用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/johnalbertini14-glitch/openclaw-skills --skill nano-banana-pro命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Use this skill to create a Polymarket wallet for your agent and trade on prediction markets. Browse markets, place bets, manage positions — all without exposing private keys.
ClawSec suite manager with embedded advisory-feed monitoring, cryptographic signature verification, approval-gated malicious-skill response, and guided setup for additional security skills.
Automated daily security audits for OpenClaw agents with email reporting. Runs deep audits and sends formatted reports.
基于 SOC 职业分类
正在显示 SKILL.md
| name | Nano Banana Pro 图像生成 |
| description | 使用 Nano Banana Pro 模型生成或编辑图像。当用户想要文生图、图像编辑,或提到 nano banana、Google 图像生成时使用此 skill。 |
| category | image |
| tags | ["图像生成","文生图","图像编辑","Google","Nano Banana"] |
| featured | false |
Nano Banana Pro (又名 Nano Banana 2) 是 Google 最新的高质量图像生成和编辑模型,支持写实风格和文字渲染。
| 模型 ID | 功能 | 说明 |
|---|---|---|
fal-ai/nano-banana-pro | 文生图/图像编辑 | 无图片时为文生图,提供图片时自动切换为编辑模式 |
积分消耗:60 积分/张
使用 MCP 工具 submit_task 提交任务:
文生图示例:
{
"model_id": "fal-ai/nano-banana-pro",
"parameters": {
"prompt": "A majestic lion standing on a cliff at sunset, photorealistic",
"aspect_ratio": "16:9",
"resolution": "2K"
}
}
图像编辑示例:
{
"model_id": "fal-ai/nano-banana-pro",
"parameters": {
"prompt": "make a photo of the man driving the car down the california coastline",
"image_urls": [
"https://example.com/man.png",
"https://example.com/car.png"
],
"aspect_ratio": "auto"
}
}
| 参数 | 类型 | 必填 | 默认值 | 说明 |
|---|---|---|---|---|
| prompt | string | 是 | - | 图像生成/编辑提示词 |
| image_urls | array | 否 | - | 输入图片 URL 列表(提供此参数时自动切换为编辑模式) |
| num_images | integer | 否 | 1 | 生成图像数量(1-4) |
| aspect_ratio | string | 否 | "1:1" | 宽高比:21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16(编辑模式额外支持 "auto") |
| resolution | string | 否 | "1K" | 分辨率:1K, 2K, 4K |
| output_format | string | 否 | "png" | 输出格式:jpeg, png, webp |
| seed | integer | 否 | - | 随机种子,用于复现结果 |
| enable_web_search | boolean | 否 | false | 启用网页搜索以获取最新信息辅助生成 |
提交任务后会返回 task_id,使用 get_task 查询结果:
{
"task_id": "返回的任务ID"
}
任务状态:
pending - 排队中processing - 处理中completed - 完成,结果在 result 中failed - 失败,查看 error 字段用户请求:生成一张黑色拉布拉多犬在泳池游泳的照片
执行步骤:
submit_task:{
"model_id": "fal-ai/nano-banana-pro",
"parameters": {
"prompt": "An action shot of a black lab swimming in an inground suburban swimming pool. The camera is placed meticulously on the water line, dividing the image in half, revealing both the dogs head above water holding a tennis ball in it's mouth, and it's paws paddling underwater.",
"aspect_ratio": "16:9",
"resolution": "2K"
}
}
task_id 后调用 get_task 查询结果用户请求:将这个人放到加州海岸线驾车的场景中
执行步骤:
submit_task:{
"model_id": "fal-ai/nano-banana-pro",
"parameters": {
"prompt": "make a photo of the man driving the car down the california coastline",
"image_urls": [
"https://example.com/man-portrait.png",
"https://example.com/car-interior.png"
],
"aspect_ratio": "auto"
}
}
task_id 后调用 get_task 查询结果enable_web_search 可以让模型使用最新的网络信息辅助生成无需手动指定模式,系统会根据是否提供图片自动选择。