Use Gemini image models

This guide demonstrates how to use Gemini image models via CometAPI using the Google Gen AI SDK. It covers:

Text-to-image generation
Image-to-image editing
Multi-image composition
Saving generated images

Base URL: https://api.cometapi.com
Install the SDK: pip install google-genai (Python) or npm install @google/genai (Node.js)

Setup

Initialize the client with CometAPI’s 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...
}

Text-to-image generation

Generate an image from a text prompt and save it to a file.

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"]
    }
  }'

Save the final image part: The image data is in candidates[0].content.parts, which can contain text and/or image parts. Gemini image models can also return intermediate thought parts before the final image, especially when you request both text and images or explicitly enable thinking output. Do not save the first inlineData blindly; skip parts where thought is true, then save the last remaining image part. Typical response with only the final image:

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

Response with a text part, an intermediate thought image, and the final image:

{
  "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"
  }]
}

Use this parsing rule for every Gemini image response:

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

Image-to-image generation

Upload an input image and transform it with a text 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"] }
  }'

The Python SDK accepts PIL.Image objects directly — no manual Base64 encoding needed.
Do not include the data:image/jpeg;base64, prefix when passing raw Base64 strings.

Multi-image composition

Generate a new image from multiple input images. CometAPI supports two approaches:

Method 1: Single collage image

Combine multiple source images into one collage, then describe the desired output.

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"] }
  }'

Method 2: Multiple separate images (up to 14)

Pass multiple images directly. Gemini 3 models support up to 14 reference images (objects + characters):

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"] }
  }'

4K image generation

Specify image_config with aspect_ratio and image_size for high-resolution output:

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 high-resolution requests, judge the output by the final non-thought image part. If your integration saves the first inlineData part, it may save an intermediate thought image that is lower resolution than the requested imageSize.

Multi-turn image editing (chat)

Use the SDK’s chat feature to iteratively refine images:

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")

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

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_spanish.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 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 Optimization

Specify style keywords (e.g., “cyberpunk, film grain, low contrast”), aspect ratio, subject, background, lighting, and detail level.

Base64 Format

When using raw HTTP, do not include data:image/png;base64, prefix — use only the raw Base64 string. The Python SDK handles this automatically with PIL.Image objects.

Force Image Output

Set "responseModalities" to ["IMAGE"] only to guarantee image output without text.

Why is my image blurry or lower resolution?

Check whether your code saved an intermediate thought image. Gemini image responses may include image parts where thought is true; these are not the final output. Skip thought: true parts and save the last image part where inlineData exists and thought is not true. If you do not need text output, request "responseModalities": ["IMAGE"] to reduce mixed text/image response handling.

For more details, see the API Reference. Official documentation: Nano Banana image generation

Gemini Image Understanding

Content moderation

API keys

Setup

Text-to-image generation

Image-to-image generation

Multi-image composition

Method 1: Single collage image

Method 2: Multiple separate images (up to 14)

4K image generation

Multi-turn image editing (chat)

Tips

​Setup

​Text-to-image generation

​Image-to-image generation

​Multi-image composition

​Method 1: Single collage image

​Method 2: Multiple separate images (up to 14)

​4K image generation

​Multi-turn image editing (chat)

​Tips

Setup

Text-to-image generation

Image-to-image generation

Multi-image composition

Method 1: Single collage image

Method 2: Multiple separate images (up to 14)

4K image generation

Multi-turn image editing (chat)

Tips