 
 // Export for module use
 export {
-  generateImage,
   sendViaOpenClaw,
   generateAndSend,
-  GrokImagineInput,
-  GrokImagineResponse,
   OpenClawMessage,
   GenerateAndSendOptions,
   Result,
diff --git a/scripts/providers/fal.ts b/scripts/providers/fal.ts
new file mode 100644
index 00000000..14f8db32
--- /dev/null
+++ b/scripts/providers/fal.ts
@@ -0,0 +1,103 @@
+/**
+ * fal.ai provider – proxies xAI Grok Imagine via fal.ai.
+ *
+ * Env: FAL_KEY
+ */
+
+import type {
+    ImageProvider,
+    GenerateImageInput,
+    EditImageInput,
+    GenerateImageResult,
+} from "./types";
+
+const FAL_BASE = "https://fal.run/xai/grok-imagine-image";
+
+export class FalProvider implements ImageProvider {
+    readonly name = "fal.ai (Grok Imagine)";
+    readonly id = "fal" as const;
+
+    private getKey(): string {
+        const key = process.env.FAL_KEY;
+        if (!key) {
+            throw new Error(
+                "FAL_KEY environment variable not set. Get your key from https://fal.ai/dashboard/keys"
+            );
+        }
+        return key;
+    }
+
+    async generateImage(input: GenerateImageInput): Promise<GenerateImageResult> {
+        const key = this.getKey();
+
+        const response = await fetch(FAL_BASE, {
+            method: "POST",
+            headers: {
+                Authorization: `Key ${key}`,
+                "Content-Type": "application/json",
+            },
+            body: JSON.stringify({
+                prompt: input.prompt,
+                num_images: input.numImages ?? 1,
+                aspect_ratio: input.aspectRatio ?? "1:1",
+                output_format: input.outputFormat ?? "jpeg",
+            }),
+        });
+
+        if (!response.ok) {
+            const error = await response.text();
+            throw new Error(`fal.ai image generation failed: ${error}`);
+        }
+
+        const data = (await response.json()) as {
+            images: Array<{ url: string; width: number; height: number }>;
+            revised_prompt?: string;
+        };
+
+        return {
+            images: data.images.map((img) => ({
+                url: img.url,
+                width: img.width,
+                height: img.height,
+            })),
+            revisedPrompt: data.revised_prompt,
+        };
+    }
+
+    async editImage(input: EditImageInput): Promise<GenerateImageResult> {
+        const key = this.getKey();
+
+        const response = await fetch(`${FAL_BASE}/edit`, {
+            method: "POST",
+            headers: {
+                Authorization: `Key ${key}`,
+                "Content-Type": "application/json",
+            },
+            body: JSON.stringify({
+                image_url: input.imageUrl,
+                prompt: input.prompt,
+                num_images: input.numImages ?? 1,
+                output_format: input.outputFormat ?? "jpeg",
+            }),
+        });
+
+        if (!response.ok) {
+            const error = await response.text();
+            throw new Error(`fal.ai image editing failed: ${error}`);
+        }
+
+        const data = (await response.json()) as {
+            images: Array<{ url: string; width: number; height: number }>;
+            revised_prompt?: string;
+        };
+
+        return {
+            images: data.images.map((img) => ({
+                url: img.url,
+                width: img.width,
+                height: img.height,
+            })),
+            revisedPrompt: data.revised_prompt,
+        };
+    }
+}
diff --git a/scripts/providers/google.ts b/scripts/providers/google.ts
new file mode 100644
index 00000000..ff91a75b
--- /dev/null
+++ b/scripts/providers/google.ts
@@ -0,0 +1,194 @@
+/**
+ * Google Gemini provider – uses Gemini's native image generation.
+ *
+ * Env: GEMINI_API_KEY
+ *
+ * Reference: https://ai.google.dev/gemini-api/docs/image-generation
+ *
+ * Uses the generateContent endpoint with responseModalities: ["IMAGE"]
+ * Response returns base64-encoded image data in inlineData parts.
+ */
+
+import * as fs from "fs";
+import * as os from "os";
+import * as path from "path";
+import type {
+    ImageProvider,
+    GenerateImageInput,
+    EditImageInput,
+    GenerateImageResult,
+} from "./types";
+
+const GEMINI_API_BASE =
+    "https://generativelanguage.googleapis.com/v1beta/models";
+
+export class GoogleProvider implements ImageProvider {
+    readonly name = "Google Gemini (gemini-2.5-flash-image)";
+    readonly id = "google" as const;
+
+    private model = "gemini-2.5-flash-image";
+
+    private getKey(): string {
+        const key = process.env.GEMINI_API_KEY;
+        if (!key) {
+            throw new Error(
+                "GEMINI_API_KEY environment variable not set. Get your key from https://aistudio.google.com/apikey"
+            );
+        }
+        return key;
+    }
+
+    private buildUrl(): string {
+        return `${GEMINI_API_BASE}/${this.model}:generateContent`;
+    }
+
+    /**
+     * Extract the first image from Gemini's generateContent response.
+     * The response may contain both text and image parts.
+     */
+    private extractImages(
+        responseData: GeminiResponse,
+        outputFormat: string
+    ): { url: string }[] {
+        const images: { url: string }[] = [];
+
+        for (const candidate of responseData.candidates ?? []) {
+            for (const part of candidate.content?.parts ?? []) {
+                if (part.inlineData?.data) {
+                    const ext =
+                        outputFormat === "png"
+                            ? "png"
+                            : outputFormat === "webp"
+                                ? "webp"
+                                : "jpeg";
+                    const tmpFile = path.join(
+                        os.tmpdir(),
+                        `clawra-gemini-${Date.now()}-${Math.random().toString(36).slice(2)}.${ext}`
+                    );
+                    fs.writeFileSync(
+                        tmpFile,
+                        Buffer.from(part.inlineData.data, "base64")
+                    );
+                    images.push({ url: tmpFile });
+                }
+            }
+        }
+
+        return images;
+    }
+
+    async generateImage(
+        input: GenerateImageInput
+    ): Promise<GenerateImageResult> {
+        const key = this.getKey();
+
+        const body = {
+            contents: [
+                {
+                    parts: [{ text: input.prompt }],
+                },
+            ],
+            generationConfig: {
+                responseModalities: ["IMAGE"],
+            },
+        };
+
+        const response = await fetch(`${this.buildUrl()}?key=${key}`, {
+            method: "POST",
+            headers: { "Content-Type": "application/json" },
+            body: JSON.stringify(body),
+        });
+
+        if (!response.ok) {
+            const error = await response.text();
+            throw new Error(`Google Gemini image generation failed: ${error}`);
+        }
+
+        const data = (await response.json()) as GeminiResponse;
+        const images = this.extractImages(data, input.outputFormat ?? "jpeg");
+
+        if (images.length === 0) {
+            throw new Error(
+                "Google Gemini returned no image data in the response"
+            );
+        }
+
+        return { images };
+    }
+
+    async editImage(input: EditImageInput): Promise<GenerateImageResult> {
+        const key = this.getKey();
+
+        // Fetch the reference image and encode as base64
+        const imageResponse = await fetch(input.imageUrl);
+        if (!imageResponse.ok) {
+            throw new Error(`Failed to fetch reference image: ${input.imageUrl}`);
+        }
