import google.generativeai as genai

genai.configure(api_key="YOUR_API_KEY")

undefined

import { GoogleGenerativeAI } from "@google/generative-ai";
import fs from "fs";

const genAI = new GoogleGenerativeAI("YOUR_API_KEY");
const model = genAI.getGenerativeModel({ model: "gemini-3-pro-image-preview" });

const result = await model.generateContent("A serene mountain landscape at sunset");
const imageData = result.response.parts[0].inlineData.data;

fs.writeFileSync("generated_image.png", Buffer.from(imageData, "base64"));
console.log("Image saved!");

import google.generativeai as genai

genai.configure(api_key="YOUR_API_KEY")

model = genai.GenerativeModel(
    "gemini-3-pro-image-preview",
    generation_config={
        "thinking_level": "high",  # Best quality
        "temperature": 1.0
    }
)

**Tips for Better Prompts:**
- Be specific and detailed
- Specify art style (realistic, cartoon, oil painting, etc.)
- Include lighting, mood, and atmosphere
- Mention quality level (4K, detailed, high-quality)
- Describe colors, textures, composition

**See:** `references/generation-guide.md` for comprehensive prompting techniques

---

undefined

**4K Features:**
- Native 4K resolution support
- Upscaling to 2K/4K
- 16:9 aspect ratio at 4K
- Enhanced detail and clarity

**See:** `references/resolution-guide.md` for resolution control

---

prompt = """Create a professional business card design with:
- Company name: "TechVision AI"
- Text: "Dr. Sarah Chen"
- Text: "Chief AI Officer"
- Text: "sarah.chen@techvision.ai"
- Text: "+1 (555) 123-4567"
- Modern, clean design
- Professional fonts
- Blue and white color scheme
- All text clearly readable"""

response = model.generate_content(prompt)

if response.parts:
    with open("business_card.png", "wb") as f:
        f.write(response.parts[0].inline_data.data)

undefined

# Check if grounding was used
if hasattr(response, 'grounding_metadata'):
    print(f"Grounding sources used: {len(response.grounding_metadata.grounding_chunks)}")

**Grounded Generation Use Cases:**
- Historical scenes (accurate to period)
- Scientific visualizations
- Current events
- Famous landmarks
- Product representations

**Benefits:**
- Factual accuracy
- Real-world grounding
- Reduced hallucination
- Up-to-date information

**Note:** Uses free Google Search quota (1,500 queries/day)

**See:** `references/grounded-generation.md` for comprehensive guide

---

model = genai.GenerativeModel("gemini-3-pro-image-preview")

**Conversational Editing Features:**
- Preserves visual context across turns
- Incremental modifications
- Natural language instructions
- Multi-turn refinement
- Context-aware changes

**Example Editing Commands:**
- "Make it darker/lighter"
- "Add more [element]"
- "Change the color scheme to [colors]"
- "Make it more realistic/artistic"
- "Remove [element]"

**See:** `references/conversational-editing.md` for advanced patterns

---

undefined

**Supported Ratios:**
- **16:9** - Wide, cinematic (4K supported)
- **1:1** - Square
- **4:3** - Standard
- **9:16** - Vertical/portrait

---

def generate_with_cost_tracking(prompt):
    """Generate image and track costs"""

    response = model.generate_content(prompt)

    # Calculate cost
    usage = response.usage_metadata
    input_cost = (usage.prompt_token_count / 1_000_000) * 2.00
    output_cost = (usage.candidates_token_count / 1_000_000) * 9.00
    image_cost = 0.134  # Per image

    total_cost = input_cost + output_cost + image_cost

    print(f"Input tokens: {usage.prompt_token_count} (${input_cost:.6f})")
    print(f"Output tokens: {usage.candidates_token_count} (${output_cost:.6f})")
    print(f"Image cost: ${image_cost:.6f}")
    print(f"Total: ${total_cost:.6f}")

    return response

response = generate_with_cost_tracking("A beautiful sunset over mountains")

import google.generativeai as genai

genai.configure(api_key="YOUR_API_KEY")
model = genai.GenerativeModel("gemini-3-pro-image-preview")

prompts = [
    "A serene mountain lake at dawn",
    "A bustling market in Morocco",
    "A futuristic robot assistant",
    "An abstract geometric pattern"
]

for i, prompt in enumerate(prompts):
    print(f"Generating image {i+1}/{len(prompts)}: {prompt}")

    response = model.generate_content(prompt)

    if response.parts:
        with open(f"generated_{i+1}.png", "wb") as f:
            f.write(response.parts[0].inline_data.data)
        print(f"  Saved: generated_{i+1}.png")

from google.api_core import exceptions

def safe_image_generation(prompt):
    """Generate image with error handling"""

    try:
        response = model.generate_content(prompt)

        if not response.parts:
            return {"success": False, "error": "No image generated"}

        if not hasattr(response.parts[0], 'inline_data'):
            return {"success": False, "error": "Invalid response format"}

        return {
            "success": True,
            "image_data": response.parts[0].inline_data.data,
            "mime_type": response.parts[0].inline_data.mime_type
        }

    except exceptions.InvalidArgument as e:
        return {"success": False, "error": f"Invalid prompt: {e}"}
    except exceptions.ResourceExhausted as e:
        return {"success": False, "error": f"Rate limit exceeded: {e}"}
    except Exception as e:
        return {"success": False, "error": f"Error: {e}"}