Token导航 LogoToken导航TokenDH.com
研究检索敏感数据clawhub未标认证来源可访问clear审计通过

nanophoto-nano-banana-2纳米照片纳米香蕉 2

Agent Skill

用于辅助图像生成、图片编辑、视觉素材处理或图像模型工作流。它适合让 Agent 根据文本生成图片、处理背景、整理视觉提示词或调用相关图像工具。使用时需要确认输入图片、版权来源、输出格式和模型限制;涉及人物、品牌、商品或公开展示素材时,应额外核对授权、真实性和内容合规边界。

总安装

6,724

周安装

283

GitHub Stars

公开资料未说明

下载量

2,355
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:nanophoto-nano-banana-2(纳米照片纳米香蕉 2)
来源仓库:https://github.com/nanophotohq/nanophoto-nano-banana-2
安装命令:
openclaw skills install nanophoto-nano-banana-2
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 nanophoto-nano-banana-2

简介

使用 NanoPhoto.AI Nano Banana 2 API 生成或编辑图像。

  • 支持文本到图像与图像到图像编辑两种模式。
  • 适用于创意设计与视觉内容快速生成需求。
  • 需注册 NanoPhoto.AI 账户并获取 API 密钥。
  • 注意输出分辨率与版权素材使用合规性。nanophoto-nano-banana-2 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

name
nano-banana-2
description
Generate or edit images with the NanoPhoto.AI Nano Banana 2 API. Use when: (1) User wants text-to-image generation, (2) User wants image-to-image editing with public image URLs, (3) User mentions Nano Banana 2, AI image generation, image editing, Google Search enhanced prompts, or checking Nano Banana generation status. Supports aspect ratio, quality, optional Google Search prompt enhancement, status checks, and optional in-process polling from a single bundled script. Prerequisite: Obtain an API key at https://nanophoto.ai/settings/apikeys and configure env.NANOPHOTO_API_KEY.
metadata
{"openclaw":{"homepage":"https://nanophoto.ai","requires":{"env":["NANOPHOTO_API_KEY"]},"primaryEnv":"NANOPHOTO_API_KEY"}}

Nano Banana 2

Generate or edit images through the NanoPhoto.AI Nano Banana 2 API.

Prerequisites

  1. Obtain an API key at: https://nanophoto.ai/settings/apikeys
  2. Configure NANOPHOTO_API_KEY before using the skill.
  3. Do not paste the API key into chat; store it in the platform's secure env setting for this skill.

Preferred OpenClaw setup:

  • Open the skill settings for this skill
  • Add an environment variable named NANOPHOTO_API_KEY
  • Paste the API key as its value

Equivalent config shape:

{
  "skills": {
    "entries": {
      "nano-banana-2": {
        "enabled": true,
        "env": {
          "NANOPHOTO_API_KEY": "your_api_key_here"
        }
      }
    }
  }
}

Other valid ways to provide the key:

  • Shell: export NANOPHOTO_API_KEY="your_api_key_here"
  • Tool-specific env config: any runtime that injects NANOPHOTO_API_KEY
  • OpenClaw config fallback: the bundled script also falls back to ~/.openclaw/openclaw.json at skills.entries.nano-banana-2.env.NANOPHOTO_API_KEY

Credential declaration summary:

  • Primary credential: NANOPHOTO_API_KEY
  • Resolution order in the bundled script: --api-keyNANOPHOTO_API_KEY environment variable → ~/.openclaw/openclaw.json skill env
  • No unrelated credentials are required

Recommended workflow

  1. Collect the user's prompt.
  2. Decide whether the request is generate (text-to-image) or edit (image-to-image).
  3. Choose aspectRatio, imageQuality, and whether googleSearch should be enabled.
  4. For edit mode, require one to fourteen public image URLs.
  5. Submit the generation request.
  6. If the user wants synchronous progress output in the same process, use submit --follow.
  7. Poll every 3-5 seconds until completed or failed.
  8. Return the final imageUrl, generationId, and progress details when available.

Parameter guidance

  • mode

- generate: text-to-image - edit: image-to-image; requires inputImageUrls

  • aspectRatio

- 16:9 - 9:16 - 4:3 - 3:4

  • imageQuality

- 1K: default, lowest cost - 2K: higher detail - 4K: highest detail and highest cost

  • googleSearch

- Disabled by default - Enable only when web context is likely to improve specificity

Preferred commands

Use the single bundled script with subcommands.

Submit text-to-image generation

python3 scripts/nano_banana_2.py submit \
  --prompt "A futuristic cityscape at sunset with flying cars and neon lights" \
  --mode generate \
  --aspect-ratio 16:9 \
  --image-quality 2K

Submit with Google Search enhancement and in-process polling

python3 scripts/nano_banana_2.py submit \
  --prompt "The latest Tesla Cybertruck in a desert landscape" \
  --mode generate \
  --aspect-ratio 16:9 \
  --image-quality 2K \
  --google-search \
  --follow

Submit image-to-image editing

python3 scripts/nano_banana_2.py submit \
  --prompt "Transform this photo into a watercolor painting style" \
  --mode edit \
  --aspect-ratio 16:9 \
  --image-quality 1K \
  --input-image-url https://static.nanophoto.ai/demo/nano-banana-pro.webp

Check status of an existing generation

python3 scripts/nano_banana_2.py status --generation-id abc123xyz

Script behavior

The bundled script resolves credentials in this order: --api-key, then NANOPHOTO_API_KEY from the environment, then ~/.openclaw/openclaw.json at skills.entries.nano-banana-2.env.NANOPHOTO_API_KEY.

Subcommands:

  • submit: submit a generation task
  • submit --follow: submit and keep polling in the same process
  • status: check an existing generationId

Cross-platform note:

  • Use python3 on macOS/Linux.
  • Use python on Windows unless python3 is available.
  • The script uses Python's standard HTTP client and does not require curl.
  • Use --json-only when another script/tool needs raw JSON output.
  • Use --poll-interval to override the default 4-second polling interval.
  • Default max wait is 180 seconds.

Manual API calls

Submit generation

curl -X POST "https://nanophoto.ai/api/nano-banana-2/generate" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NANOPHOTO_API_KEY" \
  --data-raw '{
    "prompt": "A futuristic cityscape at sunset with flying cars and neon lights",
    "mode": "generate",
    "aspectRatio": "16:9",
    "imageQuality": "2K"
  }'

Check status

curl -X POST "https://nanophoto.ai/api/nano-banana-2/check-status" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NANOPHOTO_API_KEY" \
  --data-raw '{"generationId": "abc123xyz"}'

Error handling

errorCodeCauseAction
LOGIN_REQUIREDInvalid or missing API keyVerify key at https://nanophoto.ai/settings/apikeys
API_KEY_RATE_LIMIT_EXCEEDEDRate limit exceededWait and retry
INSUFFICIENT_CREDITSNot enough creditsTop up credits
INVALID_PROMPTMissing or invalid promptAsk for a valid prompt
MISSING_INPUT_IMAGEEdit mode missing imagesAsk for public image URLs
TOO_MANY_IMAGESToo many images providedLimit to 14 public image URLs
IMAGE_URLS_REQUIREDAPI needs inputImageUrlsDo not send local files or base64
GENERATION_FAILEDServer-side generation errorRetry or simplify the prompt
NOT_FOUNDUnknown generation IDRe-submit or verify the ID
FORBIDDENGeneration not owned by callerVerify the account

Bundled files

  • scripts/nano_banana_2.py: single entry point for submit, status, and optional in-process polling
  • references/api.md: condensed API reference, parameters, and error behavior

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

92.38%
按下载量换算2,176

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

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。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