+        const imageBuffer = Buffer.from(await imageResponse.arrayBuffer());
+        const imageBase64 = imageBuffer.toString("base64");
+
+        // Determine mime type from URL or default to jpeg
+        const mimeType = input.imageUrl.endsWith(".png")
+            ? "image/png"
+            : "image/jpeg";
+
+        const body = {
+            contents: [
+                {
+                    parts: [
+                        { text: input.prompt },
+                        {
+                            inlineData: {
+                                mimeType,
+                                data: imageBase64,
+                            },
+                        },
+                    ],
+                },
+            ],
+            generationConfig: {
+                responseModalities: ["IMAGE"],
+            },
+        };
+
+        const response = await fetch(`${this.buildUrl()}?key=${key}`, {
+            method: "POST",
+            headers: { "Content-Type": "application/json" },
+            body: JSON.stringify(body),
+        });
+
+        if (!response.ok) {
+            const error = await response.text();
+            throw new Error(`Google Gemini image editing failed: ${error}`);
+        }
+
+        const data = (await response.json()) as GeminiResponse;
+        const images = this.extractImages(data, input.outputFormat ?? "jpeg");
+
+        if (images.length === 0) {
+            throw new Error(
+                "Google Gemini returned no image data in the editing response"
+            );
+        }
+
+        return { images };
+    }
+}
+
+// ---------------------------------------------------------------------------
+// Gemini response types (subset)
+// ---------------------------------------------------------------------------
+
+interface GeminiResponse {
+    candidates?: Array<{
+        content?: {
+            parts?: Array<{
+                text?: string;
+                inlineData?: {
+                    mimeType?: string;
+                    data?: string;
+                };
+            }>;
+        };
+    }>;
+}
diff --git a/scripts/providers/index.ts b/scripts/providers/index.ts
new file mode 100644
index 00000000..2c52b4e8
--- /dev/null
+++ b/scripts/providers/index.ts
@@ -0,0 +1,63 @@
+/**
+ * Provider factory – returns the appropriate ImageProvider based on
+ * the IMAGE_PROVIDER environment variable or an explicit name.
+ *
+ * Supported values: fal | openai | google | xai
+ * Default: fal (backward-compatible)
+ */
+
+export type { ProviderName, ImageProvider, GenerateImageInput, EditImageInput, GenerateImageResult, GeneratedImage, AspectRatio, OutputFormat } from "./types";
+import type { ImageProvider, ProviderName } from "./types";
+
+import { FalProvider } from "./fal";
+import { OpenAIProvider } from "./openai";
+import { GoogleProvider } from "./google";
+import { XAIProvider } from "./xai";
+
+/**
+ * Create an ImageProvider instance.
+ *
+ * @param name  Provider identifier. If omitted, falls back to
+ *              `process.env.IMAGE_PROVIDER`, then defaults to `"fal"`.
+ */
+export function getProvider(name?: string): ImageProvider {
+    const providerName = (name || process.env.IMAGE_PROVIDER || "fal") as ProviderName;
+
+    switch (providerName) {
+        case "fal":
+            return new FalProvider();
+        case "openai":
+            return new OpenAIProvider();
+        case "google":
+            return new GoogleProvider();
+        case "xai":
+            return new XAIProvider();
+        default:
+            throw new Error(
+                `Unknown image provider: "${providerName}". ` +
+                `Supported providers: fal, openai, google, xai`
+            );
+    }
+}
+
+/** List all available provider identifiers */
+export const AVAILABLE_PROVIDERS: ProviderName[] = [
+    "fal",
+    "openai",
+    "google",
+    "xai",
+];
+
+/** Map of provider → required environment variable */
+export const PROVIDER_ENV_KEYS: Record<ProviderName, string> = {
+    fal: "FAL_KEY",
+    openai: "OPENAI_API_KEY",
+    google: "GEMINI_API_KEY",
+    xai: "XAI_API_KEY",
+};
+
+// Re-export provider classes for direct use
+export { FalProvider } from "./fal";
+export { OpenAIProvider } from "./openai";
+export { GoogleProvider } from "./google";
+export { XAIProvider } from "./xai";
diff --git a/scripts/providers/openai.ts b/scripts/providers/openai.ts
new file mode 100644
index 00000000..e471aed5
--- /dev/null
+++ b/scripts/providers/openai.ts
@@ -0,0 +1,125 @@
+/**
+ * OpenAI provider – uses the Images API (gpt-image-1).
+ *
+ * Env: OPENAI_API_KEY
+ *
+ * Reference: https://developers.openai.com/api/reference/resources/images/methods/generate
+ *
+ * Note: gpt-image-1 returns base64-encoded images. We convert them to data URIs
+ * so they can be passed downstream (e.g. to OpenClaw) the same way as URLs.
+ * If the caller needs a file, they can decode the base64 from the data URI.
+ */
+
+import * as fs from "fs";
+import * as os from "os";
+import * as path from "path";
+import type {
+    ImageProvider,
+    GenerateImageInput,
+    GenerateImageResult,
+    AspectRatio,
+} from "./types";
+
+const OPENAI_API_URL = "https://api.openai.com/v1/images/generations";
+
+/** Map our aspect ratios to the closest OpenAI size preset */
+function aspectRatioToSize(ar?: AspectRatio): string {
+    switch (ar) {
+        case "16:9":
+        case "2:1":
+        case "20:9":
+        case "19.5:9":
+        case "3:2":
+            return "1536x1024"; // landscape
+        case "9:16":
+        case "1:2":
+        case "9:19.5":
+        case "9:20":
+        case "2:3":
+        case "3:4":
+            return "1024x1536"; // portrait
+        case "4:3":
+        case "1:1":
+        default:
+            return "1024x1024"; // square
+    }
+}
+
+export class OpenAIProvider implements ImageProvider {
+    readonly name = "OpenAI (gpt-image-1)";
+    readonly id = "openai" as const;
+
+    private getKey(): string {
+        const key = process.env.OPENAI_API_KEY;
+        if (!key) {
+            throw new Error(
+                "OPENAI_API_KEY environment variable not set. Get your key from https://platform.openai.com/api-keys"
+            );
+        }
+        return key;
+    }
+
+    async generateImage(input: GenerateImageInput): Promise<GenerateImageResult> {
+        const key = this.getKey();
+        const size = aspectRatioToSize(input.aspectRatio);
+
+        const body: Record<string, unknown> = {
+            model: "gpt-image-1",
+            prompt: input.prompt,
+            n: input.numImages ?? 1,
+            size,
+        };
+
+        if (input.outputFormat) {
+            body.output_format = input.outputFormat;
+        }
+
+        const response = await fetch(OPENAI_API_URL, {
+            method: "POST",
+            headers: {
+                Authorization: `Bearer ${key}`,
+                "Content-Type": "application/json",
+            },
+            body: JSON.stringify(body),
+        });
+
+        if (!response.ok) {
+            const error = await response.text();
+            throw new Error(`OpenAI image generation failed: ${error}`);
+        }
+
+        const data = (await response.json()) as {
+            data: Array<{ b64_json?: string; url?: string; revised_prompt?: string }>;
+        };
+
+        // Convert base64 images to temporary files so we get usable URLs
+        const images = await Promise.all(
+            data.data.map(async (item) => {
+                if (item.url) {
+                    return { url: item.url };
+                }
+                if (item.b64_json) {
+                    const ext = input.outputFormat ?? "png";
