API Nano Banana: geração, referências e edição

{
  "candidates": [{
    "content": {
      "role": "model",
      "parts": [{
        "inlineData": {
          "mimeType": "image/jpeg",
          "data": "BASE64_IMAGE_DATA"
        }
      }]
    },
    "finishReason": "STOP"
  }]
}

import base64
import json
from pathlib import Path

suffixes = {"image/png": ".png", "image/jpeg": ".jpg"}
result = json.loads(Path("response.json").read_text())
saved = 0
for candidate in result.get("candidates", []):
    for part in candidate.get("content", {}).get("parts", []):
        if part.get("thought"):
            continue
        blob = part.get("inlineData")
        if not blob:
            continue
        suffix = suffixes.get(blob["mimeType"])
        if suffix is None:
            raise ValueError("Unexpected image MIME type: " + blob["mimeType"])
        saved += 1
        Path(f"generated-{saved}{suffix}").write_bytes(
            base64.b64decode(blob["data"], validate=True)
        )
if saved == 0:
    raise RuntimeError("No final image returned; inspect response.json.")

python -m pip install "google-genai==2.30.1"

import os
from pathlib import Path
from google import genai
from google.genai import types

MODEL = "nano-banana-2.1"
client = genai.Client(
    vertexai=False,
    api_key=os.environ["BETTERTOKEN_API_KEY"],
    http_options=types.HttpOptions(
        base_url="https://bettertoken.ai",
        api_version="v1beta",
        timeout=650_000,
        retry_options=types.HttpRetryOptions(attempts=1),
        headers={"X-BetterToken-Max-Images": "1"},
    ),
)
config = types.GenerateContentConfig(
    response_modalities=["IMAGE"],
    candidate_count=1,
    image_config=types.ImageConfig(image_size="1K", aspect_ratio="1:1"),
)

def save_images(response, prefix):
    if len(response.candidates or []) != 1 or not response.candidates[0].content:
        raise RuntimeError("No single image candidate returned.")
    saved = 0
    suffixes = {"image/png": ".png", "image/jpeg": ".jpg"}
    for part in response.candidates[0].content.parts or []:
        if part.thought or not part.inline_data:
            continue
        blob = part.inline_data
        suffix = suffixes.get(blob.mime_type)
        if suffix is None:
            raise ValueError("Unexpected image MIME type: " + str(blob.mime_type))
        saved += 1
        Path(f"{prefix}-{saved}{suffix}").write_bytes(blob.data)
    if saved == 0:
        raise RuntimeError("No final image returned; inspect the response.")

first_turn = types.Content(
    role="user",
    parts=[types.Part(text="Uma foto de estúdio de uma caneca de cerâmica azul em uma mesa branca.")],
)
response = client.models.generate_content(
    model=MODEL, contents=[first_turn], config=config,
)
save_images(response, "generated")

first_turn = types.Content(
    role="user",
    parts=[
        types.Part(text="Mude a caneca para vermelho. Preserve a forma e o fundo."),
        types.Part.from_bytes(
            data=Path("reference.jpg").read_bytes(),
            mime_type="image/jpeg",
        ),
    ],
)
response = client.models.generate_content(
    model=MODEL, contents=[first_turn], config=config,
)
save_images(response, "reference-edit")

history = [first_turn, response.candidates[0].content]
edit_turn = types.Content(
    role="user",
    parts=[types.Part(text="Adicione uma pequena alça dourada. Mantenha o restante igual.")],
)
edited = client.models.generate_content(
    model=MODEL, contents=[*history, edit_turn], config=config,
)
save_images(edited, "follow-up")
history.extend([edit_turn, edited.candidates[0].content])

curl --fail-with-body --max-time 650 \
  "https://bettertoken.ai/v1/chat/completions" \
  -H "Authorization: Bearer $BETTERTOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -H "X-BetterToken-Max-Images: 1" \
  -d '{
    "model": "nano-banana-2.1",
    "messages": [{"role": "user", "content": "Uma caneca de cerâmica azul em uma mesa branca."}],
    "n": 1,
    "stream": false,
    "google": {"image_config": {"image_size": "1K", "aspect_ratio": "1:1"}}
  }'

import base64
import os
import re
from pathlib import Path
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["BETTERTOKEN_API_KEY"],
    base_url="https://bettertoken.ai/v1",
    max_retries=0,
    timeout=650,
)
response = client.chat.completions.create(
    model="nano-banana-2.1",
    messages=[{"role": "user", "content": "Uma caneca de cerâmica azul em uma mesa branca."}],
    n=1,
    stream=False,
    extra_headers={"X-BetterToken-Max-Images": "1"},
    extra_body={
        "google": {"image_config": {"image_size": "1K", "aspect_ratio": "1:1"}}
    },
)
content = response.choices[0].message.content or ""
images = re.findall(r"data:(image/(?:png|jpeg));base64,([A-Za-z0-9+/=]+)", content)
if not images:
    raise RuntimeError("No inline image in Chat response.")
for index, (mime, data) in enumerate(images, 1):
    suffix = ".png" if mime == "image/png" else ".jpg"
    Path(f"chat-{index}{suffix}").write_bytes(base64.b64decode(data, validate=True))