Nano Banana 시리즈 개발자 가이드

curl --location 'https://api.apiyi.com/v1beta/models/gemini-3-pro-image-preview:generateContent' \
  --header 'Authorization: Bearer sk-' \
  --header 'Content-Type: application/json' \
  --data '{
      "contents": [
          {
              "parts": [
                  {
                      "fileData": {
                          "fileUri": "https://raw.githubusercontent.com/apiyi-api/ai-api-code-samples/refs/heads/main/Vision-API-OpenAI/otter.png",
                          "mimeType": "image/png"
                      }
                  },
                  {
                      "text": "add five dogs"
                  }
              ],
              "role": "user"
          }
      ],
      "generationConfig": {"responseModalities": ["IMAGE"],
      "imageConfig": {
        "aspectRatio": "16:9",
        "imageSize": "2K"
      }},
      "safetySettings": []
  }'   > output.json

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Gemini 3 Pro Image - Image editing (minimal file_uri version)
Purpose: only for a quick check that the endpoint works
"""

import requests
import base64
import json
from pathlib import Path
from datetime import datetime

# ============================================================================
# Configuration
# ============================================================================

API_KEY = "sk-"
API_URL = "https://api.apiyi.com/v1beta/models/gemini-3-pro-image-preview:generateContent"

# Image URL
IMAGE_URL = "https://raw.githubusercontent.com/apiyi-api/ai-pics/refs/heads/main/1762260696217_dd0352c1f9604540.png"
IMAGE_MIME_TYPE = "image/png"

# Edit instructions
EDIT_PROMPT = "Change the person's clothes to a blue jacket and hair to a purple gradient; keep pose, gaze direction, and other structural features unchanged."
SYSTEM_PROMPT = "You are a professional expert in image description and generation. Your task is to produce high-quality image prompts with rich detail and a clear artistic style, or to make accurate, creative edits to existing images, based on the user's request."

# Output parameters
ASPECT_RATIO = "9:16"
RESOLUTION = "4K"
MAX_OUTPUT_TOKENS = 8000
OUTPUT_FILE = f"minimal_{datetime.now().strftime('%Y%m%d_%H%M%S')}.png"

# ============================================================================
# Core
# ============================================================================

def main():
    print("=" * 60)
    print("Testing file_uri endpoint")
    print("=" * 60)
    print(f"Image URL: {IMAGE_URL[:80]}...")
    print(f"Edit prompt: {EDIT_PROMPT}")
    print(f"Output params: {RESOLUTION}, {ASPECT_RATIO}")
    print("-" * 60)

    # Build the request body
    # Note: fileData, mimeType, fileUri must be in camelCase
    payload = {
        "generationConfig": {
            "responseModalities": ["IMAGE", "TEXT"],
            "imageConfig": {
                "imageSize": RESOLUTION,
                "aspectRatio": ASPECT_RATIO
            },
            "maxOutputTokens": MAX_OUTPUT_TOKENS
        },
        "contents": [
            {
                "role": "model",
                "parts": [{"text": SYSTEM_PROMPT}]
            },
            {
                "role": "user",
                "parts": [
                    {
                        "fileData": {           # camelCase: fileData (not file_data)
                            "mimeType": IMAGE_MIME_TYPE,  # camelCase: mimeType
                            "fileUri": IMAGE_URL          # camelCase: fileUri
                        }
                    },
                    {"text": EDIT_PROMPT}
                ]
            }
        ]
    }

    # Send the request
    print("\nSending request...")
    try:
        response = requests.post(
            API_URL,
            json=payload,
            headers={
                "Content-Type": "application/json",
                "Authorization": f"Bearer {API_KEY}"
            },
            timeout=300
        )

        print(f"Response status: {response.status_code}")

        if response.status_code != 200:
            print(f"❌ Error: {response.text}")
            return

