Tạo hình ảnh bằng Gemini (còn gọi là Nano Banana)

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

client = genai.Client()

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

response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents=[prompt],
)

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.save("generated_image.png")

import { GoogleGenAI, Modality } 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 response = await ai.models.generateContent({
    model: "gemini-2.5-flash-image-preview",
    contents: prompt,
  });
  for (const part of response.candidates[0].content.parts) {
    if (part.text) {
      console.log(part.text);
    } else if (part.inlineData) {
      const imageData = part.inlineData.data;
      const buffer = Buffer.from(imageData, "base64");
      fs.writeFileSync("gemini-native-image.png", buffer);
      console.log("Image saved as gemini-native-image.png");
    }
  }
}

main();

package main

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

func main() {

  ctx := context.Background()
  client, err := genai.NewClient(ctx, nil)
  if err != nil {
      log.Fatal(err)
  }

  result, _ := client.Models.GenerateContent(
      ctx,
      "gemini-2.5-flash-image-preview",
      genai.Text("Create a picture of a nano banana dish in a " +
                 " fancy restaurant with a Gemini theme"),
  )

  for _, part := range result.Candidates[0].Content.Parts {
      if part.Text != "" {
          fmt.Println(part.Text)
      } else if part.InlineData != nil {
          imageBytes := part.InlineData.Data
          outputFilename := "gemini_generated_image.png"
          _ = os.WriteFile(outputFilename, imageBytes, 0644)
      }
  }
}

curl -s -X POST
  "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image-preview:generateContent" \
  -H "x-goog-api-key: $GEMINI_API_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"}
      ]
    }]
  }' \
  | grep -o '"data": "[^"]*"' \
  | cut -d'"' -f4 \
  | base64 --decode > gemini-native-image.png

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

client = genai.Client()

prompt = (
    "Create a picture of my cat eating a nano-banana in a "
    "fancy restaurant under the Gemini constellation",
)

image = Image.open("/path/to/cat_image.png")

response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents=[prompt, 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.save("generated_image.png")

import { GoogleGenAI, Modality } 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 = [
    { text: "Create a picture of my cat eating a nano-banana in a" +
            "fancy restaurant under the Gemini constellation" },
    {
      inlineData: {
        mimeType: "image/png",
        data: base64Image,
      },
    },
  ];

  const response = await ai.models.generateContent({
    model: "gemini-2.5-flash-image-preview",
    contents: prompt,
  });
  for (const part of response.candidates[0].content.parts) {
    if (part.text) {
      console.log(part.text);
    } else if (part.inlineData) {
      const imageData = part.inlineData.data;
      const buffer = Buffer.from(imageData, "base64");
      fs.writeFileSync("gemini-native-image.png", buffer);
      console.log("Image saved as gemini-native-image.png");
    }
  }
}

main();

package main

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

func main() {

 ctx := context.Background()
 client, err := genai.NewClient(ctx, nil)
 if err != nil {
     log.Fatal(err)
 }

 imagePath := "/path/to/cat_image.png"
 imgData, _ := os.ReadFile(imagePath)

 parts := []*genai.Part{
   genai.NewPartFromText("Create a picture of my cat eating a nano-banana in a fancy restaurant under the Gemini constellation"),
   &genai.Part{
     InlineData: &genai.Blob{
       MIMEType: "image/png",
       Data:     imgData,
     },
   },
 }

 contents := []*genai.Content{
   genai.NewContentFromParts(parts, genai.RoleUser),
 }

 result, _ := client.Models.GenerateContent(
     ctx,
     "gemini-2.5-flash-image-preview",
     contents,
 )

 for _, part := range result.Candidates[0].Content.Parts {
     if part.Text != "" {
         fmt.Println(part.Text)
     } else if part.InlineData != nil {
         imageBytes := part.InlineData.Data
         outputFilename := "gemini_generated_image.png"
         _ = os.WriteFile(outputFilename, imageBytes, 0644)
     }
 }
}

IMG_PATH=/path/to/cat_image.jpeg

if [[ "$(base64 --version 2>&1)" = *"FreeBSD"* ]]; then
  B64FLAGS="--input"
else
  B64FLAGS="-w0"
fi

IMG_BASE64=$(base64 "$B64FLAGS" "$IMG_PATH" 2>&1)

curl -X POST \
  "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash-image-preview:generateContent" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -d "{
      \"contents\": [{
        \"parts\":[
            {\"text\": \"'Create a picture of my cat eating a nano-banana in a fancy restaurant under the Gemini constellation\"},
            {
              \"inline_data\": {
                \"mime_type\":\"image/jpeg\",
                \"data\": \"$IMG_BASE64\"
              }
            }
        ]
      }]
    }"  \
  | grep -o '"data": "[^"]*"' \
  | cut -d'"' -f4 \
  | base64 --decode > gemini-edited-image.png

A photorealistic [shot type] of [subject], [action or expression], set in
[environment]. The scene is illuminated by [lighting description], creating
a [mood] atmosphere. Captured with a [camera/lens details], emphasizing
[key textures and details]. The image should be in a [aspect ratio] format.

