Nano Banana Image Editing

curl -X POST "https://api.laozhang.ai/v1/chat/completions" \
     -H "Authorization: Bearer sk-YOUR_API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
    "model": "gemini-2.5-flash-image-preview",
    "stream": false,
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "add a dog to this image"
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://github.com/dianping/cat/raw/master/cat-home/src/main/webapp/images/logo/cat_logo03.png"
                    }
                }
            ]
        }
    ]
}'

#!/usr/bin/env python3
import requests
import json
import base64
import re
from datetime import datetime
import sys

# Configuration
API_KEY = "sk-YOUR_API_KEY"  # Replace with your actual key (pay-per-use type)
API_URL = "https://api.laozhang.ai/v1/chat/completions"

def edit_images_with_gemini():
    """Multi-image composition editing example"""
    
    # Set request headers
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    }
    
    # Request data - supports multiple image inputs
    data = {
        "model": "gemini-2.5-flash-image-preview",
        "stream": False,
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": "Combine these 2 images creatively and add a Corgi dog"
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": "https://github.com/dianping/cat/raw/master/cat-home/src/main/webapp/images/logo/cat_logo03.png"
                        }
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": "https://raw.githubusercontent.com/leonindy/camel/master/camel-admin/src/main/webapp/assets/images/camel_logo_blue.png"
                        }
                    }
                ]
            }
        ]
    }
    
    print("Requesting API...")
    
    try:
        # Send request
        response = requests.post(API_URL, headers=headers, json=data)
        response.raise_for_status()
        
        print("API request successful, processing response...")
        
        # Parse response
        result = response.json()
        
        # Extract content
        content = result['choices'][0]['message']['content']
        print(f"Received content: {content[:200]}...")  # Show first 200 characters
        
        # Find Base64 image data
        # Method 1: Find standard format data:image/type;base64,data
        base64_match = re.search(r'data:image/[^;]+;base64,([A-Za-z0-9+/=]+)', content)
        
        if base64_match:
            base64_data = base64_match.group(1)
            print("Found standard format Base64 data")
        else:
            # Method 2: Find pure Base64 data (long string)
            base64_match = re.search(r'([A-Za-z0-9+/=]{100,})', content)
            if base64_match:
                base64_data = base64_match.group(1)
                print("Found pure Base64 data")
            else:
                print("Error: Cannot find Base64 image data")
                print("Full response content:")
                print(json.dumps(result, indent=2, ensure_ascii=False))
                return False
        
        # Generate filename
        timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
        filename = f"edited_image_{timestamp}.png"
        
        print("Saving image...")
        
        # Decode and save image
        try:
            image_data = base64.b64decode(base64_data)
            with open(filename, 'wb') as f:
                f.write(image_data)
            
            print(f"Image saved successfully as: {filename}")
            print(f"File size: {len(image_data)} bytes")
            return True
            
        except Exception as e:
            print(f"Error: Problem saving image: {e}")
            return False
            
    except requests.exceptions.RequestException as e:
        print(f"Error: API request failed: {e}")
        return False
    except KeyError as e:
        print(f"Error: Response format incorrect, missing field: {e}")
        print("Full response content:")
        print(json.dumps(response.json(), indent=2, ensure_ascii=False))
        return False
    except Exception as e:
        print(f"Error: Unknown error: {e}")
        return False

if __name__ == "__main__":
    success = edit_images_with_gemini()
    sys.exit(0 if success else 1)

#!/bin/bash

# Nano Banana Image Editing - Bash Version
# Supports single/multi-image editing, auto-saves base64 results

# Set API key (replace with your actual【pay-per-use】key)
API_KEY="sk-YOUR_API_KEY"

# Set output filename
OUTPUT_FILE="edited_image_$(date +%Y%m%d_%H%M%S).png"

echo "Requesting API for image editing..."

# Send curl request and save response to temp file
RESPONSE=$(curl -s -X POST "https://api.laozhang.ai/v1/chat/completions" \
     -H "Authorization: Bearer $API_KEY" \
     -H "Content-Type: application/json" \
     -d '{
    "model": "gemini-2.5-flash-image-preview",
    "stream": false,
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Combine 2 images and add a Corgi dog image"
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://github.com/dianping/cat/raw/master/cat-home/src/main/webapp/images/logo/cat_logo03.png"
                    }
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://raw.githubusercontent.com/leonindy/camel/master/camel-admin/src/main/webapp/assets/images/camel_logo_blue.png"
                    }
                }
            ]
        }
    ]
}')

# Check if request was successful
if [ $? -ne 0 ]; then
    echo "Error: API request failed"
    exit 1
fi

echo "API request successful, processing response..."

# Extract Base64 image data from response
BASE64_DATA=$(echo "$RESPONSE" | python3 -c "
import json
import sys
import re

try:
    data = json.load(sys.stdin)
    content = data['choices'][0]['message']['content']
    
    # Find Base64 image data
    base64_match = re.search(r'data:image/[^;]+;base64,([A-Za-z0-9+/=]+)', content)
    if base64_match:
        print(base64_match.group(1))
    else:
        # Try to find pure Base64 data
        base64_match = re.search(r'([A-Za-z0-9+/=]{100,})', content)
        if base64_match:
            print(base64_match.group(1))
        else:
            print('ERROR: No Base64 data found')
            sys.exit(1)
except Exception as e:
    print(f'ERROR: {e}')
    sys.exit(1)
")

# Check if Base64 data was successfully extracted
if [[ "$BASE64_DATA" == ERROR* ]]; then
    echo "$BASE64_DATA"
    echo "Full response content:"
    echo "$RESPONSE"
    exit 1
fi

if [ -z "$BASE64_DATA" ]; then
    echo "Error: Cannot extract Base64 image data from response"
    echo "Full response content:"
    echo "$RESPONSE"
    exit 1
fi

echo "Successfully extracted Base64 data, saving image..."

