Generer bilder med 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>"
          }
        ]
      },
      "finishReason": "STOP",
      "index": 123,
      "safetyRatings": [
        {
          "category": "<string>",
          "probability": "<string>"
        }
      ]
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 123,
    "totalTokenCount": 123,
    "thoughtsTokenCount": 123
  }
}

For trinnvise eksempler, se Bruk Gemini-bildemodeller.

Alternativene for Gemini-bildegenerering kan endres når Google oppdaterer bildemodeller og generateContent. Sjekk dokumentasjonen for Gemini-bildegenerering for den nyeste komplette parameterlisten og leverandørspesifikk oppførsel.

gemini-2.5-flash-image er planlagt avviklet av leverandøren 2026-10-02. For nye prosjekter, bruk gemini-3.1-flash-image-preview eller gemini-3-pro-image-preview. Se Googles deprecation schedule for detaljer.

Gemini-bilderesponser kan inkludere mellomliggende bildedeler der thought er true. Disse er ikke det endelige resultatet. Når du lagrer genererte bilder, hopp over deler med thought: true og bruk den siste bildedelen der inlineData finnes og thought ikke er true.

Autorisasjoner

Authorization

string

header

påkrevd

Use your CometAPI API key.

Stien-parametere

model

string

standard:gemini-3.1-flash-image-preview

påkrevd

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

Kropp

application/json

contents

object[]

påkrevd

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

Svar

200 - application/json

Success

candidates

object[]

Show child attributes

usageMetadata

object

Show child attributes

Sist endret 3. juli 2026

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>"
          }
        ]
      },
      "finishReason": "STOP",
      "index": 123,
      "safetyRatings": [
        {
          "category": "<string>",
          "probability": "<string>"
        }
      ]
    }
  ],
  "usageMetadata": {
    "promptTokenCount": 123,
    "candidatesTokenCount": 123,
    "totalTokenCount": 123,
    "thoughtsTokenCount": 123
  }
}

Innholdsmoderering

API-nøkler

Autorisasjoner

Stien-parametere

Kropp

Svar