Nano Banana 圖像生成功能

from google import genai
from PIL import Image
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme",
)

with open("generated_image.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

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

async function main() {

  const ai = new GoogleGenAI({});

  const prompt =
    "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme";

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: prompt,
  });
  const generatedImage = interaction.output_image;
  if (generatedImage) {
    const buffer = Buffer.from(generatedImage.data, "base64");
    fs.writeFileSync("gemini-native-image.png", buffer);
    console.log("Image saved as gemini-native-image.png");
  }
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": [
      {"type": "text", "text": "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme"}
    ]
  }'

from google import genai
from PIL import Image
import base64

client = genai.Client()

with open("/path/to/cat_image.png", "rb") as f:
    image_bytes = f.read()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=[
        {
          "type": "text",
          "text": "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme"
        },
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        }
    ],
)

with open("generated_image.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

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

async function main() {

  const ai = new GoogleGenAI({});

  const imagePath = "path/to/cat_image.png";
  const imageData = fs.readFileSync(imagePath);
  const base64Image = imageData.toString("base64");

  const prompt = [
    { type: "text", text: "Create a picture of my cat eating a nano-banana in a" +
            "fancy restaurant under the Gemini constellation" },
    {
      type: "image",
      mime_type: "image/png",
      data: base64Image
    },
  ];

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: prompt,
  });
  const generatedImage = interaction.output_image;
  if (generatedImage) {
    const buffer = Buffer.from(generatedImage.data, "base64");
    fs.writeFileSync("gemini-native-image.png", buffer);
    console.log("Image saved as gemini-native-image.png");
  }
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d "{
      \"model\": \"gemini-3.1-flash-image\",
      \"input\": [
        {\"type\": \"text\", \"text\": \"Create a picture of my cat eating a nano-banana in a fancy restaurant under the Gemini constellation\"},
        {
          \"type\": \"image\",
          \"mime_type\": \"image/jpeg\",
          \"data\": \"<BASE64_IMAGE_DATA>\"
        }
      ]
    }"

from google import genai
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plant's favorite food. Show the \"ingredients\" (sunlight, water, CO2) and the \"finished dish\" (sugar/energy). The style should be like a page from a colorful kids' cookbook, suitable for a 4th grader.",
    tools=[{"type": "google_search"}],
)

with open("photosynthesis.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

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

const ai = new GoogleGenAI({});

async function main() {
  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plant's favorite food. Show the \"ingredients\" (sunlight, water, CO2) and the \"finished dish\" (sugar/energy). The style should be like a page from a colorful kids' cookbook, suitable for a 4th grader.",
    tools: [{"type": "google_search"}],
  });

  const generatedImage = interaction.output_image;
  if (generatedImage) {
    const buffer = Buffer.from(generatedImage.data, "base64");
    fs.writeFileSync("photosynthesis.png", buffer);
    console.log("Image saved as photosynthesis.png");
  }
}

await main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": [
      {"type": "text", "text": "Create a vibrant infographic that explains photosynthesis as if it were a recipe for a plants favorite food. Show the \"ingredients\" (sunlight, water, CO2) and the \"finished dish\" (sugar/energy). The style should be like a page from a colorful kids cookbook, suitable for a 4th grader."}
    ],
    "tools": [{"type": "google_search"}]
  }'

interaction_2 = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="Update this infographic to be in Spanish. Do not change any other elements of the image.",
    previous_interaction_id=interaction.id,
    response_format={
        "type": "image",
        "mime_type": "image/jpeg",
        "aspect_ratio": "16:9",
        "image_size": "2K"
    },
)

generated_image = interaction_2.output_image
if generated_image:
    with open("photosynthesis_spanish.png", "wb") as f:
        f.write(base64.b64decode(generated_image.data))

const interaction2 = await ai.interactions.create({
  model: "gemini-3.1-flash-image",
  input: "Update this infographic to be in Spanish. Do not change any other elements of the image.",
  previous_interaction_id: interaction.id,
  response_format: {
    type: "image",
    mime_type: "image/png",
    aspect_ratio: "16:9",
    image_size: "2K"
  },
});

const generatedImage = interaction2.output_image;
if (generatedImage) {
  const buffer = Buffer.from(generatedImage.data, "base64");
  fs.writeFileSync("photosynthesis_spanish.png", buffer);
}

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "Update this infographic to be in Spanish. Do not change any other elements of the image.",
    "previous_interaction_id": "<PREVIOUS_INTERACTION_ID>",
    "response_format": {
      "type": "image",
      "mime_type": "image/jpeg",
      "aspect_ratio": "16:9",
      "image_size": "2K"
    }
  }'

from google import genai
from google.genai import types
from PIL import Image
import base64

prompt = "An office group photo of these people, they are making funny faces."