A photorealistic close-up portrait of an elderly Japanese ceramicist with
deep, sun-etched wrinkles and a warm, knowing smile. He is carefully
inspecting a freshly glazed tea bowl. The setting is his rustic,
sun-drenched workshop. The scene is illuminated by soft, golden hour light
streaming through a window, highlighting the fine texture of the clay.
Captured with an 85mm portrait lens, resulting in a soft, blurred background
(bokeh). The overall mood is serene and masterful. Vertical portrait
orientation.

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

client = genai.Client()

# Generate an image from a text prompt
response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents="A photorealistic close-up portrait of an elderly Japanese ceramicist with deep, sun-etched wrinkles and a warm, knowing smile. He is carefully inspecting a freshly glazed tea bowl. The setting is his rustic, sun-drenched workshop with pottery wheels and shelves of clay pots in the background. The scene is illuminated by soft, golden hour light streaming through a window, highlighting the fine texture of the clay and the fabric of his apron. Captured with an 85mm portrait lens, resulting in a soft, blurred background (bokeh). The overall mood is serene and masterful.",
)

image_parts = [
    part.inline_data.data
    for part in response.candidates[0].content.parts
    if part.inline_data
]

if image_parts:
    image = Image.open(BytesIO(image_parts[0]))
    image.save('photorealistic_example.png')
    image.show()

A [style] sticker of a [subject], featuring [key characteristics] and a
[color palette]. The design should have [line style] and [shading style].
The background must be transparent.

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

client = genai.Client()

# Generate an image from a text prompt
response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents="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.",
)

image_parts = [
    part.inline_data.data
    for part in response.candidates[0].content.parts
    if part.inline_data
]

if image_parts:
    image = Image.open(BytesIO(image_parts[0]))
    image.save('red_panda_sticker.png')
    image.show()

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 design should
feature a simple, stylized icon of a a coffee bean seamlessly integrated
with the text. The color scheme is black and white.

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

client = genai.Client()

# Generate an image from a text prompt
response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents="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 design should feature a simple, stylized icon of a a coffee bean seamlessly integrated with the text. The color scheme is black and white.",
)

image_parts = [
    part.inline_data.data
    for part in response.candidates[0].content.parts
    if part.inline_data
]

if image_parts:
    image = Image.open(BytesIO(image_parts[0]))
    image.save('logo_example.png')
    image.show()

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

client = genai.Client()

# Generate an image from a text prompt
response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents="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.",
)

image_parts = [
    part.inline_data.data
    for part in response.candidates[0].content.parts
    if part.inline_data
]

if image_parts:
    image = Image.open(BytesIO(image_parts[0]))
    image.save('product_mockup.png')
    image.show()

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

client = genai.Client()

# Generate an image from a text prompt
response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents="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.",
)

image_parts = [
    part.inline_data.data
    for part in response.candidates[0].content.parts
    if part.inline_data
]

if image_parts:
    image = Image.open(BytesIO(image_parts[0]))
    image.save('minimalist_design.png')
    image.show()

A single comic book panel in a [art style] style. In the foreground,
[character description and action]. In the background, [setting details].
The panel has a [dialogue/caption box] with the text "[Text]". The lighting
creates a [mood] mood. [Aspect ratio].

A single comic book panel in a gritty, noir art style with high-contrast
black and white inks. In the foreground, a detective in a trench coat stands
under a flickering streetlamp, rain soaking his shoulders. In the
background, the neon sign of a desolate bar reflects in a puddle. A caption
box at the top reads "The city was a tough place to keep secrets." The
lighting is harsh, creating a dramatic, somber mood. Landscape.

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

client = genai.Client()

# Generate an image from a text prompt
response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents="A single comic book panel in a gritty, noir art style with high-contrast black and white inks. In the foreground, a detective in a trench coat stands under a flickering streetlamp, rain soaking his shoulders. In the background, the neon sign of a desolate bar reflects in a puddle. A caption box at the top reads \"The city was a tough place to keep secrets.\" The lighting is harsh, creating a dramatic, somber mood. Landscape.",
)

image_parts = [
    part.inline_data.data
    for part in response.candidates[0].content.parts
    if part.inline_data
]

if image_parts:
    image = Image.open(BytesIO(image_parts[0]))
    image.save('comic_panel.png')
    image.show()

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

client = genai.Client()

# Base image prompt: "A photorealistic picture of a fluffy ginger cat sitting on a wooden floor, looking directly at the camera. Soft, natural light from a window."
image_input = Image.open('/path/to/your/cat_photo.png')
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."""

