gemini-imagegen

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Gemini Image Generation (Nano Banana Pro)

Gemini 图像生成（Nano Banana Pro）

Generate and edit images using Google's Gemini API. The environment variable

GEMINI_API_KEY

must be set.

使用Google的Gemini API生成和编辑图像。必须设置环境变量

GEMINI_API_KEY

。

Default Model

默认模型

Model	Resolution	Best For
`gemini-3-pro-image-preview`	1K-4K	All image generation (default)

Note: Always use this Pro model. Only use a different model if explicitly requested.

模型	分辨率	适用场景
`gemini-3-pro-image-preview`	1K-4K	所有图像生成任务（默认）

注意： 请始终使用此Pro模型。仅在明确要求时才使用其他模型。

Quick Reference

快速参考

Default Settings

默认设置

Model:
```
gemini-3-pro-image-preview
```
Resolution: 1K (default, options: 1K, 2K, 4K)
Aspect Ratio: 1:1 (default)

模型：
```
gemini-3-pro-image-preview
```
分辨率： 1K（默认，可选：1K、2K、4K）
宽高比： 1:1（默认）

Available Aspect Ratios

可用宽高比

1:1

2:3

3:2

3:4

4:3

4:5

5:4

9:16

16:9

21:9

1:1

2:3

3:2

3:4

4:3

4:5

5:4

9:16

16:9

21:9

Available Resolutions

可用分辨率

1K

(default),

2K

4K

1K

（默认）,

2K

4K

Core API Pattern

核心API模式

python

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

client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])

python

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

client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])

Basic generation (1K, 1:1 - defaults)

response = client.models.generate_content( model="gemini-3-pro-image-preview", contents=["Your prompt here"], config=types.GenerateContentConfig( response_modalities=['TEXT', 'IMAGE'], ), )

for part in response.parts: if part.text: print(part.text) elif part.inline_data: image = part.as_image() image.save("output.png")

undefined

response = client.models.generate_content( model="gemini-3-pro-image-preview", contents=["Your prompt here"], config=types.GenerateContentConfig( response_modalities=['TEXT', 'IMAGE'], ), )

for part in response.parts: if part.text: print(part.text) elif part.inline_data: image = part.as_image() image.save("output.png")

undefined

Custom Resolution & Aspect Ratio

自定义分辨率与宽高比

python

from google.genai import types

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=[prompt],
    config=types.GenerateContentConfig(
        response_modalities=['TEXT', 'IMAGE'],
        image_config=types.ImageConfig(
            aspect_ratio="16:9",  # Wide format
            image_size="2K"       # Higher resolution
        ),
    )
)

python

from google.genai import types

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=[prompt],
    config=types.GenerateContentConfig(
        response_modalities=['TEXT', 'IMAGE'],
        image_config=types.ImageConfig(
            aspect_ratio="16:9",  # Wide format
            image_size="2K"       # Higher resolution
        ),
    )
)

Resolution Examples

分辨率示例

python

undefined

python

undefined

1K (default) - Fast, good for previews

image_config=types.ImageConfig(image_size="1K")

2K - Balanced quality/speed

image_config=types.ImageConfig(image_size="2K")

4K - Maximum quality, slower

image_config=types.ImageConfig(image_size="4K")

undefined

image_config=types.ImageConfig(image_size="4K")

undefined

Aspect Ratio Examples

宽高比示例

python

undefined

python

undefined

Square (default)

image_config=types.ImageConfig(aspect_ratio="1:1")

Landscape wide

image_config=types.ImageConfig(aspect_ratio="16:9")

Ultra-wide panoramic

image_config=types.ImageConfig(aspect_ratio="21:9")

Portrait

image_config=types.ImageConfig(aspect_ratio="9:16")

Photo standard

image_config=types.ImageConfig(aspect_ratio="4:3")

undefined

image_config=types.ImageConfig(aspect_ratio="4:3")

undefined

Editing Images

编辑图像

Pass existing images with text prompts:

python

from PIL import Image

img = Image.open("input.png")
response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=["Add a sunset to this scene", img],
    config=types.GenerateContentConfig(
        response_modalities=['TEXT', 'IMAGE'],
    ),
)

将现有图像与文本提示一起传入：

python

from PIL import Image

img = Image.open("input.png")
response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=["Add a sunset to this scene", img],
    config=types.GenerateContentConfig(
        response_modalities=['TEXT', 'IMAGE'],
    ),
)

Multi-Turn Refinement

多轮优化

Use chat for iterative editing:

python

from google.genai import types

chat = client.chats.create(
    model="gemini-3-pro-image-preview",
    config=types.GenerateContentConfig(response_modalities=['TEXT', 'IMAGE'])
)

response = chat.send_message("Create a logo for 'Acme Corp'")

使用对话进行迭代编辑：

python

from google.genai import types

chat = client.chats.create(
    model="gemini-3-pro-image-preview",
    config=types.GenerateContentConfig(response_modalities=['TEXT', 'IMAGE'])
)

response = chat.send_message("Create a logo for 'Acme Corp'")

Save first image...

response = chat.send_message("Make the text bolder and add a blue gradient")

Save refined image...

undefined

undefined

Prompting Best Practices

提示词最佳实践

Photorealistic Scenes

写实场景

Include camera details: lens type, lighting, angle, mood.

