Hasilkan gambar dengan Gemini

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
  }
}

Untuk contoh langkah demi langkah, lihat Gunakan model gambar Gemini.

Opsi pembuatan gambar Gemini dapat berubah saat Google memperbarui model gambar dan generateContent. Periksa dokumentasi pembuatan gambar Gemini untuk daftar parameter lengkap terbaru dan perilaku khusus penyedia.

gemini-2.5-flash-image dijadwalkan untuk dihentikan oleh penyedia pada 2026-10-02. Untuk proyek baru, gunakan gemini-3.1-flash-image-preview atau gemini-3-pro-image-preview. Lihat jadwal deprekasi Google untuk detailnya.

Respons gambar Gemini dapat menyertakan bagian gambar perantara saat thought bernilai true. Ini bukan output akhir. Saat menyimpan gambar yang dihasilkan, lewati bagian thought: true dan gunakan bagian gambar terakhir yang memiliki inlineData dan thought tidak bernilai true.

Otorisasi

Authorization

string

header

wajib

Use your CometAPI API key.

Parameter Path

model

string

default:gemini-3.1-flash-image-preview

wajib

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

Body

application/json

contents

object[]

wajib

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

Respons

200 - application/json

Success

candidates

object[]

Show child attributes

usageMetadata

object

Show child attributes

Buat edit gambar

Sebelumnya

Menggunakan model gambar Gemini

Selanjutnya

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
  }
}

Moderasi konten

Kunci API

Otorisasi

Parameter Path

Body

Respons