跳转到主要内容

​
根据文本生成图片

根据详尽的文本描述（prompt），直接生成与之匹配的图片。 
import base64
import requests
import os

url = "https://api.minimaxi.com/v1/image_generation"
api_key = os.environ.get("MINIMAX_API_KEY")
headers = {"Authorization": f"Bearer {api_key}"}

payload = {
    "model": "image-01",
    "prompt": "men Dressing in white t shirt, full-body stand front view image :25, outdoor, Venice beach sign, full-body image, Los Angeles, Fashion photography of 90s, documentary, Film grain, photorealistic",
    "aspect_ratio": "16:9",
    "response_format": "base64",
}

response = requests.post(url, headers=headers, json=payload)
response.raise_for_status()

images = response.json()["data"]["image_base64"]

for i in range(len(images)):
    with open(f"output-{i}.jpeg", "wb") as f:
        f.write(base64.b64decode(images[i]))
生成结果： 图片描述

​
结合参考图生成图片

此功能允许提供一张或多张包含清晰主体的参考图（支持网络图片链接），并结合 prompt 描述，生成一张保留了主体特征的新图片。该功能尤其适用于需要保持人物形象一致性的场景，例如为同一个虚拟角色生成不同情境下的图片。 
import base64
import requests
import os

url = "https://api.minimaxi.com/v1/image_generation"
api_key = os.environ.get("MINIMAX_API_KEY")
headers = {"Authorization": f"Bearer {api_key}"}

payload = {
    "model": "image-01",
    "prompt": "女孩在图书馆的窗户前，看向远方",
    "aspect_ratio": "16:9",
    "subject_reference": [
        {
            "type": "character",
            "image_file": "https://cdn.hailuoai.com/prod/2025-08-12-17/video_cover/1754990600020238321-411603868533342214-cover.jpg",
        }
    ],
    "response_format": "base64",
}

response = requests.post(url, headers=headers, json=payload)
response.raise_for_status()
images = response.json()["data"]["image_base64"]

for i in range(len(images)):
    with open(f"output-{i}.jpeg", "wb") as f:
        f.write(base64.b64decode(images[i]))
生成结果： 图片描述
⌘I