+                    const tmpFile = path.join(
+                        os.tmpdir(),
+                        `clawra-openai-${Date.now()}-${Math.random().toString(36).slice(2)}.${ext}`
+                    );
+                    fs.writeFileSync(tmpFile, Buffer.from(item.b64_json, "base64"));
+                    return { url: tmpFile };
+                }
+                throw new Error("OpenAI response contained neither url nor b64_json");
+            })
+        );
+
+        const revisedPrompt = data.data[0]?.revised_prompt;
+
+        return {
+            images,
+            revisedPrompt: revisedPrompt ?? undefined,
+        };
+    }
+
+    // OpenAI Images API does support image editing via /v1/images/edits,
+    // but it uses multipart/form-data which is more complex.
+    // For now we only expose text-to-image generation.
+}
diff --git a/scripts/providers/types.ts b/scripts/providers/types.ts
new file mode 100644
index 00000000..2a7c834e
--- /dev/null
+++ b/scripts/providers/types.ts
@@ -0,0 +1,88 @@
+/**
+ * Multi-provider image generation types and interfaces.
+ *
+ * Supported providers:
+ *   - fal   (fal.ai / Grok Imagine)
+ *   - openai (OpenAI gpt-image-1)
+ *   - google (Google Gemini gemini-2.5-flash-image)
+ *   - xai   (x.ai direct / grok-imagine-image)
+ */
+
+// ---------------------------------------------------------------------------
+// Input types
+// ---------------------------------------------------------------------------
+
+export type AspectRatio =
+    | "2:1"
+    | "20:9"
+    | "19.5:9"
+    | "16:9"
+    | "4:3"
+    | "3:2"
+    | "1:1"
+    | "2:3"
+    | "3:4"
+    | "9:16"
+    | "9:19.5"
+    | "9:20"
+    | "1:2";
+
+export type OutputFormat = "jpeg" | "png" | "webp";
+
+export interface GenerateImageInput {
+    /** Text prompt describing the image to generate */
+    prompt: string;
+    /** Number of images to generate (default: 1) */
+    numImages?: number;
+    /** Aspect ratio of the output image */
+    aspectRatio?: AspectRatio;
+    /** Output image format */
+    outputFormat?: OutputFormat;
+}
+
+export interface EditImageInput extends GenerateImageInput {
+    /** URL of the reference / source image to edit */
+    imageUrl: string;
+}
+
+// ---------------------------------------------------------------------------
+// Output types
+// ---------------------------------------------------------------------------
+
+export interface GeneratedImage {
+    /** URL of the generated image (may be a temporary URL or data URI) */
+    url: string;
+    /** Image width in pixels (if known) */
+    width?: number;
+    /** Image height in pixels (if known) */
+    height?: number;
+}
+
+export interface GenerateImageResult {
+    /** Array of generated images */
+    images: GeneratedImage[];
+    /** Revised / enhanced prompt returned by the model (if any) */
+    revisedPrompt?: string;
+}
+
+// ---------------------------------------------------------------------------
+// Provider interface
+// ---------------------------------------------------------------------------
+
+export type ProviderName = "fal" | "openai" | "google" | "xai";
+
+export interface ImageProvider {
+    /** Human-readable provider name */
+    readonly name: string;
+    /** Provider identifier */
+    readonly id: ProviderName;
+
+    /** Generate an image from a text prompt */
+    generateImage(input: GenerateImageInput): Promise<GenerateImageResult>;
+
+    /**
+     * Edit / transform an existing image with a text prompt.
+     * Not all providers support this; callers should check before calling.
+     */
+    editImage?(input: EditImageInput): Promise<GenerateImageResult>;
+}
diff --git a/scripts/providers/xai.ts b/scripts/providers/xai.ts
new file mode 100644
index 00000000..917fc7c5
--- /dev/null
+++ b/scripts/providers/xai.ts
@@ -0,0 +1,113 @@
+/**
+ * x.ai direct provider – calls x.ai API directly (no fal.ai proxy).
+ *
+ * Env: XAI_API_KEY
+ *
+ * Reference: https://docs.x.ai/developers/model-capabilities/images/generation
+ *
+ * Uses the OpenAI-compatible endpoint at api.x.ai with model grok-imagine-image.
+ * For image editing, sends image_url in the request body (application/json).
+ */
+
+import type {
+    ImageProvider,
+    GenerateImageInput,
+    EditImageInput,
+    GenerateImageResult,
+} from "./types";
+
+const XAI_API_URL = "https://api.x.ai/v1/images/generations";
+
+export class XAIProvider implements ImageProvider {
+    readonly name = "x.ai (Grok Imagine Direct)";
+    readonly id = "xai" as const;
+
+    private getKey(): string {
+        const key = process.env.XAI_API_KEY;
+        if (!key) {
+            throw new Error(
+                "XAI_API_KEY environment variable not set. Get your key from https://console.x.ai"
+            );
+        }
+        return key;
+    }
+
+    async generateImage(input: GenerateImageInput): Promise<GenerateImageResult> {
+        const key = this.getKey();
+
+        const body: Record<string, unknown> = {
+            model: "grok-imagine-image",
+            prompt: input.prompt,
+            n: input.numImages ?? 1,
+        };
+
+        if (input.aspectRatio) {
+            body.aspect_ratio = input.aspectRatio;
+        }
+
+        const response = await fetch(XAI_API_URL, {
+            method: "POST",
+            headers: {
+                Authorization: `Bearer ${key}`,
+                "Content-Type": "application/json",
+            },
+            body: JSON.stringify(body),
+        });
+
+        if (!response.ok) {
+            const error = await response.text();
+            throw new Error(`x.ai image generation failed: ${error}`);
+        }
+
+        const data = (await response.json()) as XAIImageResponse;
+
+        return {
+            images: data.data.map((item) => ({ url: item.url })),
+        };
+    }
+
+    async editImage(input: EditImageInput): Promise<GenerateImageResult> {
+        const key = this.getKey();
+
+        const body: Record<string, unknown> = {
+            model: "grok-imagine-image",
+            prompt: input.prompt,
+            n: input.numImages ?? 1,
+            image_url: input.imageUrl,
+        };
+
+        if (input.aspectRatio) {
+            body.aspect_ratio = input.aspectRatio;
+        }
+
+        const response = await fetch(XAI_API_URL, {
+            method: "POST",
+            headers: {
+                Authorization: `Bearer ${key}`,
+                "Content-Type": "application/json",
+            },
+            body: JSON.stringify(body),
+        });
+
+        if (!response.ok) {
+            const error = await response.text();
+            throw new Error(`x.ai image editing failed: ${error}`);
+        }
+
+        const data = (await response.json()) as XAIImageResponse;
+
+        return {
+            images: data.data.map((item) => ({ url: item.url })),
+        };
+    }
+}
+
+// ---------------------------------------------------------------------------
+// x.ai response types
+// ---------------------------------------------------------------------------
+
+interface XAIImageResponse {
+    data: Array<{
+        url: string;
+    }>;
+}
diff --git a/skill/SKILL.md b/skill/SKILL.md
index c09ce1db..d85beb3c 100644
--- a/skill/SKILL.md
+++ b/skill/SKILL.md
@@ -1,12 +1,23 @@
 ---
 name: clawra-selfie
-description: Edit Clawra's reference image with Grok Imagine (xAI Aurora) and send selfies to messaging channels via OpenClaw
+description: Generate and edit images using multiple AI providers (fal.ai, OpenAI, Google Gemini, x.ai) and send selfies to messaging channels via OpenClaw
 allowed-tools: Bash(npm:*) Bash(npx:*) Bash(openclaw:*) Bash(curl:*) Read Write WebFetch
 ---
 
