وثائق NanoPhoto.AIOpenClaw Skills
Use NanoPhoto.AI skills through OpenClaw AI assistant - send commands via Telegram, Feishu, WeChat and more to generate videos and images.
Demo
Video recorded by our fan 有云转晴
Overview
OpenClaw is an AI assistant that you can interact with through IM channels such as Telegram, Feishu (Lark), WeChat, and more. By installing NanoPhoto.AI skills, you can send commands directly in your favorite messaging app to generate videos, create images, and use prompt tools — no coding required.
Official directory: clawhub.ai/u/nanophotohq
Quick Install
Install any skill via the clawhub CLI:
npx clawhub@latest install <skill-name>For example:
npx clawhub@latest install sora-2-generate
npx clawhub@latest install nano-banana-pro
npx clawhub@latest install veo-3-1Prerequisites
All skills require a NANOPHOTO_API_KEY:
- Sign in to nanophoto.ai
- Go to Settings > API Keys
- Create a new API key
- Configure the key in your OpenClaw skill settings
Available Skills
| Skill | Description |
|---|---|
| sora-2-generate | Text-to-video and image-to-video with Sora 2 |
| veo-3-1 | Multi-shot long-form video with Google Veo 3.1 |
| nano-banana-pro | AI image generation and editing |
| nano-banana-2 | Image generation with Google Search enhancement |
| video-prompt-generator | Professional video prompt generation |
| video-reverse-prompt | Extract prompts from existing videos |
| sora-watermark-remover | Remove watermarks from Sora 2 videos |
| comic-drama-generate | Multi-skill comic drama production pipeline |
Veo 3.1 Video Generation API
API for generating videos using Google Veo 3.1 with text-to-video, reference image, and first/last frame modes. Supports multi-shot long videos up to 168 seconds.
Sora 2 Generate
Generate videos with the NanoPhoto.AI Sora 2 API in text-to-video or image-to-video mode via OpenClaw.