"A photorealistic close-up portrait, 85mm lens, soft golden hour light, shallow depth of field"

包含相机细节：镜头类型、光线、角度、氛围。

"A photorealistic close-up portrait, 85mm lens, soft golden hour light, shallow depth of field"

Stylized Art

风格化艺术

Specify style explicitly:

"A kawaii-style sticker of a happy red panda, bold outlines, cel-shading, white background"

明确指定风格：

"A kawaii-style sticker of a happy red panda, bold outlines, cel-shading, white background"

Text in Images

图像中的文字

Be explicit about font style and placement:

"Create a logo with text 'Daily Grind' in clean sans-serif, black and white, coffee bean motif"

明确说明字体样式和位置：

"Create a logo with text 'Daily Grind' in clean sans-serif, black and white, coffee bean motif"

Product Mockups

产品样机

Describe lighting setup and surface:

"Studio-lit product photo on polished concrete, three-point softbox setup, 45-degree angle"

描述灯光设置和表面：

"Studio-lit product photo on polished concrete, three-point softbox setup, 45-degree angle"

Advanced Features

高级功能

Google Search Grounding

Google搜索锚定

Generate images based on real-time data:

python

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=["Visualize today's weather in Tokyo as an infographic"],
    config=types.GenerateContentConfig(
        response_modalities=['TEXT', 'IMAGE'],
        tools=[{"google_search": {}}]
    )
)

根据实时数据生成图像：

python

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=["Visualize today's weather in Tokyo as an infographic"],
    config=types.GenerateContentConfig(
        response_modalities=['TEXT', 'IMAGE'],
        tools=[{"google_search": {}}]
    )
)

Multiple Reference Images (Up to 14)

多张参考图（最多14张）

Combine elements from multiple sources:

python

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=[
        "Create a group photo of these people in an office",
        Image.open("person1.png"),
        Image.open("person2.png"),
        Image.open("person3.png"),
    ],
    config=types.GenerateContentConfig(
        response_modalities=['TEXT', 'IMAGE'],
    ),
)

合并多个来源的元素：

python

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=[
        "Create a group photo of these people in an office",
        Image.open("person1.png"),
        Image.open("person2.png"),
        Image.open("person3.png"),
    ],
    config=types.GenerateContentConfig(
        response_modalities=['TEXT', 'IMAGE'],
    ),
)

Important: File Format & Media Type

重要提示：文件格式与媒体类型

CRITICAL: The Gemini API returns images in JPEG format by default. When saving, always use

.jpg

extension to avoid media type mismatches.

python

undefined

关键注意事项： Gemini API默认返回JPEG格式的图像。保存时，请始终使用

.jpg

扩展名，以避免媒体类型不匹配。

python

undefined

CORRECT - Use .jpg extension (Gemini returns JPEG)

image.save("output.jpg")

WRONG - Will cause "Image does not match media type" errors

image.save("output.png") # Creates JPEG with PNG extension!

undefined

image.save("output.png") # Creates JPEG with PNG extension!

undefined

Converting to PNG (if needed)

转换为PNG（如有需要）

If you specifically need PNG format:

python

from PIL import Image

如果您明确需要PNG格式：

python

from PIL import Image

Generate with Gemini

for part in response.parts: if part.inline_data: img = part.as_image() # Convert to PNG by saving with explicit format img.save("output.png", format="PNG")

undefined

for part in response.parts: if part.inline_data: img = part.as_image() # Convert to PNG by saving with explicit format img.save("output.png", format="PNG")

undefined

Verifying Image Format

验证图像格式

Check actual format vs extension with the

file

command:

bash

file image.png

使用

file

命令检查实际格式与扩展名是否匹配：

bash

file image.png

If output shows "JPEG image data" - rename to .jpg!

undefined

undefined

Notes

注意事项

All generated images include SynthID watermarks
Gemini returns JPEG format by default - always use
```
.jpg
```
extension
Image-only mode (
```
responseModalities: ["IMAGE"]
```
) won't work with Google Search grounding
For editing, describe changes conversationally—the model understands semantic masking
Default to 1K resolution for speed; use 2K/4K when quality is critical

所有生成的图像都包含SynthID水印
Gemini默认返回JPEG格式 - 请始终使用
```
.jpg
```
扩展名
仅图像模式（
```
responseModalities: ["IMAGE"]
```
）无法与Google搜索锚定功能配合使用
编辑图像时，用对话式语言描述更改——模型理解语义遮罩
默认使用1K分辨率以提升速度；当对画质有要求时使用2K/4K