 # Clawra Selfie
 
-Edit a fixed reference image using xAI's Grok Imagine model and distribute it across messaging platforms (WhatsApp, Telegram, Discord, Slack, etc.) via OpenClaw.
+Generate and edit images using multiple AI providers and distribute them across messaging platforms (WhatsApp, Telegram, Discord, Slack, etc.) via OpenClaw.
+
+## Supported Providers
+
+| Provider | Model | Env Variable | API Key URL |
+|----------|-------|-------------|-------------|
+| **fal** (default) | Grok Imagine (via fal.ai) | `FAL_KEY` | https://fal.ai/dashboard/keys |
+| **openai** | gpt-image-1 | `OPENAI_API_KEY` | https://platform.openai.com/api-keys |
+| **google** | gemini-2.5-flash-image | `GEMINI_API_KEY` | https://aistudio.google.com/apikey |
+| **xai** | grok-imagine-image (direct) | `XAI_API_KEY` | https://console.x.ai |
+
+Set the provider via the `IMAGE_PROVIDER` environment variable (default: `fal`).
 
 ## Reference Image
 
@@ -29,16 +40,24 @@ https://cdn.jsdelivr.net/gh/SumeLabs/clawra@main/assets/clawra.png
 ### Required Environment Variables
 
 ```bash
-FAL_KEY=your_fal_api_key          # Get from https://fal.ai/dashboard/keys
+# Pick ONE provider and set its API key:
+IMAGE_PROVIDER=fal               # Options: fal, openai, google, xai (default: fal)
+
+FAL_KEY=your_fal_api_key          # For provider: fal
+OPENAI_API_KEY=your_openai_key    # For provider: openai
+GEMINI_API_KEY=your_gemini_key    # For provider: google
+XAI_API_KEY=your_xai_key          # For provider: xai
+
 OPENCLAW_GATEWAY_TOKEN=your_token  # From: openclaw doctor --generate-gateway-token
 ```
 
 ### Workflow
 
 1. **Get user prompt** for how to edit the image
-2. **Edit image** via fal.ai Grok Imagine Edit API with fixed reference
-3. **Extract image URL** from response
-4. **Send to OpenClaw** with target channel(s)
+2. **Select provider** (from env var or default)
+3. **Generate/edit image** via selected provider
+4. **Extract image URL** from response
+5. **Send to OpenClaw** with target channel(s)
 
 ## Step-by-Step Instructions
 
@@ -49,6 +68,7 @@ Ask the user for:
 - **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)
+- **Provider** (optional): Which image provider to use?
 
 ## Prompt Modes
 
@@ -85,20 +105,13 @@ a close-up selfie taken by herself at a cozy cafe with warm lighting, direct eye
 | close-up, portrait, face, eyes, smile | `direct` |
 | full-body, mirror, reflection | `mirror` |
 
-### Step 2: Edit Image with Grok Imagine
+### Step 2: Generate/Edit Image
 
-Use the fal.ai API to edit the reference image:
+#### Provider: fal.ai (default)
 
 ```bash
 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 "$PROMPT" \
@@ -110,24 +123,114 @@ curl -X POST "https://fal.run/xai/grok-imagine-image/edit" \
   -d "$JSON_PAYLOAD"
 ```
 
-**Response Format:**
+**Response:**
 ```json
 {
-  "images": [
-    {
-      "url": "https://v3b.fal.media/files/...",
-      "content_type": "image/jpeg",
-      "width": 1024,
-      "height": 1024
-    }
-  ],
+  "images": [{ "url": "https://v3b.fal.media/files/...", "width": 1024, "height": 1024 }],
   "revised_prompt": "Enhanced prompt text..."
 }
 ```
 
+#### Provider: OpenAI
+
+```bash
+curl -X POST "https://api.openai.com/v1/images/generations" \
+  -H "Authorization: Bearer $OPENAI_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "gpt-image-1",
+    "prompt": "A cute cat wearing a hat",
+    "n": 1,
+    "size": "1024x1024"
+  }'
+```
+
+**Response:**
+```json
+{
+  "data": [{ "b64_json": "..." }]
+}
+```
+
+> Note: OpenAI gpt-image-1 returns base64-encoded images. Save the `b64_json` field to a file.
+
+#### Provider: Google Gemini
+
+```bash
+curl -s -X POST \
+  "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:generateContent?key=$GEMINI_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "contents": [{"parts": [{"text": "A cute cat wearing a hat"}]}],
+    "generationConfig": {"responseModalities": ["IMAGE"]}
+  }'
+```
+
+**Response:**
+```json
+{
+  "candidates": [{
+    "content": {
+      "parts": [{ "inlineData": { "mimeType": "image/png", "data": "<BASE64>" } }]
+    }
+  }]
+}
+```
+
+> Note: Google Gemini returns base64 inline data. Decode the `data` field and save to a file.
+
+For image editing with Gemini, include the reference image as an `inlineData` part:
+```bash
+curl -s -X POST \
+  "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:generateContent?key=$GEMINI_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d "{
+    \"contents\": [{
+      \"parts\": [
+        {\"text\": \"Edit this person to be wearing a santa hat\"},
+        {\"inlineData\": {\"mimeType\": \"image/jpeg\", \"data\": \"<BASE64_IMAGE_DATA>\"}}
+      ]
+    }],
+    \"generationConfig\": {\"responseModalities\": [\"IMAGE\"]}
+  }"
+```
+
+#### Provider: x.ai (direct)
+
+```bash
+curl -X POST "https://api.x.ai/v1/images/generations" \
+  -H "Authorization: Bearer $XAI_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "grok-imagine-image",
+    "prompt": "A cute cat wearing a hat",
+    "n": 1
+  }'
+```
+
+For image editing, add `image_url`:
+```bash
+curl -X POST "https://api.x.ai/v1/images/generations" \
+  -H "Authorization: Bearer $XAI_API_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "grok-imagine-image",
+    "prompt": "Edit this to wear a santa hat",
+    "n": 1,
+    "image_url": "https://example.com/photo.jpg"
+  }'
+```
+
+**Response:**
+```json
+{
+  "data": [{ "url": "https://..." }]
+}
+```
+
 ### Step 3: Send Image via OpenClaw
 
-Use the OpenClaw messaging API to send the edited image:
+Use the OpenClaw messaging API to send the generated image:
 
 ```bash
 openclaw message send \
@@ -154,191 +257,69 @@ curl -X POST "http://localhost:18789/message" \
 
 ```bash
 #!/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"
+# Multi-provider image generation and send
 
+PROVIDER="${IMAGE_PROVIDER:-fal}"
 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!"
+CAPTION="${3:-Generated with Clawra}"
+
+# Route to provider
+case "$PROVIDER" in
+  fal)
+    curl -s -X POST "https://fal.run/xai/grok-imagine-image" \
+      -H "Authorization: Key $FAL_KEY" \
+      -H "Content-Type: application/json" \
+      -d "{\"prompt\": \"$USER_CONTEXT\", \"num_images\": 1}"
+    ;;
+  openai)
+    curl -s -X POST "https://api.openai.com/v1/images/generations" \
+      -H "Authorization: Bearer $OPENAI_API_KEY" \
+      -H "Content-Type: application/json" \
+      -d "{\"model\": \"gpt-image-1\", \"prompt\": \"$USER_CONTEXT\", \"n\": 1, \"size\": \"1024x1024\"}"
+    ;;
+  google)
+    curl -s -X POST \
+      "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image:generateContent?key=$GEMINI_API_KEY" \
+      -H "Content-Type: application/json" \
+      -d "{\"contents\": [{\"parts\": [{\"text\": \"$USER_CONTEXT\"}]}], \"generationConfig\": {\"responseModalities\": [\"IMAGE\"]}}"
+    ;;
+  xai)
+    curl -s -X POST "https://api.x.ai/v1/images/generations" \
+      -H "Authorization: Bearer $XAI_API_KEY" \
+      -H "Content-Type: application/json" \
+      -d "{\"model\": \"grok-imagine-image\", \"prompt\": \"$USER_CONTEXT\", \"n\": 1}"
+    ;;
+esac
 ```
 
+For the full implementation with error handling, mode detection, and OpenClaw integration, see the scripts in `scripts/clawra-selfie.sh` or `scripts/clawra-selfie.ts`.
+
 ## Node.js/TypeScript Implementation
 
