Gemini Nano Banana图像生成API - 一键访问Gemini AI图像模型

gemini-nano-banana by aiagenta2z/onekey-agent-router

1 周安装量

1 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/aiagenta2z/onekey-agent-router --skill gemini-nano-banana

AI/机器学习自动化 API

🇨🇳中文介绍

OneKey Agent Router

使用一个访问密钥连接各种商业 API。请访问 OneKey Router Keys 并阅读文档 OneKey MCP Router Doc 和 OneKey Agent Router Doc。

gemini Skill

使用 OneKey Agent Router 通过统一的访问密钥访问此服务器的工具。

快速开始

设置您的 OneKey 访问密钥：

export DEEPNLP_ONEKEY_ROUTER_ACCESS=YOUR_API_KEY

如果未提供密钥，脚本将回退到演示密钥 BETA_TEST_KEY_MARCH_2026。常见设置：

unique_id: gemini/gemini
api_id: 下面列出的工具之一

工具

`generate_image_gemini`

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

相关 Skills

FlyClaw：零登录航班聚合查询工具，Python实现多源航班信息与价格搜索

4,000,000 周安装

find-skills 技能搜索工具 - Vercel Labs 开源智能体技能包管理器

812,900 周安装

Azure RBAC 权限管理工具：查找最小角色、创建自定义角色与自动化分配

117,000 周安装

React 组合模式指南：Vercel 组件架构最佳实践，提升代码可维护性

109,600 周安装

使用 Gemini Image API 生成图像。支持的模型（别名为内部名称）：model 参数允许在可用的图像生成模型之间进行选择。 - "gemini-2.5-flash-image"（推荐默认值，稳定且响应快）。 - "gemini-3-pro-image-preview"。 - "gemini-3-flash"

        这些模型的别名分别是 'nano-banana 2.5' 和 'nano-banana 3 Pro'。
        除非用户明确要求使用 Gemini 3 模型，否则请使用 'gemini-2.5-flash-image'。

    参数:
        model: 要使用的图像生成模型（参见上面支持的模型）。默认为 "gemini-2.5-flash-image"。支持：'gemini-3-flash', 'gemini-3-pro-image-preview', 'gemini-2.5-flash-image'
        prompt: 要生成的图像的详细文本描述。
        image_name: 输出图像的文件名，可以是相对路径。默认为 "gemini_output_images.png"。
        output_folder: 图像将被保存的可选文件夹路径（使用用户的个人目录）。如果为 None，则使用服务器默认路径。
        aspect_ratio: 生成图像的宽高比（例如 '16:9', '1:1', '4:3'）。默认为 '16:9'。
        image_size: 生成图像的尺寸/分辨率（例如 '1K', '2K', '4K'）。默认为 '1K'。

    返回:
        Dict: 包含图像路径、消息和成功状态的结果字典。
        output_result["image_path"]: str
        output_result["image_url"]: str
        output_result["message"]: str
        output_result["success"]: bool

model (string, optional):
prompt (string, optional):
image_name (string, optional):
output_folder (object, optional):
aspect_ratio (string, optional):
image_size (string, optional):

`generate_image_nano_banana`

从全球市场获取公开可用的股票代码

    参数:
        model: 要使用的图像生成模型。默认为 "gemini-2.5-flash-image"。支持的模型如下 Google Gemini 文档，例如 'gemini-3-flash', "gemini-3-pro-image-preview", "gemini-2.5-flash-image"，请注意 nano-banana 是 Gemini 图像模型的别名。Nano banana 3 Pro 指的是 Gemini 3 pro preview，而 Nono Banana 2.5 指的是 Gemini 2.5。除非用户指定使用 Gemini 3 模型预览，一般的 'Neno Banana' 图像模型，请使用 'gemini-2.5-flash-image' 以获得更稳定和快速的响应。
        prompt: 要生成的图像的详细文本描述。
        image_name: 输出图像的文件名，可以是相对路径，例如 "./new_gemini_image.png" 等。默认为 "gemini_output_images.png"。
        output_folder: 图像将被保存的可选文件夹路径。请为此路径使用用户的个人目录。如果为 None，则使用服务器/图像根文件夹的默认位置。
        aspect_ratio: 生成图像的宽高比（例如 '16:9', '1:1', '4:3'），默认为 '16:9'。
        image_size: 生成图像的尺寸/分辨率（例如 '1K', '2K', '4K'），默认为 '1K'。

    返回:
        Dict:  output_result 是 MCP 返回的结果字典
        output_result["image_path"] = full_path: str
        output_result["message"] = output_message: str
        output_result["success"] = success: bool

model (string, optional):
prompt (string, optional):
image_name (string, optional):
output_folder (object, optional):
aspect_ratio (string, optional):
image_size (string, optional):

每个工具在此文件夹中都有一个专用脚本：

skills/gemini/scripts/generate_image_gemini.py
skills/gemini/scripts/generate_image_nano_banana.py

python3 scripts/<tool_name>.py --data '{"key": "value"}'

🇺🇸English

OneKey Agent Router

Use One Access Key to connect to various commercial APIs. Please visit the OneKey Router Keys and read the docs OneKey MCP Router Doc and OneKey Agent Router Doc.

gemini Skill

Use the OneKey Agent Router to access tools for this server via a unified access key.

