Bruk Gemini-bildemodeller

Denne veiledningen viser hvordan du bruker Gemini-bildemodeller via CometAPI med Google Gen AI SDK. Den dekker:

Tekst-til-bilde-generering
Bilde-til-bilde-redigering
Komposisjon med flere bilder
Lagring av genererte bilder

Base URL: https://api.cometapi.com
Installer SDK-en: pip install google-genai (Python) eller npm install @google/genai (Node.js)

Oppsett

Initialiser klienten med CometAPIs base URL:

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

COMETAPI_KEY = os.environ["COMETAPI_KEY"]

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

import { GoogleGenAI } from "@google/genai";

const COMETAPI_KEY = process.env.COMETAPI_KEY;

const ai = new GoogleGenAI({
  apiKey: COMETAPI_KEY,
  httpOptions: { apiVersion: "v1beta", baseUrl: "https://api.cometapi.com" },
});

package main

import (
	"context"
	"os"
	"google.golang.org/genai"
)

func main() {
	ctx := context.Background()
	apiKey := os.Getenv("COMETAPI_KEY")

	client, _ := genai.NewClient(ctx, &genai.ClientConfig{
		APIKey:  apiKey,
		Backend: genai.BackendGeminiAPI,
		HTTPOptions: genai.HTTPOptions{
			BaseURL: "https://api.cometapi.com",
		},
	})
	// use client below...
}

Tekst-til-bilde-generering

Generer et bilde fra en tekst Prompt og lagre det til en fil.

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"],
    ),
)

final_image = None
for part in response.parts:
    if getattr(part, "thought", False):
        continue
    if part.text is not None:
        print(part.text)
    elif part.inline_data is not None:
        final_image = part.as_image()

if final_image:
    final_image.save("generated_image.png")
    print("Image saved to generated_image.png")

import { GoogleGenAI } from "@google/genai";
import * as fs from "fs";

const ai = new GoogleGenAI({
  apiKey: process.env.COMETAPI_KEY,
  httpOptions: { apiVersion: "v1beta", baseUrl: "https://api.cometapi.com" },
});

const response = await ai.models.generateContent({
  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: { responseModalities: ["TEXT", "IMAGE"] },
});

let finalImagePart;
for (const part of response.candidates[0].content.parts) {
  if (part.thought === true) {
    continue;
  }
  if (part.text) {
    console.log(part.text);
  }
  if (part.inlineData) {
    finalImagePart = part;
  }
}

if (finalImagePart) {
  const buffer = Buffer.from(finalImagePart.inlineData.data, "base64");
  fs.writeFileSync("generated_image.png", buffer);
  console.log("Image saved to generated_image.png");
}

curl -s -X POST \
  "https://api.cometapi.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "parts": [{"text": "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme"}]
    }],
    "generationConfig": {
      "responseModalities": ["TEXT", "IMAGE"]
    }
  }'

Lagre den endelige bildedelen: Bildedataene ligger i candidates[0].content.parts, som kan inneholde tekst- og/eller bildedeler. Gemini-bildemodeller kan også returnere mellomliggende thought-deler før det endelige bildet, spesielt når du ber om både tekst og bilder eller eksplisitt aktiverer thinking-utdata. Ikke lagre den første inlineData blindt; hopp over deler der thought er true, og lagre deretter den siste gjenværende bildedelen. Typisk respons med bare det endelige bildet:

{
  "candidates": [{
    "content": {
      "parts": [
        { "text": "Here is your image..." },
        {
          "inlineData": {
            "mimeType": "image/png",
            "data": "<base64-encoded-image>"
          }
        }
      ]
    }
  }]
}

Respons med en tekstdel, et mellomliggende thought-bilde og det endelige bildet:

{
  "candidates": [{
    "content": {
      "role": "model",
      "parts": [
        { "text": "Here is your image..." },
        {
          "inlineData": {
            "mimeType": "image/jpeg",
            "data": "<base64-encoded-intermediate-image>"
          },
          "thought": true
        },
        {
          "inlineData": {
            "mimeType": "image/jpeg",
            "data": "<base64-encoded-final-image>"
          },
          "thought": false,
          "thoughtSignature": "<signature>"
        }
      ]
    },
    "finishReason": "STOP"
  }]
}

Bruk denne parseregelen for hver Gemini-bilderespons:

const imageParts = response.candidates[0].content.parts.filter(
  (part) => part.inlineData && part.thought !== true,
);
const finalImagePart = imageParts.at(-1);

Bilde-til-bilde-generering

Last opp et inndatabilde og transformer det med en tekst-Prompt.