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=[
        {
            "type": "text",
            "text": prompt,
        },
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        },
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        },
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        },
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        },
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        },
    ],
    response_format={
        "type": "image",
        "aspect_ratio": "5:4",
        "image_size": "2K"
    },
)

with open("office.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

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

async function main() {
  const ai = new GoogleGenAI({});

  const input = [
    {
      type: "text",
      text: "An office group photo of these people, they are making funny faces.",
    },
    { type: "image", mime_type: "image/jpeg", data: base64ImageFile1 },
    { type: "image", mime_type: "image/jpeg", data: base64ImageFile2 },
    { type: "image", mime_type: "image/jpeg", data: base64ImageFile3 },
    { type: "image", mime_type: "image/jpeg", data: base64ImageFile4 },
    { type: "image", mime_type: "image/jpeg", data: base64ImageFile5 },
  ];

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: input,
    response_format: {
      type: "image",
      aspect_ratio: "5:4",
      image_size: "2K",
    },
  });

  const buffer = Buffer.from(interaction.output_image.data, 'base64');

  fs.writeFileSync('office.png', buffer);
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d "{
      \"model\": \"gemini-3.1-flash-image\",
      \"input\": [
        {\"type\": \"text\", \"text\": \"An office group photo of these people, they are making funny faces.\"},
        {\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_1>\"},
        {\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_2>\"},
        {\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_3>\"},
        {\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_4>\"},
        {\"type\": \"image\", \"mime_type\": \"image/png\", \"data\": \"<BASE64_DATA_IMG_5>\"}
      ],
      \"response_format\": {
        \"type\": \"image\",
        \"aspect_ratio\": \"5:4\",
        \"image_size\": \"2K\"
      }
    }"

from google import genai
from google.genai import types
import base64
prompt = "Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day"

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=prompt,
    tools=[{"type": "google_search"}],
    response_format={
        "type": "image",
        "mime_type": "image/jpeg",
        "aspect_ratio": "16:9"
    },
)

with open("weather.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day",
    tools: [{"type": "google_search"}],
    response_format: {
      type: "image",
      mime_type: "image/png",
      aspect_ratio: "16:9",
      image_size: "2K"
    },
  });

  const buffer = Buffer.from(interaction.output_image.data, 'base64');

  fs.writeFileSync('weather.png', buffer);
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": [
      {"type": "text", "text": "Visualize the current weather forecast for the next 5 days in San Francisco as a clean, modern weather chart. Add a visual on what I should wear each day"}
    ],
    "tools": [{"type": "google_search"}],
    "response_format": {
      "type": "image",
      "mime_type": "image/jpeg",
      "aspect_ratio": "16:9"
    }
  }'

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="A detailed painting of a Timareta butterfly resting on a flower",
    tools=[{
      "type": "google_search",
      "search_types": ["web_search", "image_search"]
    }]
)

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "A detailed painting of a Timareta butterfly resting on a flower",
    tools: [{
      "type": "google_search",
      "search_types": ["web_search", "image_search"]
    }]
  });
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "A detailed painting of a Timareta butterfly resting on a flower",
    "tools": [{"type": "google_search", "search_types": ["web_search", "image_search"]}]
  }'

from google import genai
from google.genai import types
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=[
        {
            "type": "video",
            "uri": "https://www.youtube.com/watch?v=UTdfxFyOQTI",
            "mime_type": "video/mp4"
        },
        {"type": "text", "text": "Generate a poster image that captures the key themes of this video."}
    ],
    response_format={"type": "image", "aspect_ratio": "16:9"}
)

# Save the generated image part
for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                with open("video_poster.png", "wb") as f:
                    f.write(base64.b64decode(content_block.data))
                print("Image saved as video_poster.png")