Quick Start

Set your OneKey access key:

export DEEPNLP_ONEKEY_ROUTER_ACCESS=YOUR_API_KEY

If no key is provided, the scripts fall back to the demo key BETA_TEST_KEY_MARCH_2026. Common settings:

unique_id: gemini/gemini
api_id: one of the tools listed below

Tools

`generate_image_gemini`

Generates an image using the Gemini Image API. Supported Models (aliases are internal): The model parameter allows selection between available image generation models. - "gemini-2.5-flash-image" (recommended default for stable, fast response). - "gemini-3-pro-image-preview". - "gemini-3-flash"

        Aliases for these models are 'nano-banana 2.5' and 'nano-banana 3 Pro' respectively.
        Please use 'gemini-2.5-flash-image' unless the user specifically requests the Gemini 3 model.

    Args:
        model: The image generation model to use (see supported models above). Defaults to "gemini-2.5-flash-image". Supports: 'gemini-3-flash', 'gemini-3-pro-image-preview', 'gemini-2.5-flash-image'
        prompt: A detailed text description for the image to be generated.
        image_name: The filename for the output image, can be a relative path. Defaults to "gemini_output_images.png".
        output_folder: The optional folder path where the image will be saved (use the user's personal directory). If None, uses a server default.
        aspect_ratio: The aspect ratio of the generated image (e.g., '16:9', '1:1', '4:3'). Defaults to '16:9'.
        image_size: The size/resolution of the generated image (e.g., '1K', '2K', '4K'). Defaults to '1K'.

    Return:
        Dict: Result dictionary containing image path, message, and success status.
        output_result["image_path"]: str
        output_result["image_url"]: str
        output_result["message"]: str
        output_result["success"]: bool

Parameters:

model (string, optional):
prompt (string, optional):
image_name (string, optional):
output_folder (object, optional):
aspect_ratio (string, optional):
image_size (string, optional):

`generate_image_nano_banana`

Get Public Available Stock Symbols from Global Marketplace

    Args:
        model: The image generation model to use. Defaults to "gemini-2.5-flash-image". Supported Models such as follows Google Gemini Doc, such as 'gemini-3-flash', "gemini-3-pro-image-preview", "gemini-2.5-flash-image", note that nano-banana is the alias name of the Gemini Image Model. Nano banana 3 Pro refers to Gemini 3 pro preview, and Nono Banana 2.5 refers to Gemini 2.5. Unless specified by user to use Gemini 3 model preview, general 'Neno Banana' image models, please use 'gemini-2.5-flash-image' for more stable and fast response.
        prompt: A detailed text description for the image to be generated.
        image_name: The filename for the output image, can be a relative path, such as "./new_gemini_image.png", etc. Defaults to "gemini_output_images.png".
        output_folder: The optional folder path where the image will be saved. Please use the users' personal directory for this path. If None, uses a default location to the root folder of the server/image
        aspect_ratio: The aspect ratio of the generated image (e.g., '16:9', '1:1', '4:3'), defaults to '16:9'.
        image_size: The size/resolution of the generated image (e.g., '1K', '2K', '4K'), defaults to '1K'.

    Return:
        Dict:  output_result is the result dict of MCP returned
        output_result["image_path"] = full_path: str
        output_result["message"] = output_message: str
        output_result["success"] = success: bool

Parameters:

model (string, optional):
prompt (string, optional):
image_name (string, optional):
output_folder (object, optional):
aspect_ratio (string, optional):
image_size (string, optional):

Scripts

Each tool has a dedicated script in this folder:

skills/gemini/scripts/generate_image_gemini.py
skills/gemini/scripts/generate_image_nano_banana.py

Example

python3 scripts/<tool_name>.py --data '{"key": "value"}'

Gemini Nano Banana图像生成API - 一键访问Gemini AI图像模型

🇨🇳中文介绍

OneKey Agent Router

gemini Skill

快速开始

工具

`generate_image_gemini`

相关 Skills

`generate_image_nano_banana`

脚本

示例

相关 DeepNLP OneKey Router 文档

🇺🇸English

OneKey Agent Router

gemini Skill

Quick Start

Tools

`generate_image_gemini`

`generate_image_nano_banana`

Scripts

Example

Related DeepNLP OneKey Router Documents

最新 Skills