Skip to main content

​
快速开始

注意：即梦系列（4.0 / 3.0 / agent）已改为按次计费，系统固定生成 4 张图片。

​
文生图（单张）

curl https://models.rivus.cn/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "jimeng-4.0",
    "prompt": "一只可爱的熊猫在图书馆看书",
    "size": "1024x1024"
  }'

​
文生图（多张）

curl https://models.rivus.cn/v1/images/generations \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "jimeng-3.0",
    "prompt": "未来城市的夜景，赛博朋克风格",
    "n": 4,
    "size": "1792x1024"
  }'

​
图生图

curl https://models.rivus.cn/v1/images/edits \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "image=@original.png" \
  -F "model=jimeng-4.0" \
  -F "prompt=添加科幻元素和霓虹灯效果" \
  -F "n=1"

​
Python 示例

​
文生图

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://models.rivus.cn/v1"
)

response = client.images.generate(
    model="jimeng-4.0",
    prompt="一只可爱的熊猫在图书馆看书",
    size="1024x1024"
)

print(response.data[0].url)

​
图生图

with open("input.png", "rb") as image_file:
    response = client.images.edit(
        image=image_file,
        model="jimeng-4.0",
        prompt="添加科幻元素"
    )

print(response.data[0].url)

​
批量生成

prompts = [
    "熊猫在图书馆看书",
    "熊猫在公园散步",
    "熊猫在竹林里休息"
]

for prompt in prompts:
    response = client.images.generate(
        model="jimeng-3.0",
        prompt=prompt,
        n=1
    )
    print(f"{prompt}: {response.data[0].url}")

​
错误处理

from openai import OpenAI, APIError, RateLimitError

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://models.rivus.cn/v1"
)

try:
    response = client.images.generate(
        model="jimeng-4.0",
        prompt="测试图片",
        n=1
    )
    print(response.data[0].url)
    
except RateLimitError:
    print("请求频率过高，请稍后重试")
    
except APIError as e:
    print(f"API 错误: {e}")

​
下载生成的图片

import requests

response = client.images.generate(
    model="jimeng-4.0",
    prompt="一只可爱的熊猫",
    n=1
)

image_url = response.data[0].url

# 下载图片
img_data = requests.get(image_url).content
with open('output.png', 'wb') as f:
    f.write(img_data)

​
模型选择建议

场景推荐模型理由
商业设计、高质量海报jimeng-4.0画质最佳，细节丰富
快速原型、批量生成jimeng-3.0速度快，性价比高
多轮对话式创作jimeng-agent智能理解上下文