 ```typescript
-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!
+import { getProvider } from "./providers";
+
+// Generate image with any provider
+const provider = getProvider("openai"); // or "fal", "google", "xai"
+const result = await provider.generateImage({
+  prompt: "A sunset over the ocean",
+  numImages: 1,
+  aspectRatio: "16:9",
+  outputFormat: "jpeg",
+});
+
+console.log(result.images[0].url);
+
+// Edit image (fal, google, xai support editing)
+if (provider.editImage) {
+  const edited = await provider.editImage({
+    imageUrl: "https://example.com/photo.jpg",
+    prompt: "Add a santa hat",
+    numImages: 1,
   });
-
-  // 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;
+  console.log(edited.images[0].url);
 }
-
-// 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");
 ```
 
 ## Supported Platforms
@@ -354,20 +335,51 @@ OpenClaw supports sending to:
 | Signal | Phone number | `+1234567890` |
 | MS Teams | Channel reference | (varies) |
 
-## Grok Imagine Edit Parameters
+## Provider-Specific Parameters
+
+### fal.ai (Grok Imagine)
 
 | Parameter | Type | Default | Description |
 |-----------|------|---------|-------------|
-| `image_url` | string | required | URL of image to edit (fixed in this skill) |
-| `prompt` | string | required | Edit instruction |
+| `image_url` | string | - | URL of image to edit |
+| `prompt` | string | required | Generation/edit instruction |
 | `num_images` | 1-4 | 1 | Number of images to generate |
+| `aspect_ratio` | enum | "1:1" | 2:1, 16:9, 4:3, 1:1, 3:4, 9:16 |
 | `output_format` | enum | "jpeg" | jpeg, png, webp |
 
+### OpenAI (gpt-image-1)
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `model` | string | "gpt-image-1" | Model to use |
+| `prompt` | string | required | Image description |
+| `n` | 1-10 | 1 | Number of images |
+| `size` | enum | "1024x1024" | 1024x1024, 1536x1024, 1024x1536 |
+| `output_format` | enum | "png" | png, jpeg, webp |
+
+### Google Gemini
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `contents` | array | required | Prompt parts (text + optional image) |
+| `responseModalities` | array | ["IMAGE"] | Must include "IMAGE" |
+| `imageMimeType` | string | - | Output mime type |
+
+### x.ai (Grok Imagine Direct)
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `model` | string | "grok-imagine-image" | Model to use |
+| `prompt` | string | required | Image description |
+| `n` | number | 1 | Number of images |
+| `image_url` | string | - | Source image for editing |
+| `aspect_ratio` | enum | - | 1:1, 16:9, 9:16, etc. |
+
 ## Setup Requirements
 
-### 1. Install fal.ai client (for Node.js usage)
+### 1. Install dependencies (for Node.js usage)
 ```bash
-npm install @fal-ai/client
+npm install @fal-ai/client  # only needed for fal provider
 ```
 
 ### 2. Install OpenClaw CLI
@@ -388,10 +400,11 @@ openclaw gateway start
 
 ## Error Handling
 
-- **FAL_KEY missing**: Ensure the API key is set in environment
-- **Image edit failed**: Check prompt content and API quota
+- **API key missing**: Ensure the correct key is set for your chosen provider
+- **Image generation failed**: Check prompt content and API quota
 - **OpenClaw send failed**: Verify gateway is running and channel exists
-- **Rate limits**: fal.ai has rate limits; implement retry logic if needed
+- **Base64 responses**: OpenAI and Google return base64 data; scripts auto-save to temp files
+- **Rate limits**: Each provider has its own rate limits; implement retry logic if needed
 
 ## Tips
 
@@ -399,14 +412,18 @@ openclaw gateway start
    - "wearing a santa hat"
    - "in a business suit"
    - "wearing a summer dress"
-   - "in streetwear fashion"
 
 2. **Direct mode context examples** (location/portrait focus):
    - "a cozy cafe with warm lighting"
    - "a sunny beach at sunset"
    - "a busy city street at night"
-   - "a peaceful park in autumn"
 
-3. **Mode selection**: Let auto-detect work, or explicitly specify for control
-4. **Batch sending**: Edit once, send to multiple channels
-5. **Scheduling**: Combine with OpenClaw scheduler for automated posts
+3. **Provider selection**:
+   - Use `fal` for quick Grok Imagine access via fal.ai proxy
+   - Use `openai` for GPT-image-1's strong prompt following
+   - Use `google` for Gemini's integrated image generation
+   - Use `xai` for direct x.ai access without fal.ai proxy
+
+4. **Mode selection**: Let auto-detect work, or explicitly specify for control
+5. **Batch sending**: Generate once, send to multiple channels
+6. **Scheduling**: Combine with OpenClaw scheduler for automated posts
diff --git a/skill/scripts/clawra-selfie.sh b/skill/scripts/clawra-selfie.sh
index 72d176d5..e7caafa1 100755
--- a/skill/scripts/clawra-selfie.sh
+++ b/skill/scripts/clawra-selfie.sh
@@ -1,14 +1,18 @@
 #!/bin/bash
-# grok-imagine-send.sh
-# Generate an image with Grok Imagine and send it via OpenClaw
+# clawra-selfie.sh
+# Generate an image with multiple AI providers and send it via OpenClaw
 #
-# Usage: ./grok-imagine-send.sh "<prompt>" "<channel>" ["<caption>"]
+# Supported providers (set via IMAGE_PROVIDER env var):
+#   fal    - fal.ai / Grok Imagine    (requires FAL_KEY)
+#   openai - OpenAI gpt-image-1       (requires OPENAI_API_KEY)
+#   google - Google Gemini             (requires GEMINI_API_KEY)
+#   xai    - x.ai direct              (requires XAI_API_KEY)
 #
-# Environment variables required:
-#   FAL_KEY - Your fal.ai API key
+# Usage: ./clawra-selfie.sh "<prompt>" "<channel>" ["<caption>"] [aspect_ratio] [output_format]
 #
 # Example:
-#   FAL_KEY=your_key ./grok-imagine-send.sh "A sunset over mountains" "#art" "Check this out!"
+#   FAL_KEY=your_key ./clawra-selfie.sh "A sunset over mountains" "#art" "Check this out!"
+#   IMAGE_PROVIDER=openai OPENAI_API_KEY=xxx ./clawra-selfie.sh "A sunset" "#art"
 
 set -euo pipefail
 
@@ -30,13 +34,6 @@ log_error() {
     echo -e "${RED}[ERROR]${NC} $1"
 }
 
-# Check required environment variables
-if [ -z "${FAL_KEY:-}" ]; then
-    log_error "FAL_KEY environment variable not set"
-    echo "Get your API key from: https://fal.ai/dashboard/keys"
-    exit 1
-fi
-
 # Check for jq
 if ! command -v jq &> /dev/null; then
     log_error "jq is required but not installed"
@@ -55,9 +52,10 @@ fi
 # Parse arguments
 PROMPT="${1:-}"
 CHANNEL="${2:-}"
-CAPTION="${3:-Generated with Grok Imagine}"
+CAPTION="${3:-Generated with Clawra}"
 ASPECT_RATIO="${4:-1:1}"
 OUTPUT_FORMAT="${5:-jpeg}"
+PROVIDER="${IMAGE_PROVIDER:-fal}"
 
 if [ -z "$PROMPT" ] || [ -z "$CHANNEL" ]; then
     echo "Usage: $0 <prompt> <channel> [caption] [aspect_ratio] [output_format]"
@@ -65,51 +63,222 @@ if [ -z "$PROMPT" ] || [ -z "$CHANNEL" ]; then
     echo "Arguments:"
     echo "  prompt        - Image description (required)"
     echo "  channel       - Target channel (required) e.g., #general, @user"
