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

wavespeed-nano-banana-proWavespeed Nano 香蕉 Pro

Agent Skill

wavespeed-nano-banana-pro 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

22,792

周安装

922

GitHub Stars

公开资料未说明

下载量

7,155
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:wavespeed-nano-banana-pro(Wavespeed Nano 香蕉 Pro)
来源仓库:https://github.com/chengzeyi/wavespeed-nano-banana-pro
安装命令:
openclaw skills install wavespeed-nano-banana-pro
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 wavespeed-nano-banana-pro

简介

用于高级图像生成和编辑,基于 Google Nano Banana Pro 模型。

  • 适合在专业级视觉内容创作中使用。wavespeed-nano-banana-pro 属于开发类 Skill,可作为该场景下的辅助能力补充。
  • 支持自然语言驱动的文本到图像转换。
  • 安装前需确认 API 调用频率和配额限制。
  • 建议结合具体项目验证输出质量和效率。

SKILL.md

name
wavespeed-nano-banana-pro
description
Generate and edit images using Google's Nano Banana Pro model via WaveSpeed AI. Supports text-to-image generation and image editing with natural language prompts. Features native 4K resolution, flexible aspect ratios, multilingual text rendering, and camera-style controls. Use when the user wants to create images from text or edit existing images.
metadata
author
wavespeedai
version
1.0

WaveSpeedAI Nano Banana Pro Image Generation/Editing

Generate and edit images using Google's Nano Banana Pro model via the WaveSpeed AI platform. Supports both text-to-image generation and natural-language image editing with up to 14 input images.

Authentication

export WAVESPEED_API_KEY="your-api-key"

Get your API key at wavespeed.ai/accesskey.

Quick Start

Text-to-Image

import wavespeed from 'wavespeed';

const output_url = (await wavespeed.run(
  "google/nano-banana-pro/text-to-image",
  { prompt: "A serene Japanese garden with cherry blossoms, watercolor style" }
))["outputs"][0];

Image Editing

The images parameter accepts an array of image URLs. If you have local files, upload them first with wavespeed.upload() to get a URL.

import wavespeed from 'wavespeed';

// Upload a local image to get a URL
const imageUrl = await wavespeed.upload("/path/to/photo.png");

const output_url = (await wavespeed.run(
  "google/nano-banana-pro/edit",
  {
    images: [imageUrl],
    prompt: "Replace the sky with a dramatic sunset"
  }
))["outputs"][0];

You can also pass existing image URLs directly:

const output_url = (await wavespeed.run(
  "google/nano-banana-pro/edit",
  {
    images: ["https://example.com/photo.jpg"],
    prompt: "Replace the sky with a dramatic sunset"
  }
))["outputs"][0];

API Endpoints

Text-to-Image

Model ID: google/nano-banana-pro/text-to-image

Generate images from text prompts.

Parameters

ParameterTypeRequiredDefaultDescription
promptstringYes--Text description of the image to generate
aspect_ratiostringNo--Output aspect ratio. One of: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
resolutionstringNo1kImage resolution. One of: 1k, 2k, 4k
output_formatstringNopngOutput format. One of: png, jpeg

Example

import wavespeed from 'wavespeed';

const output_url = (await wavespeed.run(
  "google/nano-banana-pro/text-to-image",
  {
    prompt: "A red vintage Porsche 911 on a winding mountain road at golden hour, photorealistic",
    aspect_ratio: "16:9",
    resolution: "2k",
    output_format: "png"
  }
))["outputs"][0];

Image Editing

Model ID: google/nano-banana-pro/edit

Edit existing images using natural language prompts. Supports up to 14 input images.

