nanobanana-skill

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Nanobanana Image Generation Skill

Nanobanana 图片生成Skill

Generate or edit images using Google Gemini API through the nanobanana tool.

通过nanobanana工具，使用Google Gemini API生成或编辑图片。

Requirements

前提条件

GEMINI_API_KEY: Must be configured in

~/.nanobanana.env

export GEMINI_API_KEY=<your-api-key>

Python3 with depedent packages installed: google-genai, Pillow, python-dotenv. They could be installed via
```
python3 -m pip install -r ~/.codex/skills/nanobanana-skill/requirements.txt
```
if not installed yet.

Executable:

~/.codex/skills/nanobanana-skill/nanobanana.py

Example

.nanobanana.env

bash

GEMINI_API_KEY=sk-dummy

GEMINI_API_KEY：必须在

~/.nanobanana.env

中配置，或通过

export GEMINI_API_KEY=<your-api-key>

设置

已安装依赖包的Python3：需要安装google-genai、Pillow、python-dotenv。如果尚未安装，可以通过
```
python3 -m pip install -r ~/.codex/skills/nanobanana-skill/requirements.txt
```
进行安装

可执行文件：

~/.codex/skills/nanobanana-skill/nanobanana.py

示例

.nanobanana.env

：

bash

GEMINI_API_KEY=sk-dummy

Instructions

使用说明

For image generation

图片生成

Ask the user for:
- What they want to create (the prompt)
- Desired aspect ratio/size (optional, defaults to 9:16 portrait)
- Output filename (optional, auto-generates UUID if not specified)
- Model preference (optional, defaults to gemini-3-pro-image-preview)
- Resolution (optional, defaults to 1K)

Run the nanobanana script with appropriate parameters:

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py --prompt "description of image" --output "filename.png"

Show the user the saved image path when complete

向用户确认以下信息：
- 想要创建的内容（提示词）
- 期望的宽高比/尺寸（可选，默认是9:16竖版）
- 输出文件名（可选，未指定时自动生成UUID）
- 模型偏好（可选，默认是gemini-3-pro-image-preview）
- 分辨率（可选，默认是1K）

使用合适的参数运行nanobanana脚本：

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py --prompt "图片描述" --output "filename.png"

完成后向用户展示保存的图片路径

For image editing

图片编辑

Ask the user for:
- Input image file(s) to edit
- What changes they want (the prompt)
- Output filename (optional)

Run with input images:

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py --prompt "editing instructions" --input image1.png image2.png --output "edited.png"

向用户确认以下信息：
- 要编辑的输入图片文件
- 想要进行的修改（提示词）
- 输出文件名（可选）

传入输入图片运行脚本：

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py --prompt "编辑说明" --input image1.png image2.png --output "edited.png"

Available Options

可用选项

Aspect Ratios (--size)

宽高比（--size）

```
1024x1024
```
(1:1) - Square
```
832x1248
```
(2:3) - Portrait
```
1248x832
```
(3:2) - Landscape
```
864x1184
```
(3:4) - Portrait
```
1184x864
```
(4:3) - Landscape
```
896x1152
```
(4:5) - Portrait
```
1152x896
```
(5:4) - Landscape
```
768x1344
```
(9:16) - Portrait (default)
```
1344x768
```
(16:9) - Landscape
```
1536x672
```
(21:9) - Ultra-wide

```
1024x1024
```
(1:1) - 正方形
```
832x1248
```
(2:3) - 竖版
```
1248x832
```
(3:2) - 横版
```
864x1184
```
(3:4) - 竖版
```
1184x864
```
(4:3) - 横版
```
896x1152
```
(4:5) - 竖版
```
1152x896
```
(5:4) - 横版
```
768x1344
```
(9:16) - 竖版（默认）
```
1344x768
```
(16:9) - 横版
```
1536x672
```
(21:9) - 超宽屏

Models (--model)

模型（--model）

```
gemini-3-pro-image-preview
```
(default) - Higher quality
```
gemini-2.5-flash-image
```
- Faster generation

```
gemini-3-pro-image-preview
```
（默认）- 更高质量
```
gemini-2.5-flash-image
```
- 生成速度更快

Resolution (--resolution)

分辨率（--resolution）

```
1K
```
(default)
```
2K
```
```
4K
```

```
1K
```
（默认）
```
2K
```
```
4K
```

Optional Flags

可选标志

```
--enable-google-search
```
Enable Google Search tool for the model (default: disabled)
```
--include-thoughts
```
Include model thinking in output (default: disabled)

```
--enable-google-search
```
为模型启用Google Search工具（默认：禁用）
```
--include-thoughts
```
在输出中包含模型的思考过程（默认：禁用）

Examples

示例

Generate a simple image

生成简单图片

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py --prompt "A serene mountain landscape at sunset with a lake"

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py --prompt "日落时分宁静的山湖景观"

Generate with specific size and output

按指定尺寸和输出文件名生成

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py \
  --prompt "Modern minimalist logo for a tech startup" \
  --size 1024x1024 \
  --output "logo.png"

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py \
  --prompt "科技初创公司的现代极简风格logo" \
  --size 1024x1024 \
  --output "logo.png"

Generate landscape image with high resolution

生成高分辨率横版图片

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py \
  --prompt "Futuristic cityscape with flying cars" \
  --size 1344x768 \
  --resolution 2K \
  --output "cityscape.png"

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py \
  --prompt "带有飞行汽车的未来都市景观" \
  --size 1344x768 \
  --resolution 2K \
  --output "cityscape.png"

Edit existing images

编辑现有图片

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py \
  --prompt "Add a rainbow in the sky" \
  --input photo.png \
  --output "photo-with-rainbow.png"

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py \
  --prompt "在天空中添加一道彩虹" \
  --input photo.png \
  --output "photo-with-rainbow.png"

Use faster model

使用更快的模型

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py \
  --prompt "Quick sketch of a cat" \
  --model gemini-2.5-flash-image \
  --output "cat-sketch.png"

bash

python3 ~/.codex/skills/nanobanana-skill/nanobanana.py \
  --prompt "快速绘制一只猫的草图" \
  --model gemini-2.5-flash-image \
  --output "cat-sketch.png"

Error Handling

错误处理

If the script fails:

Check that
```
GEMINI_API_KEY
```
is exported or set in ~/.nanobanana.env
Verify input image files exist and are readable
Ensure the output directory is writable
If no image is generated, try making the prompt more specific about wanting an image

如果脚本运行失败：

检查
```
GEMINI_API_KEY
```
是否已导出或在~/.nanobanana.env中设置
验证输入图片文件是否存在且可读取
确保输出目录可写入
如果未生成图片，尝试让提示词更明确地表明需要生成图片

Best Practices

最佳实践

Be descriptive in prompts - include style, mood, colors, composition
For logos/graphics, use square aspect ratio (1024x1024)
For social media posts, use 9:16 for stories or 1:1 for posts
For wallpapers, use 16:9 or 21:9
Start with 1K resolution for testing, upgrade to 2K/4K for final output
Use gemini-3-pro-image-preview for best quality, gemini-2.5-flash-image for speed

提示词要详细描述 - 包含风格、氛围、颜色、构图
对于logo/图形，使用正方形宽高比（1024x1024）
对于社交媒体帖子，故事类使用9:16，帖子类使用1:1
对于壁纸，使用16:9或21:9
测试时先用1K分辨率，最终输出再升级到2K/4K
追求最佳质量使用gemini-3-pro-image-preview，追求速度使用gemini-2.5-flash-image