# Decode Base64 data and save as image file
echo "$BASE64_DATA" | base64 -d > "$OUTPUT_FILE"

# Check if file was successfully created
if [ -f "$OUTPUT_FILE" ] && [ -s "$OUTPUT_FILE" ]; then
    echo "Image saved successfully as: $OUTPUT_FILE"
    echo "File size: $(ls -lh "$OUTPUT_FILE" | awk '{print $5}')"
else
    echo "Error: Image save failed"
    exit 1
fi

echo "✨ Edit complete!"

def add_element_to_image(image_url, element_description):
    """Add new element to image"""
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    }
    
    data = {
        "model": "gemini-2.5-flash-image-preview",
        "stream": False,
        "messages": [{
            "role": "user",
            "content": [
                {"type": "text", "text": f"Add {element_description} to this image"},
                {"type": "image_url", "image_url": {"url": image_url}}
            ]
        }]
    }
    
    response = requests.post(API_URL, headers=headers, json=data)
    return extract_base64_from_response(response.json())

# Usage example
result = add_element_to_image(
    "https://example.com/landscape.jpg",
    "a rainbow in the sky"
)

def creative_merge(image_urls, merge_instruction):
    """Creatively merge multiple images"""
    content = [{"type": "text", "text": merge_instruction}]
    
    # Add all images
    for url in image_urls:
        content.append({
            "type": "image_url",
            "image_url": {"url": url}
        })
    
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    }
    
    data = {
        "model": "gemini-2.5-flash-image-preview",
        "stream": False,
        "messages": [{
            "role": "user",
            "content": content
        }]
    }
    
    response = requests.post(API_URL, headers=headers, json=data)
    return extract_base64_from_response(response.json())

# Usage example
images = [
    "https://example.com/cat.jpg",
    "https://example.com/background.jpg"
]
result = creative_merge(images, "Naturally blend the cat into the background")

def style_transfer(image_url, style_description):
    """Image style transfer"""
    headers = {
        "Authorization": f"Bearer {API_KEY}",
        "Content-Type": "application/json"
    }
    
    data = {
        "model": "gemini-2.5-flash-image-preview",
        "stream": False,
        "messages": [{
            "role": "user",
            "content": [
                {"type": "text", "text": f"Transform this image into {style_description} style"},
                {"type": "image_url", "image_url": {"url": image_url}}
            ]
        }]
    }
    
    response = requests.post(API_URL, headers=headers, json=data)
    return extract_base64_from_response(response.json())

# Usage example
result = style_transfer(
    "https://example.com/photo.jpg",
    "Van Gogh painting"
)

# ❌ Vague instruction
instruction = "edit the image"

# ✅ Clear and specific instruction
instruction = """
1. Add a bright moon in the upper right corner
2. Adjust overall color tone to warm tones
3. Add some firefly light effects
4. Keep the main subject unchanged
"""

def smart_multi_image_edit(images, instruction):
    """Smart multi-image editing, auto-handles different numbers of images"""
    
    if len(images) == 1:
        # Single image edit
        prompt = f"Edit this image: {instruction}"
    elif len(images) == 2:
        # Two-image composition
        prompt = f"Combine these two images creatively: {instruction}"
    else:
        # Multi-image processing
        prompt = f"Process these {len(images)} images together: {instruction}"
    
    # Build content
    content = [{"type": "text", "text": prompt}]
    for img in images:
        content.append({
            "type": "image_url",
            "image_url": {"url": img}
        })
    
    # Send request...
    return send_edit_request(content)

import base64
import io
import re
from datetime import datetime
from PIL import Image

class Base64ImageHandler:
    """Base64 image processing utility class"""
    
    @staticmethod
    def extract_from_response(response_content):
        """Extract base64 data from API response"""
        patterns = [
            r'data:image/([^;]+);base64,([A-Za-z0-9+/=]+)',
            r'([A-Za-z0-9+/=]{100,})'
        ]
        
        for pattern in patterns:
            match = re.search(pattern, response_content)
            if match:
                if len(match.groups()) == 2:
                    return match.group(2), match.group(1)  # data, format
                else:
                    return match.group(1), 'png'  # default to png
        
        return None, None
    
    @staticmethod
    def save_to_file(base64_data, filename=None):
        """Save base64 data as file"""
        if not filename:
            filename = f"image_{datetime.now().strftime('%Y%m%d_%H%M%S')}.png"
        
        image_data = base64.b64decode(base64_data)
        with open(filename, 'wb') as f:
            f.write(image_data)
        
        return filename
    
    @staticmethod
    def to_pil_image(base64_data):
        """Convert to PIL Image object"""
        image_data = base64.b64decode(base64_data)
        return Image.open(io.BytesIO(image_data))
    
    @staticmethod
    def from_pil_image(pil_image, format='PNG'):
        """Convert from PIL Image to base64"""
        buffer = io.BytesIO()
        pil_image.save(buffer, format=format)
        img_str = base64.b64encode(buffer.getvalue()).decode()
        return f"data:image/{format.lower()};base64,{img_str}"