魔搭社区API使用方法
输入“/”快速插入内容
魔搭社区API使用方法
魔搭社区API使用方法
飞书用户638月23日修改
•
文生图示例代码
代码块
import requests
import time
import json
from PIL import Image
from io import BytesIO
base_url = 'https://api-inference.modelscope.cn/'
api_key = "<MODELSCOPE_SDK_TOKEN>"
common_headers = {
"Authorization": f"Bearer {api_key}",
"Content-Type": "application/json",
}
response = requests.post(
f"{base_url}v1/images/generations",
headers={**common_headers, "X-ModelScope-Async-Mode": "true"},
data=json.dumps({
"model": "black-forest-labs/FLUX.1-Krea-dev", # ModelScope Model-Id, required
"prompt": "A golden cat"
}, ensure_ascii=False).encode('utf-8')
)
response.raise_for_status()
task_id = response.json()["task_id"]
while True:
result = requests.get(
f"{base_url}v1/tasks/{task_id}",
headers={**common_headers, "X-ModelScope-Task-Type": "image_generation"},
)
result.raise_for_status()
data = result.json()
if data["task_status"] == "SUCCEED":
image = Image.open(BytesIO(requests.get(data["output_images"][0]).content))
image.save("result_image.jpg")
break
elif data["task_status"] == "FAILED":
print("Image Generation Failed.")
break
time.sleep(5)
•
•
模型：具体模型页
•