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: [
      {
        type: "video",
        uri: "https://www.youtube.com/watch?v=UTdfxFyOQTI",
        mime_type: "video/mp4"
      },
      { type: "text", text: "Generate a poster image that captures the key themes of this video." }
    ],
    response_format: {
      type: "image",
      aspect_ratio: "16:9"
    }
  });

  for (const step of interaction.steps) {
    if (step.type === "model_output") {
      for (const contentBlock of step.content) {
        if (contentBlock.type === "text") {
          console.log(contentBlock.text);
        } else if (contentBlock.type === "image") {
          const buffer = Buffer.from(contentBlock.data, "base64");
          fs.writeFileSync("video_poster.png", buffer);
          console.log("Image saved as video_poster.png");
        }
      }
    }
  }
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": [
      {
        "type": "video",
        "uri": "https://www.youtube.com/watch?v=UTdfxFyOQTI",
        "mime_type": "video/mp4"
      },
      {
        "type": "text",
        "text": "Generate a poster image that captures the key themes of this video."
      }
    ],
    "response_format": {
      "type": "image",
      "aspect_ratio": "16:9"
    }
  }'

from google import genai
from google.genai import types
import base64

prompt = "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English."

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=prompt,
    response_format={
        "type": "image",
        "mime_type": "image/jpeg",
        "aspect_ratio": "1:1",
        "image_size": "1K"
    },
)

print(interaction.output_text)

with open("butterfly.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English.",
    response_format: {
      type: "image",
      mime_type: "image/png",
      aspect_ratio: "1:1",
      image_size: "1K",
    },
  });

  console.log(interaction.output_text);

  const buffer = Buffer.from(interaction.output_image.data, 'base64');

  fs.writeFileSync('butterfly.png', buffer);
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "Da Vinci style anatomical sketch of a dissected Monarch butterfly. Detailed drawings of the head, wings, and legs on textured parchment with notes in English.",
    "response_format": {
      "type": "image",
      "mime_type": "image/jpeg",
      "aspect_ratio": "1:1",
      "image_size": "1K"
    }
  }'

for step in interaction.steps:
    if step.type == "thought":
        for content_block in step.summary:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                image = Image.open(io.BytesIO(base64.b64decode(content_block.data)))
                image.show()

for (const step of interaction.steps) {
  if (step.type === "thought") {
    for (const contentBlock of step.summary) {
      if (contentBlock.type === "text") {
        console.log(contentBlock.text);
      } else if (contentBlock.type === "image") {
        const buffer = Buffer.from(contentBlock.data, 'base64');
        fs.writeFileSync('thought_image.png', buffer);
      }
    }
  }
}

interaction = client.interactions.create(
    model="gemini-3-pro-image",
    input="Write the story of the lifecycle of a monarch butterfly, interleave illustrations",
)

image_counter = 1
for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                filename = f"butterfly_lifecycle_{image_counter}.png"
                with open(filename, "wb") as f:
                    f.write(base64.b64decode(content_block.data))
                print(f"\n[Saved illustration: {filename}]\n")
                image_counter += 1

const interaction = await ai.interactions.create({
    model: "gemini-3-pro-image",
    input: "Write the story of the lifecycle of a monarch butterfly, interleave illustrations",
});

let imageCounter = 1;
for (const step of interaction.steps) {
  if (step.type === "model_output") {
    for (const contentBlock of step.content) {
      if (contentBlock.type === "text") {
        console.log(contentBlock.text);
      } else if (contentBlock.type === "image") {
        const buffer = Buffer.from(contentBlock.data, "base64");
        const filename = `butterfly_lifecycle_${imageCounter}.png`;
        fs.writeFileSync(filename, buffer);
        console.log(`\n[Saved illustration: ${filename}]\n`);
        imageCounter++;
      }
    }
  }
}

from google import genai
from PIL import Image
import base64
import io

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="A futuristic city built inside a giant glass bottle floating in space",
    generation_config={"thinking_level": "high"},
)

print(interaction.output_text)

image = Image.open(io.BytesIO(base64.b64decode(interaction.output_image.data)))

image.show()

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "A futuristic city built inside a giant glass bottle floating in space",
    generation_config: { thinking_level: "high" },
  });

  console.log(interaction.output_text);

  const buffer = Buffer.from(interaction.output_image.data, 'base64');

  fs.writeFileSync('image.png', buffer);
}
main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "A futuristic city built inside a giant glass bottle floating in space",
    "generation_config": {
      "thinking_level": "high"
    }
  }'

A photorealistic [type of shot] of a [subject description] in a [setting
description]. [Description of the light]. Shot from a [camera angle]
with a [lens type].