-    echo "  caption       - Message caption (default: 'Generated with Grok Imagine')"
+    echo "  caption       - Message caption (default: 'Generated with Clawra')"
     echo "  aspect_ratio  - Image ratio (default: 1:1) Options: 2:1, 16:9, 4:3, 1:1, 3:4, 9:16"
     echo "  output_format - Image format (default: jpeg) Options: jpeg, png, webp"
     echo ""
+    echo "Environment:"
+    echo "  IMAGE_PROVIDER   - Provider to use (default: fal)"
+    echo "                     Options: fal, openai, google, xai"
+    echo "  FAL_KEY          - Required for provider: fal"
+    echo "  OPENAI_API_KEY   - Required for provider: openai"
+    echo "  GEMINI_API_KEY   - Required for provider: google"
+    echo "  XAI_API_KEY      - Required for provider: xai"
+    echo ""
     echo "Example:"
     echo "  $0 \"A cyberpunk city at night\" \"#art-gallery\" \"AI Art!\""
+    echo "  IMAGE_PROVIDER=openai $0 \"A sunset\" \"#photos\""
     exit 1
 fi
 
-log_info "Generating image with Grok Imagine..."
+log_info "Provider: $PROVIDER"
+log_info "Generating image..."
 log_info "Prompt: $PROMPT"
 log_info "Aspect ratio: $ASPECT_RATIO"
 
-# Generate image via fal.ai
-RESPONSE=$(curl -s -X POST "https://fal.run/xai/grok-imagine-image" \
-    -H "Authorization: Key $FAL_KEY" \
-    -H "Content-Type: application/json" \
-    -d "{
-        \"prompt\": $(echo "$PROMPT" | jq -Rs .),
-        \"num_images\": 1,
-        \"aspect_ratio\": \"$ASPECT_RATIO\",
-        \"output_format\": \"$OUTPUT_FORMAT\"
-    }")
-
-# Check for errors in response
-if echo "$RESPONSE" | jq -e '.error' > /dev/null 2>&1; then
-    ERROR_MSG=$(echo "$RESPONSE" | jq -r '.error // .detail // "Unknown error"')
-    log_error "Image generation failed: $ERROR_MSG"
-    exit 1
-fi
+# ============================================================================
+# Provider: fal.ai (Grok Imagine)
+# ============================================================================
+generate_fal() {
+    if [ -z "${FAL_KEY:-}" ]; then
+        log_error "FAL_KEY environment variable not set"
+        echo "Get your API key from: https://fal.ai/dashboard/keys"
+        exit 1
+    fi
+
+    RESPONSE=$(curl -s -X POST "https://fal.run/xai/grok-imagine-image" \
+        -H "Authorization: Key $FAL_KEY" \
+        -H "Content-Type: application/json" \
+        -d "{
+            \"prompt\": $(echo "$PROMPT" | jq -Rs .),
+            \"num_images\": 1,
+            \"aspect_ratio\": \"$ASPECT_RATIO\",
+            \"output_format\": \"$OUTPUT_FORMAT\"
+        }")
+
+    # Check for error (ensure it's not null/empty)
+    ERROR_VAL=$(echo "$RESPONSE" | jq -r '.error // .detail // empty')
+    if [ -n "$ERROR_VAL" ]; then
+        log_error "fal.ai image generation failed: $ERROR_VAL"
+        exit 1
+    fi
+
+    # Try multiple response paths: images[0].url, data[0].url
+    IMAGE_URL=$(echo "$RESPONSE" | jq -r '.images[0].url // .data[0].url // empty')
+    REVISED_PROMPT=$(echo "$RESPONSE" | jq -r '.revised_prompt // empty')
+
+    if [ -z "$IMAGE_URL" ]; then
+        log_warn "Could not extract image URL from fal.ai response"
+        log_warn "Response: $(echo "$RESPONSE" | head -c 500)"
+    fi
+}
+
+# ============================================================================
+# Provider: OpenAI (gpt-image-1)
+# ============================================================================
+generate_openai() {
+    if [ -z "${OPENAI_API_KEY:-}" ]; then
+        log_error "OPENAI_API_KEY environment variable not set"
+        echo "Get your API key from: https://platform.openai.com/api-keys"
+        exit 1
+    fi
+
+    # Map aspect ratio to OpenAI size
+    case "$ASPECT_RATIO" in
+        16:9|2:1|20:9|19.5:9|3:2) SIZE="1536x1024" ;;
+        9:16|1:2|9:19.5|9:20|2:3|3:4) SIZE="1024x1536" ;;
+        *) SIZE="1024x1024" ;;
+    esac
+
+    RESPONSE=$(curl -s -X POST "https://api.openai.com/v1/images/generations" \
+        -H "Authorization: Bearer $OPENAI_API_KEY" \
+        -H "Content-Type: application/json" \
+        -d "{
+            \"model\": \"gpt-image-1\",
+            \"prompt\": $(echo "$PROMPT" | jq -Rs .),
+            \"n\": 1,
+            \"size\": \"$SIZE\"
+        }")
+
+    if echo "$RESPONSE" | jq -e '.error' > /dev/null 2>&1; then
+        ERROR_MSG=$(echo "$RESPONSE" | jq -r '.error.message // .error // "Unknown error"')
+        log_error "OpenAI image generation failed: $ERROR_MSG"
+        exit 1
+    fi
+
+    # OpenAI gpt-image-1 returns base64 – save to temp file
+    B64_DATA=$(echo "$RESPONSE" | jq -r '.data[0].b64_json // empty')
+    URL_DATA=$(echo "$RESPONSE" | jq -r '.data[0].url // empty')
 
-# Extract image URL
-IMAGE_URL=$(echo "$RESPONSE" | jq -r '.images[0].url // empty')
+    if [ -n "$URL_DATA" ]; then
+        IMAGE_URL="$URL_DATA"
+    elif [ -n "$B64_DATA" ]; then
+        TMPFILE=$(mktemp /tmp/clawra-openai-XXXXXX."$OUTPUT_FORMAT")
+        echo "$B64_DATA" | base64 -d > "$TMPFILE"
+        IMAGE_URL="$TMPFILE"
+        log_info "Saved to temp file: $TMPFILE"
+    else
+        log_error "OpenAI response contained neither url nor b64_json"
+        echo "Response: $RESPONSE"
+        exit 1
+    fi
+
+    REVISED_PROMPT=$(echo "$RESPONSE" | jq -r '.data[0].revised_prompt // empty')
+}
 
+# ============================================================================
+# Provider: Google Gemini (gemini-2.5-flash-image)
+# ============================================================================
+generate_google() {
+    if [ -z "${GEMINI_API_KEY:-}" ]; then
+        log_error "GEMINI_API_KEY environment variable not set"
+        echo "Get your API key from: https://aistudio.google.com/apikey"
+        exit 1
+    fi
+
+    local MODEL="gemini-2.5-flash-image"
+
+    RESPONSE=$(curl -s -X POST \
+        "https://generativelanguage.googleapis.com/v1beta/models/${MODEL}:generateContent?key=${GEMINI_API_KEY}" \
+        -H "Content-Type: application/json" \
+        -d "{
+            \"contents\": [{
+                \"parts\": [{\"text\": $(echo "$PROMPT" | jq -Rs .)}]
+            }],
+            \"generationConfig\": {
+                \"responseModalities\": [\"IMAGE\"]
+            }
+        }")
+
+    if echo "$RESPONSE" | jq -e '.error' > /dev/null 2>&1; then
+        ERROR_MSG=$(echo "$RESPONSE" | jq -r '.error.message // .error // "Unknown error"')
+        log_error "Google Gemini image generation failed: $ERROR_MSG"
+        exit 1
+    fi
+
+    # Extract base64 image data from Gemini response
+    B64_DATA=$(echo "$RESPONSE" | jq -r '.candidates[0].content.parts[] | select(.inlineData) | .inlineData.data // empty' | head -1)
+
+    if [ -z "$B64_DATA" ]; then
+        log_error "Google Gemini returned no image data"
+        echo "Response: $RESPONSE"
+        exit 1
+    fi
+
+    TMPFILE=$(mktemp /tmp/clawra-gemini-XXXXXX."$OUTPUT_FORMAT")
+    echo "$B64_DATA" | base64 -d > "$TMPFILE"
