免費試用 Nano Banana Pro Edit API，精準編輯圖片並支援原生 2K/4K 輸出，適合局部修改、背景替換、產品修圖和批量自動化處理。
立即體驗 AI 圖片生成器
Google Nano Banana Pro Edit API（由 Gemini 3.0 Pro Image 模型驅動）為開發者與創意團隊提供經濟高效、可投入生產的 AI 圖像編輯能力。這項高階 Gemini 圖像編輯 API 整合，能協助您透過自然語言指令將既有視覺素材轉換為最高 4K 的高解析度輸出。Gemini 模型為複雜編輯提供語意推理，而 API 則為 Best Image AI 上的可擴展工作流程提供穩定整合。
注意 請確保您的提示詞符合 Google 的安全指南。如果發生錯誤，請檢查您的提示詞是否包含受限內容，調整後再試一次。
// Step 1: Submit generation request
// width and height must be aspect-ratio integers such as 16 and 9,
// not pixel dimensions like 768 and 1280.
// Currently all width/height values are passed as ratio integers,
// and the backend does not support custom pixel dimensions for these fields.
const response = await fetch('https://api.flaq.ai/api/v1/image/task', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
'Authorization': 'Bearer YOUR_API_KEY'
},
body: JSON.stringify({
model_name: 'nano-banana-pro-edit',
prompt: 'Transform this image into a watercolor painting style',
width: 16, // Aspect-ratio value, not pixel width
height: 9, // Aspect-ratio value, not pixel height
resolution: '2k', // Supported values: '1k', '2k', '4k'
image_url_list: [
'https://example.com/image1.jpg',
'https://example.com/image2.jpg'
]
})
});
const { data } = await response.json();
const taskId = data.task_id;
// Step 2: Poll for results
const taskId = data.task_id;
const pollResult = async (taskId) => {
const res = await fetch(`https://api.flaq.ai/api/v1/image/${taskId}`, {
headers: { 'Authorization': 'Bearer YOUR_API_KEY' }
});
return res.json();
};
while (true) {
const pollResultData = await pollResult(taskId);
const status = pollResultData.data.task_status;
if (status === 'succeed') {
console.log(pollResultData.data.task_result.images[].);
;
}
(status === ) {
.(pollResultData..);
;
}
( (resolve, ));
}
# Step 1: Submit generation request
import requests
response = requests.post(
'https://api.flaq.ai/api/v1/image/task',
headers={
'Content-Type': 'application/json',
'Authorization': 'Bearer YOUR_API_KEY'
},
json={
'model_name': 'nano-banana-pro-edit',
'prompt': 'Transform this image into a watercolor painting style',
'width': 16, # Aspect-ratio value, not pixel width
'height': 9, # Aspect-ratio value, not pixel height
'resolution': '2k', # Supported values: '1k', '2k', '4k'
'image_url_list': [
'https://example.com/image1.jpg',
'https://example.com/image2.jpg'
]
}
)
result = response.json()
task_id = result['data']['task_id']
# Step 1: Submit generation request
curl -X POST https://api.flaq.ai/api/v1/image/task \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model_name": "nano-banana-pro-edit",
"prompt": "Transform this image into a watercolor painting style",
"width": 16,
"height": 9,
"resolution": "2k",
"image_url_list": [
"https://example.com/image1.jpg",
"https://example.com/image2.jpg"
]
}'
# Step 2: Poll for results
# Replace {task_id} with the task_id returned from the submit response
curl -X GET "https://api.flaq.ai/api/v1/image/{task_id}" \
-H "Authorization: Bearer YOUR_API_KEY"
# Step 2: Poll for results
task_id = response.json()['data']['task_id']
poll_url = f"https://api.flaq.ai/api/v1/image/{task_id}"
while True:
poll_result = requests.get(poll_url, headers={'Authorization': 'Bearer YOUR_API_KEY'}).json()
status = poll_result['data']['task_status']
if status == 'succeed':
print(poll_result['data']['task_result']['images'][0]['url'])
break
if status == 'failed':
print(poll_result['data']['task_status_msg'])
break
time.sleep(10)