A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.

from google import genai
from google.genai import types
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.",
    response_format=[
        {
            "type": "image",
            "mime_type": "image/jpeg",
            "aspect_ratio": "16:9",
        }
    ],
)

print(interaction.output_text)

with open("coral_reef.png", "wb") as f:

    f.write(base64.b64decode(interaction.output_image.data))

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.",
    response_format: [
      {
        type: "image",
        mime_type: "image/jpeg",
        aspect_ratio: "16:9",
      }
    ],
  });
  console.log(interaction.output_text);

  const buffer = Buffer.from(interaction.output_image.data, 'base64');

  fs.writeFileSync('coral_reef.png', buffer);
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "A photorealistic wide-angle shot of a vibrant coral reef teeming with tropical fish. Crystal-clear turquoise water with sunbeams filtering down from the surface, illuminating a sea turtle gliding gracefully over the coral. Shot from a low perspective with a wide-angle lens. Aspect ratio 16:9.",
    "response_format": {
      "type": "image",
      "mime_type": "image/png",
      "aspect_ratio": "16:9"
    }
  }'

A [style] of a [subject, with details about accessories or actions]
doing [activity]. The design features [visual qualities, e.g., bold outlines,
cel-shading, etc.] and [color/background preference].

A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white.

from google import genai
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white.",
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                with open("red_panda_sticker.png", "wb") as f:
                    f.write(base64.b64decode(content_block.data))

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It's munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white.",
  });
  for (const step of interaction.steps) {
    if (step.type === "model_output") {
      for (const contentBlock of step.content) {
        if (contentBlock.type === "text") {
          console.log(contentBlock.text);
        } else if (contentBlock.type === "image") {
          const buffer = Buffer.from(contentBlock.data, "base64");
          fs.writeFileSync("red_panda_sticker.png", buffer);
        }
      }
    }
  }
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "A kawaii-style sticker of a happy red panda wearing a tiny bamboo hat. It is munching on a green bamboo leaf. The design features bold, clean outlines, simple cel-shading, and a vibrant color palette. The background must be white."
  }'

Create a [image type] for [brand/concept] with the text "[text to render]"
in a [font style]. The design should be [style description], with a
[color scheme].

Create a modern, minimalist logo for a coffee shop called 'The Daily Grind'. The text should be in a clean, bold, sans-serif font. The color scheme is black and white. Put the logo in a circle. Use a coffee bean in a clever way.

from google import genai
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="Create a modern, minimalist logo for a coffee shop called 'The Daily Grind'. The text should be in a clean, bold, sans-serif font. The color scheme is black and white. Put the logo in a circle. Use a coffee bean in a clever way.",
    response_format={"type": "image", "aspect_ratio": "1:1"},
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                with open("logo_example.jpg", "wb") as f:
                    f.write(base64.b64decode(content_block.data))

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "Create a modern, minimalist logo for a coffee shop called 'The Daily Grind'. The text should be in a clean, bold, sans-serif font. The color scheme is black and white. Put the logo in a circle. Use a coffee bean in a clever way.",
    response_format: { type: "image", aspect_ratio: "1:1" },
  });
  for (const step of interaction.steps) {
    if (step.type === "model_output") {
      for (const contentBlock of step.content) {
        if (contentBlock.type === "text") {
          console.log(contentBlock.text);
        } else if (contentBlock.type === "image") {
          const buffer = Buffer.from(contentBlock.data, "base64");
          fs.writeFileSync("logo_example.jpg", buffer);
        }
      }
    }
  }
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "Create a modern, minimalist logo for a coffee shop called The Daily Grind. The text should be in a clean, bold, sans-serif font. The color scheme is black and white. Put the logo in a circle. Use a coffee bean in a clever way.",
    "response_format": {
      "type": "image",
      "aspect_ratio": "1:1"
    }
  }'

A high-resolution, studio-lit product photograph of a [product description]
on a [background surface/description]. The lighting is a [lighting setup,
e.g., three-point softbox setup] to [lighting purpose]. The camera angle is
a [angle type] to showcase [specific feature]. Ultra-realistic, with sharp
focus on [key detail]. [Aspect ratio].