        # Parse the response
        data = response.json()
        print("✅ Response received")

        # Save full response for debugging
        with open(OUTPUT_FILE + ".response.json", "w", encoding="utf-8") as f:
            json.dump(data, f, indent=2, ensure_ascii=False)
        print(f"📄 Response saved: {OUTPUT_FILE}.response.json")

        # Extract and print text
        parts = data["candidates"][0]["content"]["parts"]
        for part in parts:
            if "text" in part:
                print(f"\n💬 Text response: {part['text']}")

        # Save image
        for part in parts:
            if "inlineData" in part or "inline_data" in part:
                image_data = part.get("inlineData", part.get("inline_data", {})).get("data")
                if image_data:
                    image_bytes = base64.b64decode(image_data)
                    with open(OUTPUT_FILE, "wb") as f:
                        f.write(image_bytes)
                    print(f"\n✅ Image saved: {OUTPUT_FILE}")
                    print(f"📦 File size: {len(image_bytes) / 1024:.1f} KB")
                    print(f"🔗 File path: {Path(OUTPUT_FILE).resolve()}")
                    return

        print("⚠️  No image data found in the response")

    except requests.Timeout:
        print("❌ Request timed out")
    except Exception as e:
        print(f"❌ Error: {e}")

if __name__ == "__main__":
    main()
    print("\n" + "=" * 60)
    print("Test finished")
    print("=" * 60)

{
  "contents": [{ "parts": [{ "text": "A weather card poster for Tokyo today" }] }],
  "tools": [{ "googleSearch": {} }]
}

API Connection Error: HTTPSConnectionPool(host='api.apiyi.com', port=443): Read timed out. (read timeout=120)

timeout = {
    "1K": 300,  # 5 minutes - quick preview
    "2K": 300,  # 5 minutes - recommended
    "4K": 600,  # 10 minutes - ultra HD
}

import requests, base64

API_KEY = "sk-your-api-key"
URL = "https://api.apiyi.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent"
H = {"Authorization": f"Bearer {API_KEY}", "Content-Type": "application/json"}
CFG = {"responseModalities": ["IMAGE"], "imageConfig": {"imageSize": "2K"}}

contents = []  # keep one running conversation history

def turn(instruction, save_to):
    contents.append({"role": "user", "parts": [{"text": instruction}]})
    data = requests.post(URL, headers=H,
                         json={"contents": contents, "generationConfig": CFG}, timeout=300).json()
    part = next(p for p in data["candidates"][0]["content"]["parts"] if "inlineData" in p)
    contents.append({"role": "model", "parts": [part]})   # key: backfill the output image
    with open(save_to, "wb") as f:
        f.write(base64.b64decode(part["inlineData"]["data"]))

turn("Generate an orange cat sitting on a blue sofa, simple line-art style", "step1.png")
turn("Make the sofa red; keep the cat and composition unchanged", "step2.png")   # edits the previous image
turn("Put a small yellow hat on the cat; keep everything else the same", "step3.png")  # accumulates; red sofa kept

cand = (resp.get("candidates") or [{}])[0]
parts = (cand.get("content") or {}).get("parts") or []      # handles parts=null
images = [p["inlineData"] for p in parts if "inlineData" in p]
if not images:
    raise RuntimeError(f"No image returned, finishReason={cand.get('finishReason')}")

final = images[-1]                                 # last one is the final version
image_bytes = base64.b64decode(final["data"])
mime = final["mimeType"]                           # trust the response; don't hardcode image/png

const parts = resp?.candidates?.[0]?.content?.parts ?? [];
const images = parts.filter((p) => p.inlineData?.data);   // ✅ never write parts[1]
if (images.length === 0) throw new Error("Gemini returned no image data");
const { data, mimeType } = images[images.length - 1].inlineData;   // last is the final version

parts = response["candidates"][0]["content"]["parts"] or []   # parts is null on safety refusals
images = [p["inlineData"]["data"] for p in parts if "inlineData" in p]

if images:
    final_image = images[-1]   # last one = final version