+    IMAGE_URL="$TMPFILE"
+    log_info "Saved to temp file: $TMPFILE"
+
+    REVISED_PROMPT=""
+}
+
+# ============================================================================
+# Provider: x.ai direct (grok-imagine-image)
+# ============================================================================
+generate_xai() {
+    if [ -z "${XAI_API_KEY:-}" ]; then
+        log_error "XAI_API_KEY environment variable not set"
+        echo "Get your API key from: https://console.x.ai"
+        exit 1
+    fi
+
+    RESPONSE=$(curl -s -X POST "https://api.x.ai/v1/images/generations" \
+        -H "Authorization: Bearer $XAI_API_KEY" \
+        -H "Content-Type: application/json" \
+        -d "{
+            \"model\": \"grok-imagine-image\",
+            \"prompt\": $(echo "$PROMPT" | jq -Rs .),
+            \"n\": 1
+        }")
+
+    if echo "$RESPONSE" | jq -e '.error' > /dev/null 2>&1; then
+        ERROR_MSG=$(echo "$RESPONSE" | jq -r '.error.message // .error // "Unknown error"')
+        log_error "x.ai image generation failed: $ERROR_MSG"
+        exit 1
+    fi
+
+    IMAGE_URL=$(echo "$RESPONSE" | jq -r '.data[0].url // empty')
+    REVISED_PROMPT=""
+}
+
+# ============================================================================
+# Route to the correct provider
+# ============================================================================
+IMAGE_URL=""
+REVISED_PROMPT=""
+
+case "$PROVIDER" in
+    fal)    generate_fal ;;
+    openai) generate_openai ;;
+    google) generate_google ;;
+    xai)    generate_xai ;;
+    *)
+        log_error "Unknown provider: $PROVIDER"
+        echo "Supported providers: fal, openai, google, xai"
+        exit 1
+        ;;
+esac
+
+# Validate result
 if [ -z "$IMAGE_URL" ]; then
     log_error "Failed to extract image URL from response"
-    echo "Response: $RESPONSE"
     exit 1
 fi
 
 log_info "Image generated successfully!"
 log_info "URL: $IMAGE_URL"
 
-# Get revised prompt if available
-REVISED_PROMPT=$(echo "$RESPONSE" | jq -r '.revised_prompt // empty')
 if [ -n "$REVISED_PROMPT" ]; then
     log_info "Revised prompt: $REVISED_PROMPT"
 fi
@@ -118,22 +287,15 @@ fi
 log_info "Sending to channel: $CHANNEL"
 
 if [ "$USE_CLI" = true ]; then
-    # Use OpenClaw CLI
     openclaw message send \
         --action send \
         --channel "$CHANNEL" \
         --message "$CAPTION" \
         --media "$IMAGE_URL"
 else
-    # Direct API call to local gateway
     GATEWAY_URL="${OPENCLAW_GATEWAY_URL:-http://localhost:18789}"
     GATEWAY_TOKEN="${OPENCLAW_GATEWAY_TOKEN:-}"
 
-    HEADERS="-H \"Content-Type: application/json\""
-    if [ -n "$GATEWAY_TOKEN" ]; then
-        HEADERS="$HEADERS -H \"Authorization: Bearer $GATEWAY_TOKEN\""
-    fi
-
     curl -s -X POST "$GATEWAY_URL/message" \
         -H "Content-Type: application/json" \
         ${GATEWAY_TOKEN:+-H "Authorization: Bearer $GATEWAY_TOKEN"} \
@@ -154,9 +316,11 @@ jq -n \
     --arg url "$IMAGE_URL" \
     --arg channel "$CHANNEL" \
     --arg prompt "$PROMPT" \
+    --arg provider "$PROVIDER" \
     '{
         success: true,
         image_url: $url,
         channel: $channel,
-        prompt: $prompt
+        prompt: $prompt,
+        provider: $provider
     }'
diff --git a/skill/scripts/clawra-selfie.ts b/skill/scripts/clawra-selfie.ts
index e15f644a..4b336910 100644
--- a/skill/scripts/clawra-selfie.ts
+++ b/skill/scripts/clawra-selfie.ts
@@ -1,43 +1,45 @@
 /**
- * Grok Imagine to OpenClaw Integration
+ * Clawra Selfie – Multi-Provider Image Generation & Editing
  *
- * Generates images using xAI's Grok Imagine model via fal.ai
- * and sends them to messaging channels via OpenClaw.
+ * Generates or edits images using multiple AI providers and sends them
+ * to messaging channels via OpenClaw.
+ *
+ * Supported providers (set via IMAGE_PROVIDER env var):
+ *   - fal    (fal.ai / Grok Imagine)    – requires FAL_KEY
+ *   - openai (OpenAI gpt-image-1)       – requires OPENAI_API_KEY
+ *   - google (Google Gemini)             – requires GEMINI_API_KEY
+ *   - xai    (x.ai direct)              – requires XAI_API_KEY
  *
  * Usage:
- *   npx ts-node grok-imagine-send.ts "<prompt>" "<channel>" ["<caption>"]
+ *   npx ts-node clawra-selfie.ts <prompt> <channel> [caption] [aspect_ratio] [output_format] [provider]
  *
  * Environment variables:
- *   FAL_KEY - Your fal.ai API key
- *   OPENCLAW_GATEWAY_URL - OpenClaw gateway URL (default: http://localhost:18789)
- *   OPENCLAW_GATEWAY_TOKEN - Gateway auth token (optional)
+ *   IMAGE_PROVIDER             - Provider to use (default: fal)
+ *   FAL_KEY / OPENAI_API_KEY / GEMINI_API_KEY / XAI_API_KEY
+ *   OPENCLAW_GATEWAY_URL       - OpenClaw gateway URL (default: http://localhost:18789)
+ *   OPENCLAW_GATEWAY_TOKEN     - Gateway auth token (optional)
  */
 
 import { exec } from "child_process";
 import { promisify } from "util";
 
+import {
+  getProvider,
+  PROVIDER_ENV_KEYS,
+  AVAILABLE_PROVIDERS,
+} from "./providers";
+import type {
+  AspectRatio,
+  OutputFormat,
+  ProviderName,
+  GenerateImageResult,
+} from "./providers";
+
 const execAsync = promisify(exec);
 
+// ---------------------------------------------------------------------------
 // Types
-interface GrokImagineInput {
-  prompt: string;
-  num_images?: number;
-  aspect_ratio?: AspectRatio;
-  output_format?: OutputFormat;
-}
-
-interface GrokImagineImage {
-  url: string;
-  content_type: string;
-  file_name?: string;
-  width: number;
-  height: number;
-}
-
-interface GrokImagineResponse {
-  images: GrokImagineImage[];
-  revised_prompt?: string;
-}
+// ---------------------------------------------------------------------------
 
 interface OpenClawMessage {
   action: "send";
@@ -46,29 +48,13 @@ interface OpenClawMessage {
   media?: string;
 }
 
-type AspectRatio =
-  | "2:1"
-  | "20:9"
-  | "19.5:9"
-  | "16:9"
-  | "4:3"
-  | "3:2"
-  | "1:1"
-  | "2:3"
-  | "3:4"
-  | "9:16"
-  | "9:19.5"
-  | "9:20"
-  | "1:2";
-
-type OutputFormat = "jpeg" | "png" | "webp";
-
 interface GenerateAndSendOptions {
   prompt: string;
   channel: string;
   caption?: string;
   aspectRatio?: AspectRatio;
   outputFormat?: OutputFormat;
+  provider?: ProviderName;
   useClaudeCodeCLI?: boolean;
 }
 
@@ -77,87 +63,24 @@ interface Result {
   imageUrl: string;
   channel: string;
   prompt: string;
+  provider: string;
   revisedPrompt?: string;
 }
 
-// Check for fal.ai client
-let falClient: any;
-try {
-  const { fal } = require("@fal-ai/client");
-  falClient = fal;
-} catch {
-  // Will use fetch instead
-  falClient = null;
-}
-
-/**
- * Generate image using Grok Imagine via fal.ai
- */
-async function generateImage(
-  input: GrokImagineInput
-): Promise<GrokImagineResponse> {
-  const falKey = process.env.FAL_KEY;
-
-  if (!falKey) {
-    throw new Error(
-      "FAL_KEY environment variable not set. Get your key from https://fal.ai/dashboard/keys"