A high-resolution, studio-lit product photograph of a minimalist ceramic
coffee mug in matte black, presented on a polished concrete surface. The
lighting is a three-point softbox setup designed to create soft, diffused
highlights and eliminate harsh shadows. The camera angle is a slightly
elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with
sharp focus on the steam rising from the coffee. Square image.

from google import genai
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface. The lighting is a three-point softbox setup designed to create soft, diffused highlights and eliminate harsh shadows. The camera angle is a slightly elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with sharp focus on the steam rising from the coffee. Square image.",
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                with open("product_mockup.png", "wb") as f:
                    f.write(base64.b64decode(content_block.data))

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface. The lighting is a three-point softbox setup designed to create soft, diffused highlights and eliminate harsh shadows. The camera angle is a slightly elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with sharp focus on the steam rising from the coffee. Square image.",
  });
  for (const step of interaction.steps) {
    if (step.type === "model_output") {
      for (const contentBlock of step.content) {
        if (contentBlock.type === "text") {
          console.log(contentBlock.text);
        } else if (contentBlock.type === "image") {
          const buffer = Buffer.from(contentBlock.data, "base64");
          fs.writeFileSync("product_mockup.png", buffer);
        }
      }
    }
  }
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "A high-resolution, studio-lit product photograph of a minimalist ceramic coffee mug in matte black, presented on a polished concrete surface. The lighting is a three-point softbox setup designed to create soft, diffused highlights and eliminate harsh shadows. The camera angle is a slightly elevated 45-degree shot to showcase its clean lines. Ultra-realistic, with sharp focus on the steam rising from the coffee. Square image."
  }'

A minimalist composition featuring a single [subject] positioned in the
[bottom-right/top-left/etc.] of the frame. The background is a vast, empty
[color] canvas, creating significant negative space. Soft, subtle lighting.
[Aspect ratio].

A minimalist composition featuring a single, delicate red maple leaf
positioned in the bottom-right of the frame. The background is a vast, empty
off-white canvas, creating significant negative space for text. Soft,
diffused lighting from the top left. Square image.

from google import genai
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas, creating significant negative space for text. Soft, diffused lighting from the top left. Square image.",
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                with open("minimalist_design.png", "wb") as f:
                    f.write(base64.b64decode(content_block.data))

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas, creating significant negative space for text. Soft, diffused lighting from the top left. Square image.",
  });
  for (const step of interaction.steps) {
    if (step.type === "model_output") {
      for (const contentBlock of step.content) {
        if (contentBlock.type === "text") {
          console.log(contentBlock.text);
        } else if (contentBlock.type === "image") {
          const buffer = Buffer.from(contentBlock.data, "base64");
          fs.writeFileSync("minimalist_design.png", buffer);
        }
      }
    }
  }
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "A minimalist composition featuring a single, delicate red maple leaf positioned in the bottom-right of the frame. The background is a vast, empty off-white canvas, creating significant negative space for text. Soft, diffused lighting from the top left. Square image."
  }'

Make a 3 panel comic in a [style]. Put the character in a [type of scene].

Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene.

from google import genai
from PIL import Image
import base64

client = genai.Client()

with open('/path/to/your/man_in_white_glasses.jpg', 'rb') as f:
    image_bytes = f.read()
text_input = "Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene."

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=[
        {"type": "text", "text": text_input},
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/jpeg"
        }
    ],
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                with open("comic_panel.jpg", "wb") as f:
                    f.write(base64.b64decode(content_block.data))

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

async function main() {
  const ai = new GoogleGenAI({});

  const imagePath = "/path/to/your/man_in_white_glasses.jpg";
  const imageData = fs.readFileSync(imagePath);
  const base64Image = imageData.toString("base64");

  const input = [
    { type: "text", text: "Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene." },
    {
      type: "image",
      mime_type: "image/jpeg",
      data: base64Image
    },
  ];

