跳转到主要内容
本指南演示如何通过 CometAPI 使用 Google Gen AI SDK 调用 Gemini 图像模型。内容涵盖:
  • 文生图
  • 图像到图像编辑
  • 多图合成
  • 保存生成的图像
  • 基础 URL: https://api.cometapi.com
  • 安装 SDK:pip install google-genai(Python)或 npm install @google/genai(Node.js)

设置

使用 CometAPI 的基础 URL 初始化客户端:
from google import genai
from google.genai import types
import os

COMETAPI_KEY = os.environ.get("COMETAPI_KEY") or "<YOUR_COMETAPI_KEY>"

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

文本到图像生成

根据文本 Prompt 生成图像并将其保存到文件中。
from google import genai
from google.genai import types
from PIL import Image
import os

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-image-preview",
    contents="Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme",
    config=types.GenerateContentConfig(
        response_modalities=["TEXT", "IMAGE"],
    ),
)

for part in response.parts:
    if part.text is not None:
        print(part.text)
    elif part.inline_data is not None:
        image = part.as_image()
        image.save("generated_image.png")
        print("Image saved to generated_image.png")
响应结构: 图像数据位于 candidates[0].content.parts 中,其中可以包含文本部分和/或图像部分:
{
  "candidates": [{
    "content": {
      "parts": [
        { "text": "Here is your image..." },
        {
          "inlineData": {
            "mimeType": "image/png",
            "data": "<base64-encoded-image>"
          }
        }
      ]
    }
  }]
}

图生图生成

上传一张输入图片,并通过文本 Prompt 对其进行转换。
from google import genai
from google.genai import types
from PIL import Image
import os

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

# Load the source image
source_image = Image.open("source.jpg")

response = client.models.generate_content(
    model="gemini-3.1-flash-image-preview",
    contents=["Transform this into a watercolor painting", source_image],
    config=types.GenerateContentConfig(
        response_modalities=["TEXT", "IMAGE"],
    ),
)

for part in response.parts:
    if part.text is not None:
        print(part.text)
    elif part.inline_data is not None:
        image = part.as_image()
        image.save("watercolor_output.png")
  • Python SDK 可直接接受 PIL.Image 对象——无需手动进行 Base64 编码。
  • 传递原始 Base64 字符串时,不要包含 data:image/jpeg;base64, 前缀。

多图像合成

从多个输入图像生成一张新图像。CometAPI 支持两种方式:

方法 1:单张拼贴图

将多张源图像合并为一张拼贴图,然后描述期望的输出效果。
输入拼贴图示例
生成结果
from google import genai
from google.genai import types
from PIL import Image
import os

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

collage = Image.open("collage.jpg")

response = client.models.generate_content(
    model="gemini-3.1-flash-image-preview",
    contents=[
        "A model is posing and leaning against a pink BMW with a green alien keychain attached to a pink handbag, a pink parrot on her shoulder, and a pug wearing a pink collar and gold headphones",
        collage,
    ],
    config=types.GenerateContentConfig(
        response_modalities=["TEXT", "IMAGE"],
    ),
)

for part in response.parts:
    if part.inline_data is not None:
        part.as_image().save("composition_output.png")

方法 2:多张独立图像(最多 14 张)

直接传入多张图像。Gemini 3 模型最多支持 14 张参考图像(对象 + 角色):
from google import genai
from google.genai import types
from PIL import Image
import os

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

image1 = Image.open("image1.jpg")
image2 = Image.open("image2.jpg")
image3 = Image.open("image3.jpg")

response = client.models.generate_content(
    model="gemini-3.1-flash-image-preview",
    contents=["Merge the three images", image1, image2, image3],
    config=types.GenerateContentConfig(
        response_modalities=["TEXT", "IMAGE"],
    ),
)

for part in response.parts:
    if part.inline_data is not None:
        part.as_image().save("merged_output.png")
多图像生成结果

4K 图像生成

指定带有 aspect_ratioimage_sizeimage_config 以获得高分辨率输出:
from google import genai
from google.genai import types
import os

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-image-preview",
    contents="Da Vinci style anatomical sketch of a Monarch butterfly on textured parchment",
    config=types.GenerateContentConfig(
        response_modalities=["TEXT", "IMAGE"],
        image_config=types.ImageConfig(
            aspect_ratio="1:1",
            image_size="4K",
        ),
    ),
)

for part in response.parts:
    if part.text is not None:
        print(part.text)
    elif image := part.as_image():
        image.save("butterfly_4k.png")

多轮图像编辑(Chat)

使用 SDK 的 chat 功能对图像进行迭代优化:
from google import genai
from google.genai import types
import os

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

chat = client.chats.create(
    model="gemini-3.1-flash-image-preview",
    config=types.GenerateContentConfig(
        response_modalities=["TEXT", "IMAGE"],
    ),
)

# First turn: generate
response = chat.send_message(
    "Create a vibrant infographic explaining photosynthesis as a recipe, styled like a colorful kids cookbook"
)

for part in response.parts:
    if part.text is not None:
        print(part.text)
    elif image := part.as_image():
        image.save("photosynthesis.png")

# Second turn: refine
response = chat.send_message("Update this infographic to be in Spanish. Do not change any other elements.")

for part in response.parts:
    if part.text is not None:
        print(part.text)
    elif image := part.as_image():
        image.save("photosynthesis_spanish.png")

提示

指定风格关键词(例如:“cyberpunk、film grain、low contrast”)、宽高比、主体、背景、光照和细节级别。
使用原始 HTTP 时,不要包含 data:image/png;base64, 前缀——只使用原始 Base64 字符串。Python SDK 会通过 PIL.Image 对象自动处理这一点。
"responseModalities" 仅设置为 ["IMAGE"],即可保证只输出图像而不包含文本。
更多详情,请参阅 API 参考 官方文档: Gemini 图像生成