Token导航 LogoToken导航TokenDH.com
开发敏感数据clawhub未标认证来源可访问clear审计提醒

nano-banana-skill纳米香蕉技能

Agent Skill

nano-banana-skill 用于处理图像、截图、视觉识别或图片素材相关工作,适合在 OpenClaw 中需要让 Agent 分析图片、整理视觉素材或辅助图像流程时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

16,325

周安装

637

GitHub Stars

1

下载量

5,147
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:nano-banana-skill(纳米香蕉技能)
来源仓库:https://github.com/seekton/nano-banana-skill
安装命令:
openclaw skills install nano-banana-skill
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install nano-banana-skill

简介

nano-banana-skill 用于处理图像、截图、视觉识别或图片素材相关工作,适合在 OpenClaw 中需要让 Agent 分析图片、整理视觉素材或辅助图像流程时使用。

  • 适用于 Nano Banana、Nano Banana Pro、Nano Banana 2 等 Google AI 图像生成模型,支持超高字符一致性。
  • 通过 clawhub 安装并使用 openclaw skills install nano-banana-skill 命令部署。
  • 安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写操作。
  • 可结合来源仓库和原始 README 继续核验具体用法和功能细节。

SKILL.md

name
nano-banana-skill
description
Nano Banana, Nano Banana Pro, Nano Banana 2 - Google AI image generation models for AI agents. Ultra-high character consistency, 1K-4K resolution, up to 14 reference images, extreme aspect ratios up to 21:9 and 8:1.
metadata
openclaw
requires
env
bins
[]

Nano Banana Skill

Nano Banana is Google's cutting-edge AI image generation model series designed for AI agents. Part of the Monet AI unified API platform.

When to Use

Use this skill when:

  • Character Consistent Image Series: Create images with consistent characters using reference images

- nano-banana-1: Up to 5 reference images for character consistency - nano-banana-1-pro: Up to 14 reference images with 1K-4K resolution - nano-banana-2: Latest Gemini model with extreme aspect ratio support

  • High-Resolution Output: Generate professional-grade images with 1K, 2K, or 4K resolution
  • Ultra-Wide Formats: Create panoramic images with extreme aspect ratios (21:9, 8:1)
  • Style Transfer: Use multiple reference images to guide style and character

Getting API Key

  1. Visit https://monet.vision to register an account
  2. After login, go to https://monet.vision/skills/keys to create an API Key
  3. Configure the API Key in environment variables or code

If you don't have an API Key, ask your owner to apply at monet.vision.

Quick Start

Create an Image Generation Task

curl -X POST https://monet.vision/api/v1/tasks/async \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MONET_API_KEY" \
  -d '{
    "type": "image",
    "input": {
      "model": "nano-banana-1",
      "prompt": "A cute cat in a garden",
      "aspect_ratio": "16:9"
    },
    "idempotency_key": "unique-key-123"
  }'
⚠️ Important: idempotency_key is required. Use a unique value (e.g., UUID) to prevent duplicate task creation if the request is retried.

Response:

{
  "id": "task_abc123",
  "status": "pending",
  "type": "image",
  "created_at": "2026-02-27T10:00:00Z"
}

Get Task Status and Result

Task processing is asynchronous. You need to poll the task status until it becomes success or failed. Recommended polling interval: 5 seconds.

curl https://monet.vision/api/v1/tasks/task_abc123 \
  -H "Authorization: Bearer $MONET_API_KEY"

Response when completed:

{
  "id": "task_abc123",
  "status": "success",
  "type": "image",
  "outputs": [
    {
      "model": "nano-banana-1",
      "status": "success",
      "progress": 100,
      "url": "https://files.monet.vision/..."
    }
  ],
  "created_at": "2026-02-27T10:00:00Z",
  "updated_at": "2026-02-27T10:01:30Z"
}

Example: Poll until completion

const TASK_ID = "task_abc123";
const MONET_API_KEY = process.env.MONET_API_KEY;

async function pollTask() {
  while (true) {
    const response = await fetch(
      `https://monet.vision/api/v1/tasks/${TASK_ID}`,
      {
        headers: {
          Authorization: `Bearer ${MONET_API_KEY}`,
        },
      },
    );

    const data = await response.json();
    const status = data.status;

    if (status === "success") {
      console.log("Task completed successfully!");
      console.log(JSON.stringify(data, null, 2));
      break;
    } else if (status === "failed") {
      console.log("Task failed!");
      console.log(JSON.stringify(data, null, 2));
      break;
    } else {
      console.log(`Task status: ${status}, waiting...`);
      await new Promise((resolve) => setTimeout(resolve, 5000));
    }
  }
}

pollTask();

