Nano Banana 2 API: generate and edit images

"""Generate or edit images with Nano Banana 2 (gemini-3.1-flash-image)."""
import argparse
import base64
import os
import sys
from pathlib import Path

import requests

URL = "https://api.laozhang.ai/v1beta/models/gemini-3.1-flash-image:generateContent"
RATIOS = ["1:1", "1:4", "1:8", "2:3", "3:2", "3:4", "4:1", "4:3", "4:5", "5:4", "8:1", "9:16", "16:9", "21:9"]
SIZES = ["512", "1K", "2K", "4K"]
MIME_TYPES = {".png": "image/png", ".jpg": "image/jpeg", ".jpeg": "image/jpeg", ".webp": "image/webp"}
EXTENSIONS = {"image/png": "png", "image/jpeg": "jpg", "image/webp": "webp"}

parser = argparse.ArgumentParser(description="Generate an image, or edit the images you pass.")
parser.add_argument("prompt")
parser.add_argument("images", nargs="*", help="up to 14 PNG, JPEG, or WebP reference images")
parser.add_argument("--ratio", choices=RATIOS, help="aspect ratio; omit for 1:1, or to follow an input image")
parser.add_argument("--size", default="1K", choices=SIZES)
parser.add_argument("--out", default="nano-banana-2", help="output file name without extension")
args = parser.parse_args()
if len(args.images) > 14:
    sys.exit("Send at most 14 reference images.")

parts = [{"text": args.prompt}]
for path in args.images:
    mime = MIME_TYPES.get(Path(path).suffix.lower())
    if mime is None:
        sys.exit(f"Use a PNG, JPEG, or WebP file: {path}")
    data = base64.b64encode(Path(path).read_bytes()).decode("ascii")
    parts.append({"inlineData": {"mimeType": mime, "data": data}})

image_config = {"imageSize": args.size}
if args.ratio:
    image_config["aspectRatio"] = args.ratio

response = requests.post(
    URL,
    headers={"Authorization": f"Bearer {os.environ['LAOZHANG_API_KEY']}"},
    json={
        "contents": [{"role": "user", "parts": parts}],
        "generationConfig": {"responseModalities": ["IMAGE"], "imageConfig": image_config},
    },
    timeout=300,
)
if response.status_code != 200:
    sys.exit(f"HTTP {response.status_code}: {response.text[:500]}")

result = response.json()
images = [
    part["inlineData"]
    for candidate in result.get("candidates") or []
    for part in (candidate.get("content") or {}).get("parts") or []
    if "inlineData" in part and not part.get("thought")
]
if not images:
    reasons = [candidate.get("finishReason") for candidate in result.get("candidates") or []]
    sys.exit(f"No image returned: {result.get('promptFeedback') or reasons}")
for number, image in enumerate(images, start=1):
    suffix = "" if number == 1 else f"-{number}"
    output = Path(f"{args.out}{suffix}.{EXTENSIONS.get(image['mimeType'], 'bin')}")
    output.write_bytes(base64.b64decode(image["data"]))
    print("Saved", output)

python nano_banana_2.py "Generate an image of a night market food stall with a hand-painted sign that reads \"NOODLES\", warm lantern light." --ratio 16:9 --size 4K --out nb2-night-market

# Edit one image
python nano_banana_2.py "Turn this daytime street photo into a rainy night scene with neon reflections. Keep the buildings unchanged." street.jpg --ratio 3:2 --size 2K --out nb2-street

# Combine three references: product, scene, and a third image for the look
python nano_banana_2.py "Place the product from the first image on the table in the second image, painted in the style of the third image." product.png scene.jpg style.jpg --ratio 3:2 --size 2K --out nb2-composite