Generating and Editing images

See Live Demo built using these code snippets

Typescript
Python

import { GoogleGenerativeAI } from "@google/generative-ai";

const genAI = new GoogleGenerativeAI(process.env.GEMINI_API_KEY);
const model = genAI.getGenerativeModel({
  model: "gemini-2.0-flash-exp",
  generationConfig: {
    responseModalities: ["text", "image"],
  },
});

const prompt = 'Hi, can you create a 3d rendered image of a pig ' +
               'with wings and a top hat flying over a happy ' +
               'futuristic scifi city with lots of greenery?';

const result = await model.generateContent({
  contents: [{ role: "user", parts: [{ text: prompt }] }],
});

result.response.candidates[0].content.parts.forEach(part => {
  if (part.text) {
    console.log(part.text);
  } else if (part.inlineData) {
    const img = document.createElement('img');
    img.src = `data:${part.inlineData.mimeType};base64,${part.inlineData.data}`;
    document.body.appendChild(img);
  }
});

from google import genai
from google.genai import types
from PIL import Image
from io import BytesIO

client = genai.Client()

contents = ('Hi, can you create a 3d rendered image of a pig '
            'with wings and a top hat flying over a happy ' 
            'futuristic scifi city with lots of greenery?')

response = client.models.generate_content(
    model="models/gemini-2.0-flash-exp",
    contents=contents,
    config=types.GenerateContentConfig(response_modalities=['Text', 'Image'])
)

for part in response.candidates[0].content.parts:
  if part.text is not None:
    print(part.text)
  elif part.inline_data is not None:
    image = Image.open(BytesIO(part.inline_data.data))
    image.show()

Edit an image

Typescript
Python

const genAI = new GoogleGenerativeAI(apiKey);
const model = genAI.getGenerativeModel({
  model: "gemini-2.0-flash-exp",
  generationConfig: {
    responseModalities: ["text", "image"],
  },
});

const base64Data = result.split(',')[1];
const byteCharacters = atob(base64Data);
const byteNumbers = new Array(byteCharacters.length);
for (let i = 0; i < byteCharacters.length; i++) {
  byteNumbers[i] = byteCharacters.charCodeAt(i);
}
const byteArray = new Uint8Array(byteNumbers);
const blob = new Blob([byteArray], { type: result.split(';')[0].split(':')[1] });

const buffer = await blob.arrayBuffer();
const base64 = btoa(
  new Uint8Array(buffer).reduce((data, byte) => data + String.fromCharCode(byte), '')
);

const response = await model.generateContent([
  "Remove the lemons from the image",
  {
    inlineData: {
      mimeType: blob.type,
      data: base64
    }
  }
]);

response.response.candidates[0].content.parts.forEach(part => {
  if (part.text) {
    console.log(part.text);
  } else if (part.inlineData) {
    setResult(`data:${part.inlineData.mimeType};base64,${part.inlineData.data}`);
  }
});

from google import genai
from PIL import Image

# Initialize the model
model = genai.GenerativeModel("gemini-2.0-flash-exp")

def edit_image(image_path, edit_prompt):
    image = Image.open(image_path)
    response = model.generate_content(
        [edit_prompt, image],
        config=genai.types.GenerateContentConfig(
            response_modalities=['Text', 'Image']
        )
    )

    for part in response.candidates[0].content.parts:
        if part.text is not None:
            print(part.text)
        elif part.inline_data is not None:
            # Display or save the edited image
            edited_image = Image.open(BytesIO(part.inline_data.data))
            edited_image.show()
            

Edit an image​

Edit an image