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"],
    ),
)

final_image = None
for part in response.parts:
    if getattr(part, "thought", False):
        continue
    if part.text is not None:
        print(part.text)
    elif part.inline_data is not None:
        final_image = part.as_image()

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

import { GoogleGenAI } from "@google/genai";
import * as fs from "fs";

const ai = new GoogleGenAI({
  apiKey: process.env.COMETAPI_KEY,
  httpOptions: { apiVersion: "v1beta", baseUrl: "https://api.cometapi.com" },
});

const imageData = fs.readFileSync("source.jpg").toString("base64");

const response = await ai.models.generateContent({
  model: "gemini-3.1-flash-image-preview",
  contents: [
    { text: "Transform this into a watercolor painting" },
    { inlineData: { mimeType: "image/jpeg", data: imageData } },
  ],
  config: { responseModalities: ["TEXT", "IMAGE"] },
});

const imageParts = response.candidates[0].content.parts.filter(
  (part) => part.inlineData && part.thought !== true,
);
const finalImagePart = imageParts.at(-1);

if (finalImagePart) {
  fs.writeFileSync("watercolor_output.png", Buffer.from(finalImagePart.inlineData.data, "base64"));
}

curl -s -X POST \
  "https://api.cometapi.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [
        { "text": "Transform this into a watercolor painting" },
        { "inline_data": { "mime_type": "image/jpeg", "data": "<base64-encoded-source-image>" } }
      ]
    }],
    "generationConfig": { "responseModalities": ["TEXT", "IMAGE"] }
  }'

Python SDK-en godtar PIL.Image-objekter direkte — ingen manuell Base64-koding er nødvendig.
Ikke inkluder prefikset data:image/jpeg;base64, når du sender rå Base64-strenger.

Komponering med flere bilder

Generer et nytt bilde fra flere inndatabilder. CometAPI støtter to tilnærminger:

Metode 1: Ett kollasjbilde

Kombiner flere kildebilder til én kollasj, og beskriv deretter ønsket utdata.

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"],
    ),
)

final_image = None
for part in response.parts:
    if getattr(part, "thought", False):
        continue
    if part.inline_data is not None:
        final_image = part.as_image()

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

curl -s -X POST \
  "https://api.cometapi.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [
        { "text": "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" },
        { "inline_data": { "mime_type": "image/jpeg", "data": "<base64-encoded-collage-image>" } }
      ]
    }],
    "generationConfig": { "responseModalities": ["TEXT", "IMAGE"] }
  }'

Metode 2: Flere separate bilder (opptil 14)

Send flere bilder direkte. Gemini 3-modeller støtter opptil 14 referansebilder (objekter + karakterer):

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"],
    ),
)

final_image = None
for part in response.parts:
    if getattr(part, "thought", False):
        continue
    if part.inline_data is not None:
        final_image = part.as_image()

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

curl -s -X POST \
  "https://api.cometapi.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [
        { "text": "Merge the three images" },
        { "inline_data": { "mime_type": "image/jpeg", "data": "<base64-image-1>" } },
        { "inline_data": { "mime_type": "image/jpeg", "data": "<base64-image-2>" } },
        { "inline_data": { "mime_type": "image/jpeg", "data": "<base64-image-3>" } }
      ]
    }],
    "generationConfig": { "responseModalities": ["TEXT", "IMAGE"] }
  }'

Resultat for generering med flere bilder

4K-bildegenerering

Spesifiser image_config med aspect_ratio og image_size for høyoppløselig utdata:

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",
        ),
    ),
)

final_image = None
for part in response.parts:
    if getattr(part, "thought", False):
        continue
    if part.text is not None:
        print(part.text)
    elif image := part.as_image():
        final_image = image

if final_image:
    final_image.save("butterfly_4k.png")

import { GoogleGenAI } from "@google/genai";
import * as fs from "fs";

const ai = new GoogleGenAI({
  apiKey: process.env.COMETAPI_KEY,
  httpOptions: { apiVersion: "v1beta", baseUrl: "https://api.cometapi.com" },
});

const response = await ai.models.generateContent({
  model: "gemini-3.1-flash-image-preview",
  contents: "Da Vinci style anatomical sketch of a Monarch butterfly on textured parchment",
  config: {
    responseModalities: ["TEXT", "IMAGE"],
    imageConfig: { aspectRatio: "1:1", imageSize: "4K" },
  },
});

const imageParts = response.candidates[0].content.parts.filter(
  (part) => part.inlineData && part.thought !== true,
);
const finalImagePart = imageParts.at(-1);

if (finalImagePart) {
  fs.writeFileSync("butterfly_4k.png", Buffer.from(finalImagePart.inlineData.data, "base64"));
}

curl -s -X POST \
  "https://api.cometapi.com/v1beta/models/gemini-3.1-flash-image-preview:generateContent" \
  -H "Authorization: Bearer $COMETAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [{"parts": [{"text": "Da Vinci style anatomical sketch of a Monarch butterfly on textured parchment"}]}],
    "generationConfig": {
      "responseModalities": ["TEXT", "IMAGE"],
      "imageConfig": {"aspectRatio": "1:1", "imageSize": "4K"}
    }
  }'

