Nano Banana 改圖與多圖融合

from google import genai
from google.genai import types
 
client = genai.Client(
    api_key="YOUR_OFOX_API_KEY",
    http_options={"api_version": "v1beta", "base_url": "https://api.ofox.ai/gemini"},
)
 
with open("apple.png", "rb") as f:
    image = types.Part.from_bytes(data=f.read(), mime_type="image/png")
 
resp = client.models.generate_content(
    model="google/gemini-3.1-flash-image",
    contents=["把蘋果改成綠色，其他保持不變", image],
    config=types.GenerateContentConfig(
        response_modalities=["IMAGE"],
        image_config=types.ImageConfig(aspect_ratio="1:1", image_size="1K"),
    ),
)
 
for part in resp.candidates[0].content.parts:
    if part.inline_data:
        with open("apple_green.png", "wb") as f:
            f.write(part.inline_data.data)

# 圖片的 base64 很長，直接放進命令列會出現 Argument list too long，先寫入檔案
base64 < apple.png | tr -d '\n' > apple.b64
jq -n --rawfile img apple.b64 '{
  contents: [{ parts: [
    { text: "把蘋果改成綠色，其他保持不變" },
    { inlineData: { mimeType: "image/png", data: $img } }
  ] }],
  generationConfig: {
    responseModalities: ["IMAGE"],
    imageConfig: { aspectRatio: "1:1", imageSize: "1K" }
  }
}' > body.json
 
curl 'https://api.ofox.ai/gemini/v1beta/models/google/gemini-3.1-flash-image:generateContent' \
  --max-time 600 \
  -H "x-goog-api-key: $OFOX_API_KEY" \
  -H 'Content-Type: application/json' \
  -d @body.json \
  | jq -r '.candidates[0].content.parts[] | select(.inlineData) | .inlineData.data' | base64 --decode > apple_green.png

curl https://api.ofox.ai/v1/images/edits \
  --max-time 600 \
  -H "Authorization: Bearer $OFOX_API_KEY" \
  -F model=google/gemini-3.1-flash-image \
  -F prompt="把蘋果改成綠色，其他保持不變" \
  -F image=@apple.png \
  | jq -r '.data[0].b64_json' | base64 --decode > apple_green.png