Supported Models

nano-banana-1

nano-banana-1 - Google Nano Banana

_Ultra-high character consistency_

  • 🎯 Use Cases: Image series requiring consistent character appearance
  • 📐 Max Reference Images: 5
{
  model: "nano-banana-1",
  prompt: string,                // Required
  images?: string[],             // Optional: Up to 5 reference images
  aspect_ratio?: "1:1" | "2:3" | "3:2" | "4:3" | "3:4" | "16:9" | "9:16"
}

nano-banana-1-pro

nano-banana-1-pro - Nano Banana Pro

_Google flagship generation model_

  • 🎯 Use Cases: Professional-grade high-quality image generation
  • 📐 Max Reference Images: 14
  • 🖥️ Resolution: 1K, 2K, 4K
{
  model: "nano-banana-1-pro",
  prompt: string,                // Required
  images?: string[],             // Optional: Up to 14 reference images
  aspect_ratio?: "1:1" | "2:3" | "3:2" | "4:3" | "3:4" | "4:5" | "5:4" | "16:9" | "9:16" | "21:9",
  resolution?: "1K" | "2K" | "4K"
}

nano-banana-2

nano-banana-2 - Nano Banana 2

_Google Gemini latest model_

  • 🎯 Use Cases: Latest technology for high-quality image generation
  • 📐 Max Reference Images: 14
  • 🖥️ Resolution: 1K, 2K, 4K
  • 🌍 Special: Ultra-wide aspect ratios including 8:1
{
  model: "nano-banana-2",
  prompt: string,                // Required
  images?: string[],             // Optional: Up to 14 reference images
  aspect_ratio?: "1:1" | "2:3" | "3:2" | "4:3" | "3:4" | "4:5" | "5:4" | "16:9" | "9:16" | "21:9" | "4:1" | "1:4" | "8:1" | "1:8",
  resolution?: "1K" | "2K" | "4K"
}

API Reference

Create Task (Async)

POST /api/v1/tasks/async - Create an async task. Returns immediately with task ID.

Request:

curl -X POST https://monet.vision/api/v1/tasks/async \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MONET_API_KEY" \
  -d '{
    "type": "image",
    "input": {
      "model": "nano-banana-1",
      "prompt": "A cute cat"
    },
    "idempotency_key": "unique-key-123"
  }'
⚠️ Important: idempotency_key is required. Use a unique value (e.g., UUID) to prevent duplicate task creation if the request is retried.

Response:

{
  "id": "task_abc123",
  "status": "pending",
  "type": "image",
  "created_at": "2026-02-27T10:00:00Z"
}

Create Task (Streaming)

POST /api/v1/tasks/sync - Create a task with SSE streaming. Waits for completion and streams progress.

Request:

curl -X POST https://monet.vision/api/v1/tasks/sync \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MONET_API_KEY" \
  -N \
  -d '{
    "type": "image",
    "input": {
      "model": "nano-banana-1",
      "prompt": "A cute cat"
    },
    "idempotency_key": "unique-key-123"
  }'

Get Task

GET /api/v1/tasks/{taskId} - Get task status and result.

Request:

curl https://monet.vision/api/v1/tasks/task_abc123 \
  -H "Authorization: Bearer $MONET_API_KEY"

Response:

{
  "id": "task_abc123",
  "status": "success",
  "type": "image",
  "outputs": [
    {
      "model": "nano-banana-1",
      "status": "success",
      "progress": 100,
      "url": "https://files.monet.vision/..."
    }
  ],
  "created_at": "2026-02-27T10:00:00Z",
  "updated_at": "2026-02-27T10:01:30Z"
}

List Tasks

GET /api/v1/tasks/list - List tasks with pagination.

Request:

curl "https://monet.vision/api/v1/tasks/list?page=1&pageSize=20" \
  -H "Authorization: Bearer $MONET_API_KEY"

Response:

{
  "tasks": [
    {
      "id": "task_abc123",
      "status": "success",
      "type": "image",
      "outputs": [
        {
          "model": "nano-banana-1",
          "status": "success",
          "progress": 100,
          "url": "https://files.monet.vision/..."
        }
      ],
      "created_at": "2026-02-27T10:00:00Z",
      "updated_at": "2026-02-27T10:01:30Z"
    }
  ],
  "page": 1,
  "pageSize": 20,
  "total": 100
}

Upload File

POST /api/v1/files - Upload a file to get an online access URL.

📁 File Storage: Uploaded files are stored for 24 hours and will be automatically deleted after expiration.

Request:

curl -X POST https://monet.vision/api/v1/files \
  -H "Authorization: Bearer $MONET_API_KEY" \
  -F "file=@/path/to/your/image.jpg" \
  -v

Response:

{
  "id": "file_xyz789",
  "url": "...",
  "filename": "image.jpg",
  "size": 1048576,
  "content_type": "image/jpeg",
  "created_at": "2026-02-27T10:00:00Z"
}

Configuration

Environment Variables

export MONET_API_KEY="monet_xxx"

Authentication

All API requests require authentication via the Authorization header:

Authorization: Bearer monet_xxx

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

98.12%
按下载量换算5,050

安全审计

VirusTotal

可疑

ClawScan

通过

Static analysis

未展示

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills