使用 Gemini 生成图像

POST

v1beta

models

{model}

:generateContent

import os
from google import genai
from google.genai import types

client = genai.Client(
    http_options={"api_version": "v1beta", "base_url": "https://api.cometapi.com"},
    api_key=os.environ.get("COMETAPI_KEY"),
)

response = client.models.generate_content(
    model="gemini-3.1-flash-lite-image",
    contents="A Monarch butterfly anatomical sketch on textured parchment",
    config=types.GenerateContentConfig(
        response_modalities=["TEXT", "IMAGE"],
        image_config=types.ImageConfig(aspect_ratio="1:1", image_size="1K"),
    ),
)

final_image = None
for part in response.parts:
    if getattr(part, "thought", False):
        continue
    if part.text:
        print(part.text)
    elif image := part.as_image():
        final_image = image

if final_image:
    final_image.save("output.png")

{
  "candidates": [
    {
      "content": {
        "role": "<string>",
        "parts": [
          {
            "text": "<string>",
            "inlineData": {
              "mimeType": "<string>",
              "data": "<string>"
            },
            "thought": true,
            "thoughtSignature": "<string>"
          }
        ]
      },
      "index": 123,
      "safetyRatings": [
        {
          "category": "<string>",
          "probability": "<string>"
        }
      ]
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 123,
    "totalTokenCount": 123,
    "thoughtsTokenCount": 123
  }
}

有关分步示例，请参阅使用 Gemini 图像模型。

随着 Google 更新图像模型和 generateContent，Gemini 图像生成选项可能会发生变化。请查看 Gemini 图像生成文档以获取最新的完整参数列表和特定于提供商的行为说明。

gemini-2.5-flash-image 已被提供商安排于 2026-10-02 停用。对于新项目，请使用 gemini-3.1-flash-image-preview 或 gemini-3-pro-image-preview。详情请参阅 Google 的弃用时间表。

Gemini 图像响应可能包含 thought 为 true 的中间图像部分。这些不是最终输出。保存生成的图像时，请跳过 thought: true 的部分，并使用最后一个存在 inlineData 且 thought 不为 true 的图像部分。

授权

Authorization

string

header

必填

Use your CometAPI API key.

路径参数

model

string

默认值:gemini-3.1-flash-image-preview

必填

The Gemini image model to use. See the Models page for current options.

请求体

application/json

contents

object[]

必填

Conversation turns. Each item has a role ("user" or "model") and parts array containing text and/or image data.

Show child attributes

generationConfig

object

Controls generation behavior — output modalities, image resolution, thinking, etc.

Show child attributes

tools

object[]

Optional tools. Pass [{"google_search": {}}] to enable Google Search grounding for real-time information in generated images.

Show child attributes

响应

200 - application/json

Success

candidates

object[]

Show child attributes

usageMetadata

object

Show child attributes

创建图像编辑

使用 Gemini 图像模型

import os
from google import genai
from google.genai import types

client = genai.Client(
    http_options={"api_version": "v1beta", "base_url": "https://api.cometapi.com"},
    api_key=os.environ.get("COMETAPI_KEY"),
)

response = client.models.generate_content(
    model="gemini-3.1-flash-lite-image",
    contents="A Monarch butterfly anatomical sketch on textured parchment",
    config=types.GenerateContentConfig(
        response_modalities=["TEXT", "IMAGE"],
        image_config=types.ImageConfig(aspect_ratio="1:1", image_size="1K"),
    ),
)

final_image = None
for part in response.parts:
    if getattr(part, "thought", False):
        continue
    if part.text:
        print(part.text)
    elif image := part.as_image():
        final_image = image

if final_image:
    final_image.save("output.png")

{
  "candidates": [
    {
      "content": {
        "role": "<string>",
        "parts": [
          {
            "text": "<string>",
            "inlineData": {
              "mimeType": "<string>",
              "data": "<string>"
            },
            "thought": true,
            "thoughtSignature": "<string>"
          }
        ]
      },
      "index": 123,
      "safetyRatings": [
        {
          "category": "<string>",
          "probability": "<string>"
        }
      ]
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 123,
    "totalTokenCount": 123,
    "thoughtsTokenCount": 123
  }
}

内容审核

API 密钥

授权

路径参数

请求体

响应