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: input,
  });
  for (const step of interaction.steps) {
    if (step.type === "model_output") {
      for (const contentBlock of step.content) {
        if (contentBlock.type === "text") {
          console.log(contentBlock.text);
        } else if (contentBlock.type === "image") {
          const buffer = Buffer.from(contentBlock.data, "base64");
          fs.writeFileSync("comic_panel.jpg", buffer);
        }
      }
    }
  }
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": [
      {"type": "text", "text": "Make a 3 panel comic in a gritty, noir art style with high-contrast black and white inks. Put the character in a humurous scene."},
      {"type": "image", "data": "<BASE64_IMAGE_DATA>", "mime_type": "image/jpeg"}
    ]
  }'

Make a simple but stylish graphic of last night's Arsenal game in the Champion's League

from google import genai
from google.genai import types
import base64

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input="Make a simple but stylish graphic of last night's Arsenal game in the Champion's League",
    tools=[{"type": "google_search"}],
    response_format={"type": "image", "aspect_ratio": "16:9"},
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                with open("football-score.jpg", "wb") as f:
                    f.write(base64.b64decode(content_block.data))

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

async function main() {
  const ai = new GoogleGenAI({});

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: "Make a simple but stylish graphic of last night's Arsenal game in the Champion's League",
    tools: [{ type: "google_search" }],
    response_format: { type: "image", aspect_ratio: "16:9", image_size: "2K" },
  });

  for (const step of interaction.steps) {
    if (step.type === "model_output") {
      for (const contentBlock of step.content) {
        if (contentBlock.type === "text") {
          console.log(contentBlock.text);
        } else if (contentBlock.type === "image") {
          const buffer = Buffer.from(contentBlock.data, "base64");
          fs.writeFileSync("football-score.jpg", buffer);
        }
      }
    }
  }
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-3.1-flash-image",
    "input": "Make a simple but stylish graphic of last nights Arsenal game in the Champions League",
    "tools": [{"type": "google_search"}],
    "response_format": {
      "type": "image",
      "aspect_ratio": "16:9"
    }
  }'

Using the provided image of [subject], please [add/remove/modify] [element]
to/from the scene. Ensure the change is [description of how the change should
integrate].

"Using the provided image of my cat, please add a small, knitted wizard hat
on its head. Make it look like it's sitting comfortably and matches the soft
lighting of the photo."

from google import genai
from PIL import Image
import base64

client = genai.Client()

with open('/path/to/your/cat_photo.png', 'rb') as f:
    image_bytes = f.read()
text_input = """Using the provided image of my cat, please add a small, knitted wizard hat on its head. Make it look like it's sitting comfortably and not falling off."""

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=[
        {"type": "text", "text": text_input},
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        }
    ],
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                with open("cat_with_hat.png", "wb") as f:
                    f.write(base64.b64decode(content_block.data))

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

async function main() {
  const ai = new GoogleGenAI({});

  const imagePath = "/path/to/your/cat_photo.png";
  const imageData = fs.readFileSync(imagePath);
  const base64Image = imageData.toString("base64");

  const input = [
    { type: "text", text: "Using the provided image of my cat, please add a small, knitted wizard hat on its head. Make it look like it's sitting comfortably and not falling off." },
    {
      type: "image",
      mime_type: "image/png",
      data: base64Image
    },
  ];

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: input,
  });
  for (const step of interaction.steps) {
    if (step.type === "model_output") {
      for (const contentBlock of step.content) {
        if (contentBlock.type === "text") {
          console.log(contentBlock.text);
        } else if (contentBlock.type === "image") {
          const buffer = Buffer.from(contentBlock.data, "base64");
          fs.writeFileSync("cat_with_hat.png", buffer);
        }
      }
    }
  }
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d "{
      \"model\": \"gemini-3.1-flash-image\",
      \"input\": [
            {\"type\": \"text\", \"text\": \"Using the provided image of my cat, please add a small, knitted wizard hat on its head. Make it look like it's sitting comfortably and not falling off.\"},
            {\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA>\"}
        ]
    }"

Using the provided image, change only the [specific element] to [new
element/description]. Keep everything else in the image exactly the same,
preserving the original style, lighting, and composition.