# Generate an image from a text prompt
response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents=[text_input, image_input],
)

image_parts = [
    part.inline_data.data
    for part in response.candidates[0].content.parts
    if part.inline_data
]

if image_parts:
    image = Image.open(BytesIO(image_parts[0]))
    image.save('cat_with_hat.png')
    image.show()

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

client = genai.Client()

# Base image prompt: "A wide shot of a modern, well-lit living room with a prominent blue sofa in the center. A coffee table is in front of it and a large window is in the background."
living_room_image = Image.open('/path/to/your/living_room.png')
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."""

# Generate an image from a text prompt
response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents=[living_room_image, text_input],
)

image_parts = [
    part.inline_data.data
    for part in response.candidates[0].content.parts
    if part.inline_data
]

if image_parts:
    image = Image.open(BytesIO(image_parts[0]))
    image.save('living_room_edited.png')
    image.show()

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

client = genai.Client()

# Base image prompt: "A photorealistic, high-resolution photograph of a busy city street in New York at night, with bright neon signs, yellow taxis, and tall skyscrapers."
city_image = Image.open('/path/to/your/city.png')
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."""

# Generate an image from a text prompt
response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents=[city_image, text_input],
)

image_parts = [
    part.inline_data.data
    for part in response.candidates[0].content.parts
    if part.inline_data
]

if image_parts:
    image = Image.open(BytesIO(image_parts[0]))
    image.save('city_style_transfer.png')
    image.show()

Create a new image by combining the elements from the provided images. Take
the [element from image 1] and place it with/on the [element from image 2].
The final image should be a [description of the final scene].

"Create a professional e-commerce fashion photo. Take the blue floral dress
from the first image and let the woman from the second image wear it.
Generate a realistic, full-body shot of the woman wearing the dress, with
the lighting and shadows adjusted to match the outdoor environment."

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

client = genai.Client()

# Base image prompts:
# 1. Dress: "A professionally shot photo of a blue floral summer dress on a plain white background, ghost mannequin style."
# 2. Model: "Full-body shot of a woman with her hair in a bun, smiling, standing against a neutral grey studio background."
dress_image = Image.open('/path/to/your/dress.png')
model_image = Image.open('/path/to/your/model.png')

text_input = """Create a professional e-commerce fashion photo. Take the blue floral dress from the first image and let the woman from the second image wear it. Generate a realistic, full-body shot of the woman wearing the dress, with the lighting and shadows adjusted to match the outdoor environment."""

# Generate an image from a text prompt
response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents=[dress_image, model_image, text_input],
)

image_parts = [
    part.inline_data.data
    for part in response.candidates[0].content.parts
    if part.inline_data
]

if image_parts:
    image = Image.open(BytesIO(image_parts[0]))
    image.save('fashion_ecommerce_shot.png')
    image.show()

Using the provided images, place [element from image 2] onto [element from
image 1]. Ensure that the features of [element from image 1] remain
completely unchanged. The added element should [description of how the
element should integrate].

"Take the first image of the woman with brown hair, blue eyes, and a neutral
expression. Add the logo from the second image onto her black t-shirt.
Ensure the woman's face and features remain completely unchanged. The logo
should look like it's naturally printed on the fabric, following the folds
of the shirt."

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

client = genai.Client()

# Base image prompts:
# 1. Woman: "A professional headshot of a woman with brown hair and blue eyes, wearing a plain black t-shirt, against a neutral studio background."
# 2. Logo: "A simple, modern logo with the letters 'G' and 'A' in a white circle."
woman_image = Image.open('/path/to/your/woman.png')
logo_image = Image.open('/path/to/your/logo.png')
text_input = """Take the first image of the woman with brown hair, blue eyes, and a neutral expression. Add the logo from the second image onto her black t-shirt. Ensure the woman's face and features remain completely unchanged. The logo should look like it's naturally printed on the fabric, following the folds of the shirt."""

# Generate an image from a text prompt
response = client.models.generate_content(
    model="gemini-2.5-flash-image-preview",
    contents=[woman_image, logo_image, text_input],
)

image_parts = [
    part.inline_data.data
    for part in response.candidates[0].content.parts
    if part.inline_data
]

if image_parts:
    image = Image.open(BytesIO(image_parts[0]))
    image.save('woman_with_logo.png')
    image.show()