Gemini 2.5 Flash Image Editing

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

"""
Gemini Image Editing Tool - Python Version
Upload local image + text description to generate new image with custom aspect ratios
"""

import requests
import base64
import os
import datetime
import mimetypes
from typing import Optional, Tuple

class GeminiImageEditor:
    """Gemini Image Editor"""

    # Supported aspect ratios
    SUPPORTED_ASPECT_RATIOS = [
        "21:9", "16:9", "4:3", "3:2", "1:1",
        "9:16", "3:4", "2:3", "5:4", "4:5"
    ]

    def __init__(self, api_key: str,
                 api_url: str = "https://api.laozhang.ai/v1beta/models/gemini-2.5-flash-image:generateContent"):
        """
        Initialize image editor

        Args:
            api_key: API key
            api_url: API URL (using Google native Gemini API)
        """
        self.api_key = api_key
        self.api_url = api_url
        self.headers = {
            "Content-Type": "application/json",
            "Authorization": f"Bearer {api_key}"
        }

    def edit_image(self, image_path: str, prompt: str,
                   aspect_ratio: Optional[str] = "1:1",
                   output_dir: str = ".") -> Tuple[bool, str]:
        """
        Edit image and generate new image

        Args:
            image_path: Input image path
            prompt: Edit description (prompt)
            aspect_ratio: Aspect ratio like "16:9", "1:1" etc (default 1:1)
            output_dir: Output directory (default current directory)

        Returns:
            (success, message)
        """
        print(f"🚀 Starting image editing...")
        print(f"📁 Input image: {image_path}")
        print(f"📝 Edit description: {prompt}")
        print(f"📐 Aspect ratio: {aspect_ratio}")

        # Check if image file exists
        if not os.path.exists(image_path):
            return False, f"Image file not found: {image_path}"

        # Validate aspect ratio
        if aspect_ratio and aspect_ratio not in self.SUPPORTED_ASPECT_RATIOS:
            return False, f"Unsupported aspect ratio {aspect_ratio}. Supported: {', '.join(self.SUPPORTED_ASPECT_RATIOS)}"

        # Read and encode image
        try:
            with open(image_path, 'rb') as f:
                image_data = f.read()
            image_base64 = base64.b64encode(image_data).decode('utf-8')

            # Detect image type
            mime_type, _ = mimetypes.guess_type(image_path)
            if not mime_type or not mime_type.startswith('image/'):
                mime_type = 'image/jpeg'  # Default
            print(f"🎨 Image type: {mime_type}")

        except Exception as e:
            return False, f"Failed to read image: {str(e)}"

        # Generate output filename
        timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
        output_file = os.path.join(output_dir, f"gemini_edited_{timestamp}.png")

        try:
            # Build request payload (Google native format)
            payload = {
                "contents": [{
                    "parts": [
                        {"text": prompt},
                        {
                            "inline_data": {
                                "mime_type": mime_type,
                                "data": image_base64
                            }
                        }
                    ]
                }]
            }

            # Add aspect ratio config
            if aspect_ratio:
                payload["generationConfig"] = {
                    "responseModalities": ["IMAGE"],
                    "imageConfig": {
                        "aspectRatio": aspect_ratio
                    }
                }

            print("📡 Sending request to Gemini API...")

            # Send request
            response = requests.post(
                self.api_url,
                headers=self.headers,
                json=payload,
                timeout=120
            )

            if response.status_code != 200:
                return False, f"API request failed, status code: {response.status_code}"

            # Parse response
            result = response.json()

            # Extract image data
            if "candidates" not in result or len(result["candidates"]) == 0:
                return False, "Image data not found"

            candidate = result["candidates"][0]
            if "content" not in candidate or "parts" not in candidate["content"]:
                return False, "Response format error"

            parts = candidate["content"]["parts"]
            output_image_data = None

            for part in parts:
                if "inlineData" in part and "data" in part["inlineData"]:
                    output_image_data = part["inlineData"]["data"]
                    break

            if not output_image_data:
                return False, "Image data not found"

            # Decode and save image
            print("💾 Saving image...")
            decoded_data = base64.b64decode(output_image_data)

            os.makedirs(os.path.dirname(output_file) if os.path.dirname(output_file) else ".", exist_ok=True)

            with open(output_file, 'wb') as f:
                f.write(decoded_data)

            file_size = len(decoded_data) / 1024  # KB
            print(f"✅ Image saved: {output_file}")
            print(f"📊 File size: {file_size:.2f} KB")

            return True, f"Successfully saved image: {output_file}"

        except requests.exceptions.Timeout:
            return False, "Request timeout (120 seconds)"
        except requests.exceptions.ConnectionError:
            return False, "Network connection error"
        except Exception as e:
            return False, f"Error: {str(e)}"

def main():
    """Main function - usage example"""

    # ========== Configuration ==========
    # 1. Set your API key
    API_KEY = "sk-YOUR_API_KEY"

    # 2. Input image path
    INPUT_IMAGE = "./input.jpg"  # Replace with your image path

    # 3. Input edit description (prompt)
    PROMPT = "add a cute cat next to the dog, keep the original composition"

    # 4. Select aspect ratio (optional)
    # Supported: 21:9, 16:9, 4:3, 3:2, 1:1, 9:16, 3:4, 2:3, 5:4, 4:5
    ASPECT_RATIO = "16:9"  # Widescreen
    # ASPECT_RATIO = "1:1"   # Square
    # ASPECT_RATIO = "9:16"  # Portrait

    # 5. Set output directory (optional)
    OUTPUT_DIR = "."  # Current directory
    # ============================

    print("="*60)
    print("Gemini Image Editing Tool")
    print("="*60)
    print(f"⏰ Start time: {datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
    print("="*60)

    # Create editor and edit image
    editor = GeminiImageEditor(API_KEY)
    success, message = editor.edit_image(
        image_path=INPUT_IMAGE,
        prompt=PROMPT,
        aspect_ratio=ASPECT_RATIO,
        output_dir=OUTPUT_DIR
    )

    # Display result
    print("\n" + "="*60)
    if success:
        print("🎉 Edit successful!")
        print(f"✅ {message}")
    else:
        print("❌ Edit failed")
        print(f"💥 {message}")
        print("\nSuggestions:")
        print("  1. Check if API key is correct")
        print("  2. Check if image path is correct")
        print("  3. Check network connection")
        print("  4. Check if prompt is reasonable")

    print(f"⏰ End time: {datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
    print("="*60)

if __name__ == "__main__":
    main()