-    );
-  }
-
-  // Use fal client if available
-  if (falClient) {
-    falClient.config({ credentials: falKey });
-
-    const result = await falClient.subscribe("xai/grok-imagine-image", {
-      input: {
-        prompt: input.prompt,
-        num_images: input.num_images || 1,
-        aspect_ratio: input.aspect_ratio || "1:1",
-        output_format: input.output_format || "jpeg",
-      },
-    });
-
-    return result.data as GrokImagineResponse;
-  }
-
-  // Fallback to fetch
-  const response = await fetch("https://fal.run/xai/grok-imagine-image", {
-    method: "POST",
-    headers: {
-      Authorization: `Key ${falKey}`,
-      "Content-Type": "application/json",
-    },
-    body: JSON.stringify({
-      prompt: input.prompt,
-      num_images: input.num_images || 1,
-      aspect_ratio: input.aspect_ratio || "1:1",
-      output_format: input.output_format || "jpeg",
-    }),
-  });
-
-  if (!response.ok) {
-    const error = await response.text();
-    throw new Error(`Image generation failed: ${error}`);
-  }
+// ---------------------------------------------------------------------------
+// OpenClaw integration
+// ---------------------------------------------------------------------------
 
-  return response.json();
-}
-
-/**
- * Send image via OpenClaw
- */
 async function sendViaOpenClaw(
   message: OpenClawMessage,
   useCLI: boolean = true
 ): Promise<void> {
   if (useCLI) {
-    // Use OpenClaw CLI
     const cmd = `openclaw message send --action send --channel "${message.channel}" --message "${message.message}" --media "${message.media}"`;
     await execAsync(cmd);
     return;
   }
 
-  // Direct API call
   const gatewayUrl =
     process.env.OPENCLAW_GATEWAY_URL || "http://localhost:18789";
   const gatewayToken = process.env.OPENCLAW_GATEWAY_TOKEN;
@@ -182,36 +105,43 @@ async function sendViaOpenClaw(
   }
 }
 
-/**
- * Main function: Generate image and send to channel
- */
-async function generateAndSend(options: GenerateAndSendOptions): Promise<Result> {
+// ---------------------------------------------------------------------------
+// Main logic
+// ---------------------------------------------------------------------------
+
+async function generateAndSend(
+  options: GenerateAndSendOptions
+): Promise<Result> {
   const {
     prompt,
     channel,
-    caption = "Generated with Grok Imagine",
+    caption = "Generated with Clawra",
     aspectRatio = "1:1",
     outputFormat = "jpeg",
+    provider: providerName,
     useClaudeCodeCLI = true,
   } = options;
 
-  console.log(`[INFO] Generating image with Grok Imagine...`);
+  // Resolve provider
+  const provider = getProvider(providerName);
+  console.log(`[INFO] Provider: ${provider.name}`);
+  console.log(`[INFO] Generating image...`);
   console.log(`[INFO] Prompt: ${prompt}`);
   console.log(`[INFO] Aspect ratio: ${aspectRatio}`);
 
   // Generate image
-  const imageResult = await generateImage({
+  const imageResult: GenerateImageResult = await provider.generateImage({
     prompt,
-    num_images: 1,
-    aspect_ratio: aspectRatio,
-    output_format: outputFormat,
+    numImages: 1,
+    aspectRatio,
+    outputFormat,
   });
 
   const imageUrl = imageResult.images[0].url;
   console.log(`[INFO] Image generated: ${imageUrl}`);
 
-  if (imageResult.revised_prompt) {
-    console.log(`[INFO] Revised prompt: ${imageResult.revised_prompt}`);
+  if (imageResult.revisedPrompt) {
+    console.log(`[INFO] Revised prompt: ${imageResult.revisedPrompt}`);
   }
 
   // Send via OpenClaw
@@ -234,35 +164,42 @@ async function generateAndSend(options: GenerateAndSendOptions): Promise<Result>
     imageUrl,
     channel,
     prompt,
-    revisedPrompt: imageResult.revised_prompt,
+    provider: provider.name,
+    revisedPrompt: imageResult.revisedPrompt,
   };
 }
 
+// ---------------------------------------------------------------------------
 // CLI entry point
+// ---------------------------------------------------------------------------
+
 async function main() {
   const args = process.argv.slice(2);
 
   if (args.length < 2) {
     console.log(`
-Usage: npx ts-node grok-imagine-send.ts <prompt> <channel> [caption] [aspect_ratio] [output_format]
+Usage: npx ts-node clawra-selfie.ts <prompt> <channel> [caption] [aspect_ratio] [output_format] [provider]
 
 Arguments:
   prompt        - Image description (required)
   channel       - Target channel (required) e.g., #general, @user
-  caption       - Message caption (default: 'Generated with Grok Imagine')
+  caption       - Message caption (default: 'Generated with Clawra')
   aspect_ratio  - Image ratio (default: 1:1) Options: 2:1, 16:9, 4:3, 1:1, 3:4, 9:16
   output_format - Image format (default: jpeg) Options: jpeg, png, webp
+  provider      - Image provider (default: fal) Options: ${AVAILABLE_PROVIDERS.join(", ")}
 
 Environment:
-  FAL_KEY       - Your fal.ai API key (required)
+  IMAGE_PROVIDER   - Default provider (overridden by provider argument)
+${AVAILABLE_PROVIDERS.map((p) => `  ${PROVIDER_ENV_KEYS[p].padEnd(17)}- Required for provider: ${p}`).join("\n")}
 
 Example:
-  FAL_KEY=your_key npx ts-node grok-imagine-send.ts "A cyberpunk city" "#art" "Check this out!"
+  FAL_KEY=xxx npx ts-node clawra-selfie.ts "A cyberpunk city" "#art" "Check this!"
+  IMAGE_PROVIDER=openai OPENAI_API_KEY=xxx npx ts-node clawra-selfie.ts "A sunset" "#photos"
 `);
     process.exit(1);
   }
 
-  const [prompt, channel, caption, aspectRatio, outputFormat] = args;
+  const [prompt, channel, caption, aspectRatio, outputFormat, provider] = args;
 
   try {
     const result = await generateAndSend({
@@ -271,6 +208,7 @@ Example:
       caption,
       aspectRatio: aspectRatio as AspectRatio,
       outputFormat: outputFormat as OutputFormat,
+      provider: provider as ProviderName,
     });
 
     console.log("\n--- Result ---");
@@ -283,11 +221,8 @@ Example:
 
 // Export for module use
 export {
-  generateImage,
   sendViaOpenClaw,
   generateAndSend,
-  GrokImagineInput,
-  GrokImagineResponse,
   OpenClawMessage,
   GenerateAndSendOptions,
   Result,
diff --git a/tsconfig.json b/tsconfig.json
new file mode 100644
index 00000000..ff0b6b08
--- /dev/null
+++ b/tsconfig.json
@@ -0,0 +1,28 @@
+{
+    "compilerOptions": {
+        "target": "ES2020",
+        "module": "commonjs",
+        "lib": [
+            "ES2020"
+        ],
+        "types": [
+            "node"
+        ],
+        "strict": true,
+        "esModuleInterop": true,
+        "skipLibCheck": true,
+        "forceConsistentCasingInFileNames": true,
+        "resolveJsonModule": true,
+        "outDir": "./dist",
+        "rootDir": "./scripts",
+        "declaration": true,
+        "noEmit": true
+    },
+    "include": [
+        "scripts/**/*.ts"
+    ],
+    "exclude": [
+        "node_modules",
+        "dist"
+    ]
+}
\ No newline at end of file