Nano Banana 시리즈 개발자 가이드

{
  "contents": [{
    "role": "user",
    "parts": [
      { "fileData": { "fileUri": "https://your-cdn.example.com/a.png", "mimeType": "image/png" } },
      { "fileData": { "fileUri": "https://your-cdn.example.com/b.jpg", "mimeType": "image/jpeg" } },
      { "text": "Put the jacket from the second image on the person in the first image" }
    ]
  }],
  "generationConfig": {
    "responseModalities": ["IMAGE"],
    "imageConfig": { "imageSize": "2K" }
  }
}

"promptTokensDetails": [
  { "modality": "TEXT", "tokenCount": 17 },
  { "modality": "IMAGE", "tokenCount": 1120 }
]

curl --location 'https://api.apiyi.com/v1beta/models/gemini-3-pro-image:generateContent' \
  --header "Authorization: Bearer $APIYI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
      "contents": [{
          "role": "user",
          "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" }
          ]
      }],
      "generationConfig": {
          "responseModalities": ["IMAGE"],
          "imageConfig": { "aspectRatio": "16:9", "imageSize": "2K" }
      }
  }' > output.json

import base64, os, requests

API_KEY = os.environ["APIYI_API_KEY"]
MODEL = "gemini-3.1-flash-image"
URL = f"https://api.apiyi.com/v1beta/models/{MODEL}:generateContent"

IMAGE_URLS = [
    "https://raw.githubusercontent.com/apiyi-api/ai-pics/refs/heads/main/1762260696217_dd0352c1f9604540.png",
]
PROMPT = "Change the person's clothes to a blue jacket and keep everything else the same"

payload = {
    "contents": [{
        "role": "user",
        "parts": [
            *[{"fileData": {"fileUri": u, "mimeType": "image/png"}} for u in IMAGE_URLS],
            {"text": PROMPT},
        ],
    }],
    "generationConfig": {
        "responseModalities": ["IMAGE"],
        "imageConfig": {"imageSize": "2K"},
    },
}

resp = requests.post(URL, json=payload, timeout=300,
                     headers={"Authorization": f"Bearer {API_KEY}"})
if resp.status_code != 200:
    raise SystemExit(f"HTTP {resp.status_code}: {resp.text[:500]}")
data = resp.json()

# 1. Confirm the reference image was read: promptTokensDetails must include IMAGE
details = data.get("usageMetadata", {}).get("promptTokensDetails", [])
image_tokens = sum(d.get("tokenCount", 0) for d in details if d.get("modality") == "IMAGE")
if image_tokens == 0:
    print("⚠️ Reference image was not read (Google could not fetch it); the result will ignore it")

# 2. Iterate over parts to find the image; never index into it
for part in data["candidates"][0]["content"]["parts"]:
    inline = part.get("inlineData")
    if inline:
        with open("output.png", "wb") as f:
            f.write(base64.b64decode(inline["data"]))
        print(f"✅ Saved output.png (reference image: {image_tokens} tokens)")
        break
else:
    print("No image in the response:", data["candidates"][0].get("finishReason"))

{
  "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: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