For høyoppløselige forespørsler bør du vurdere resultatet ut fra den siste ikke-thought-bildedelen. Hvis integrasjonen din lagrer den første inlineData-delen, kan den lagre et mellomliggende thought-bilde med lavere oppløsning enn den forespurte imageSize.

Flerturns bilderedigering (chat)

Bruk SDK-ens chat-funksjon til å forbedre bilder iterativt:

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"
)

final_image = None
for part in response.parts:
    if getattr(part, "thought", False):
        continue
    if part.text is not None:
        print(part.text)
    elif image := part.as_image():
        final_image = image

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

```javascript Node.js
import { GoogleGenAI } from "@google/genai";
import * as fs from "fs";

const ai = new GoogleGenAI({
  apiKey: process.env.COMETAPI_KEY,
  httpOptions: { apiVersion: "v1beta", baseUrl: "https://api.cometapi.com" },
});

const chat = ai.chats.create({
  model: "gemini-3.1-flash-image-preview",
  config: { responseModalities: ["TEXT", "IMAGE"] },
});

// First turn: generate
const response1 = await chat.sendMessage(
  "Create a vibrant infographic explaining photosynthesis as a recipe, styled like a colorful kids cookbook"
);
const imageParts1 = response1.candidates[0].content.parts.filter(
  (part) => part.inlineData && part.thought !== true,
);
const finalImagePart1 = imageParts1.at(-1);
if (finalImagePart1) {
  fs.writeFileSync("photosynthesis.png", Buffer.from(finalImagePart1.inlineData.data, "base64"));
}

// Second turn: refine
const response2 = await chat.sendMessage(
  "Update this infographic to be in Spanish. Do not change any other elements."
);
const imageParts2 = response2.candidates[0].content.parts.filter(
  (part) => part.inlineData && part.thought !== true,
);
const finalImagePart2 = imageParts2.at(-1);
if (finalImagePart2) {
  fs.writeFileSync("photosynthesis_spanish.png", Buffer.from(finalImagePart2.inlineData.data, "base64"));
}

Tips

Prompt-optimalisering

Spesifiser stilnøkkelord (f.eks. “cyberpunk, film grain, low contrast”), sideforhold, motiv, bakgrunn, belysning og detaljnivå.

Base64-format

Når du bruker rå HTTP, ikke inkluder prefikset data:image/png;base64, — bruk bare den rå Base64-strengen. Python SDK håndterer dette automatisk med PIL.Image-objekter.

Tving bildeutdata

Sett "responseModalities" til bare ["IMAGE"] for å garantere bildeutdata uten tekst.

Hvorfor er bildet mitt uskarpt eller i lavere oppløsning?

Sjekk om koden din lagret et mellomliggende thought-bilde. Gemini-bildesvar kan inkludere bildedeler der thought er true; disse er ikke den endelige utdataen. Hopp over deler med thought: true og lagre den siste bildedelen der inlineData finnes og thought ikke er true. Hvis du ikke trenger tekstutdata, be om "responseModalities": ["IMAGE"] for å redusere håndtering av blandede tekst-/bildesvar.

For flere detaljer, se API-referansen. Offisiell dokumentasjon: Nano Banana-bildegenerering

Gemini bildeforståelse

Innholdsmoderering

API-nøkler

Oppsett

Tekst-til-bilde-generering

Bilde-til-bilde-generering

Komponering med flere bilder

Metode 1: Ett kollasjbilde

Metode 2: Flere separate bilder (opptil 14)

4K-bildegenerering

Flerturns bilderedigering (chat)

Tips

​Oppsett

​Tekst-til-bilde-generering

​Bilde-til-bilde-generering

​Komponering med flere bilder

​Metode 1: Ett kollasjbilde

​Metode 2: Flere separate bilder (opptil 14)

​4K-bildegenerering

​Flerturns bilderedigering (chat)

​Tips

Oppsett

Tekst-til-bilde-generering

Bilde-til-bilde-generering

Komponering med flere bilder

Metode 1: Ett kollasjbilde

Metode 2: Flere separate bilder (opptil 14)

4K-bildegenerering

Flerturns bilderedigering (chat)

Tips