"Using the provided image of a living room, change only the blue sofa to be
a vintage, brown leather chesterfield sofa. Keep the rest of the room,
including the pillows on the sofa and the lighting, unchanged."

from google import genai
from PIL import Image
import base64

client = genai.Client()

with open('/path/to/your/living_room.png', 'rb') as f:
    image_bytes = f.read()
text_input = """Using the provided image of a living room, change only the blue sofa to be a vintage, brown leather chesterfield sofa. Keep the rest of the room, including the pillows on the sofa and the lighting, unchanged."""

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=[
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        },
        {"type": "text", "text": text_input}
    ],
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                with open("living_room_edited.png", "wb") as f:
                    f.write(base64.b64decode(content_block.data))

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

async function main() {
  const ai = new GoogleGenAI({});

  const imagePath = "/path/to/your/living_room.png";
  const imageData = fs.readFileSync(imagePath);
  const base64Image = imageData.toString("base64");

  const input = [
    {
      type: "image",
      mime_type: "image/png",
      data: base64Image
    },
    { type: "text", text: "Using the provided image of a living room, change only the blue sofa to be a vintage, brown leather chesterfield sofa. Keep the rest of the room, including the pillows on the sofa and the lighting, unchanged." },
  ];

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: input,
  });
  for (const step of interaction.steps) {
    if (step.type === "model_output") {
      for (const contentBlock of step.content) {
        if (contentBlock.type === "text") {
          console.log(contentBlock.text);
        } else if (contentBlock.type === "image") {
          const buffer = Buffer.from(contentBlock.data, "base64");
          fs.writeFileSync("living_room_edited.png", buffer);
        }
      }
    }
  }
}

main();

curl -s -X POST \
  "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d "{
      \"model\": \"gemini-3.1-flash-image\",
      \"input\": [
        {\"type\": \"image\", \"mime_type\":\"image/png\", \"data\": \"<BASE64_IMAGE_DATA>\"},
        {\"type\": \"text\", \"text\": \"Using the provided image of a living room, change only the blue sofa to be a vintage, brown leather chesterfield sofa. Keep the rest of the room, including the pillows on the sofa and the lighting, unchanged.\"}
      ]
    }"

Transform the provided photograph of [subject] into the artistic style of [artist/art style]. Preserve the original composition but render it with [description of stylistic elements].

"Transform the provided photograph of a modern city street at night into the artistic style of Vincent van Gogh's 'Starry Night'. Preserve the original composition of buildings and cars, but render all elements with swirling, impasto brushstrokes and a dramatic palette of deep blues and bright yellows."

from google import genai
from PIL import Image
import base64

client = genai.Client()

with open('/path/to/your/city.png', 'rb') as f:
    image_bytes = f.read()
text_input = """Transform the provided photograph of a modern city street at night into the artistic style of Vincent van Gogh's 'Starry Night'. Preserve the original composition of buildings and cars, but render all elements with swirling, impasto brushstrokes and a dramatic palette of deep blues and bright yellows."""

interaction = client.interactions.create(
    model="gemini-3.1-flash-image",
    input=[
        {
            "type": "image",
            "data": base64.b64encode(image_bytes).decode('utf-8'),
            "mime_type": "image/png"
        },
        {"type": "text", "text": text_input}
    ],
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
            elif content_block.type == "image":
                with open("city_style_transfer.png", "wb") as f:
                    f.write(base64.b64decode(content_block.data))

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

async function main() {
  const ai = new GoogleGenAI({});
  const imageData = fs.readFileSync("/path/to/your/city.png");
  const base64Image = imageData.toString("base64");

  const interaction = await ai.interactions.create({
    model: "gemini-3.1-flash-image",
    input: [
      {
        type: "image",
        mime_type: "image/png",
        data: base64Image
      },
      { type: "text", text: "Transform the provided photograph of a modern city street at night into the artistic style of Vincent van Gogh's 'Starry Night'. Preserve the original composition of buildings and cars, but render all elements with swirling, impasto brushstrokes and a dramatic palette of deep blues and bright yellows." },
    ],
  });
  for (const step of interaction.steps) {
    if (step.type === "model_output") {
      for (const contentBlock of step.content) {
        if (contentBlock.type === "text") {
          console.log(contentBlock.text);
        } else if (contentBlock.type === "image") {
          const buffer = Buffer.from(contentBlock.data, "base64");
          fs.writeFileSync("city_style_transfer.png", buffer);
        }
      }
    }
  }
}

main();