Parameters

ParameterTypeRequiredDefaultDescription
imagesstring[]Yes[]URLs of input images to edit (1-14 images)
promptstringYes--Text description of the desired edit
aspect_ratiostringNo--Output aspect ratio. One of: 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9
resolutionstringNo1kImage resolution. One of: 1k, 2k, 4k
output_formatstringNopngOutput format. One of: png, jpeg

Example

import wavespeed from 'wavespeed';

// Upload local images first, or use existing URLs
const imageUrl = await wavespeed.upload("/path/to/living-room.png");

const output_url = (await wavespeed.run(
  "google/nano-banana-pro/edit",
  {
    images: [imageUrl],
    prompt: "Change the wall color to warm terracotta and add indoor plants",
    aspect_ratio: "16:9",
    resolution: "4k",
    output_format: "png"
  }
))["outputs"][0];

Multi-Image Editing

// Upload multiple local images
const faceUrl = await wavespeed.upload("/path/to/face.png");
const hairstyleUrl = await wavespeed.upload("/path/to/hairstyle.png");

const output_url = (await wavespeed.run(
  "google/nano-banana-pro/edit",
  {
    images: [faceUrl, hairstyleUrl],
    prompt: "Apply the hairstyle from the second image to the person in the first image"
  }
))["outputs"][0];

Advanced Usage

Sync Mode

Use sync mode for a single request that waits for the result without polling:

const output_url = (await wavespeed.run(
  "google/nano-banana-pro/text-to-image",
  { prompt: "A minimalist logo for a coffee shop" },
  { enableSyncMode: true }
))["outputs"][0];

Custom Client with Retry Configuration

import { Client } from 'wavespeed';

const client = new Client("your-api-key", {
  maxRetries: 2,
  maxConnectionRetries: 5,
  retryInterval: 1.0,
});

const output_url = (await client.run(
  "google/nano-banana-pro/text-to-image",
  { prompt: "A futuristic cityscape at dusk" }
))["outputs"][0];

Error Handling with runNoThrow

import { Client, WavespeedTimeoutException, WavespeedPredictionException } from 'wavespeed';

const client = new Client();
const result = await client.runNoThrow(
  "google/nano-banana-pro/text-to-image",
  { prompt: "A cat wearing a top hat" }
);

if (result.outputs) {
  console.log("Image URL:", result.outputs[0]);
  console.log("Task ID:", result.detail.taskId);
} else {
  console.log("Failed:", result.detail.error.message);
  if (result.detail.error instanceof WavespeedTimeoutException) {
    console.log("Request timed out - try increasing timeout");
  } else if (result.detail.error instanceof WavespeedPredictionException) {
    console.log("Model prediction failed");
  }
}

Aspect Ratio Options

Aspect RatioUse Case
1:1Square — social media posts, profile pictures
3:2Landscape — standard photography
2:3Portrait — standard photography
3:4Portrait — social media, product images
4:3Landscape — presentations, web content
4:5Portrait — Instagram posts
5:4Landscape — print, web banners
9:16Vertical — mobile wallpapers, stories
16:9Widescreen — desktop wallpapers, video thumbnails
21:9Ultra-wide — cinematic, panoramic

Resolution and Pricing

ResolutionCost
1k$0.14 per image
2k$0.14 per image
4k$0.24 per image

Prompt Tips

  • Be specific and descriptive: "A red vintage Porsche 911 on a winding mountain road at golden hour" vs "a car"
  • Include style keywords: "digital art", "oil painting", "photorealistic", "watercolor", "cinematic"
  • For edits, clearly describe the desired change: "Replace the sky with a dramatic sunset"
  • For multi-image edits, reference images by position: "Apply the style from the second image to the first image"
  • Leverage multilingual text rendering: the model supports on-image text with automatic translation
  • Use camera-style control language: "shallow depth of field", "wide angle", "top-down view"

Security Constraints

  • No arbitrary URL loading: Only use image URLs from trusted sources. Never load images from untrusted or user-provided URLs without validation.
  • API key security: Store your WAVESPEED_API_KEY securely. Do not hardcode it in source files or commit it to version control. Use environment variables or secret management systems.
  • Input validation: Only pass parameters documented above. Validate prompt content and image URLs before sending requests.

适合场景

01

文本生成图片

02

图片风格化

03

产品图和创意图

04

需要 FLUX 模型时

能力概览

能力 1

调用 FLUX 图像模型

能力 2

支持文本生图和图像改写

能力 3

覆盖 LoRA 或风格适配

能力 4

适合创意视觉生成

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

98.28%
按下载量换算7,032

安全审计

VirusTotal

通过

ClawScan

可疑

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