← 返回 Skills 市场
Ai Video Gen Pro
作者
bingze00000
· GitHub ↗
· v1.0.0
· MIT-0
146
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install ai-video-gen-pro
功能描述
Generate AI videos with Google Veo, Seedance, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 1.5 Pro, Wan 2.5, Grok Imagine...
使用说明 (SKILL.md)
\r \r
AI Video Generation\r
\r
Generate videos with 40+ AI models via inference.sh CLI.\r
\r
\r
\r
Quick Start\r
\r
Requires inference.sh CLI (
infsh). Install instructions\r \r
infsh login\r
\r
# Generate a video with Veo\r
infsh app run google/veo-3-1-fast --input '{"prompt": "drone shot flying over a forest"}'\r
```\r
\r
\r
## Available Models\r
\r
### Text-to-Video\r
\r
| Model | App ID | Best For |\r
|-------|--------|----------|\r
| Veo 3.1 Fast | `google/veo-3-1-fast` | Fast, with optional audio |\r
| Veo 3.1 | `google/veo-3-1` | Best quality, frame interpolation |\r
| Veo 3 | `google/veo-3` | High quality with audio |\r
| Veo 3 Fast | `google/veo-3-fast` | Fast with audio |\r
| Veo 2 | `google/veo-2` | Realistic videos |\r
| **P-Video** | `pruna/p-video` | Fast, economical, with audio support |\r
| **WAN-T2V** | `pruna/wan-t2v` | Economical 480p/720p |\r
| Grok Video | `xai/grok-imagine-video` | xAI, configurable duration |\r
| Seedance 1.5 Pro | `bytedance/seedance-1-5-pro` | With first-frame control |\r
| Seedance 1.0 Pro | `bytedance/seedance-1-0-pro` | Up to 1080p |\r
\r
### Image-to-Video\r
\r
| Model | App ID | Best For |\r
|-------|--------|----------|\r
| Wan 2.5 | `falai/wan-2-5` | Animate any image |\r
| Wan 2.5 I2V | `falai/wan-2-5-i2v` | High quality i2v |\r
| **WAN-I2V** | `pruna/wan-i2v` | Economical 480p/720p |\r
| **P-Video** | `pruna/p-video` | Fast i2v with audio |\r
| Seedance Lite | `bytedance/seedance-1-0-lite` | Lightweight 720p |\r
\r
### Avatar / Lipsync\r
\r
| Model | App ID | Best For |\r
|-------|--------|----------|\r
| OmniHuman 1.5 | `bytedance/omnihuman-1-5` | Multi-character |\r
| OmniHuman 1.0 | `bytedance/omnihuman-1-0` | Single character |\r
| Fabric 1.0 | `falai/fabric-1-0` | Image talks with lipsync |\r
| PixVerse Lipsync | `falai/pixverse-lipsync` | Realistic lipsync |\r
\r
### Utilities\r
\r
| Tool | App ID | Description |\r
|------|--------|-------------|\r
| HunyuanVideo Foley | `infsh/hunyuanvideo-foley` | Add sound effects to video |\r
| Topaz Upscaler | `falai/topaz-video-upscaler` | Upscale video quality |\r
| Media Merger | `infsh/media-merger` | Merge videos with transitions |\r
\r
## Browse All Video Apps\r
\r
```bash\r
infsh app list --category video\r
```\r
\r
## Examples\r
\r
### Text-to-Video with Veo\r
\r
```bash\r
infsh app run google/veo-3-1-fast --input '{\r
"prompt": "A timelapse of a flower blooming in a garden"\r
}'\r
```\r
\r
### Grok Video\r
\r
```bash\r
infsh app run xai/grok-imagine-video --input '{\r
"prompt": "Waves crashing on a beach at sunset",\r
"duration": 5\r
}'\r
```\r
\r
### Image-to-Video with Wan 2.5\r
\r
```bash\r
infsh app run falai/wan-2-5 --input '{\r
"image_url": "https://your-image.jpg"\r
}'\r
```\r
\r
### AI Avatar / Talking Head\r
\r
```bash\r
infsh app run bytedance/omnihuman-1-5 --input '{\r
"image_url": "https://portrait.jpg",\r
"audio_url": "https://speech.mp3"\r
}'\r
```\r
\r
### Fabric Lipsync\r
\r
```bash\r
infsh app run falai/fabric-1-0 --input '{\r
"image_url": "https://face.jpg",\r
"audio_url": "https://audio.mp3"\r
}'\r
```\r
\r
### PixVerse Lipsync\r
\r
```bash\r
infsh app run falai/pixverse-lipsync --input '{\r
"image_url": "https://portrait.jpg",\r
"audio_url": "https://speech.mp3"\r
}'\r
```\r
\r
### Video Upscaling\r
\r
```bash\r
infsh app run falai/topaz-video-upscaler --input '{"video_url": "https://..."}'\r
```\r
\r
### Add Sound Effects (Foley)\r
\r
```bash\r
infsh app run infsh/hunyuanvideo-foley --input '{\r
"video_url": "https://silent-video.mp4",\r
"prompt": "footsteps on gravel, birds chirping"\r
}'\r
```\r
\r
### Merge Videos\r
\r
```bash\r
infsh app run infsh/media-merger --input '{\r
"videos": ["https://clip1.mp4", "https://clip2.mp4"],\r
"transition": "fade"\r
}'\r
```\r
\r
## Related Skills\r
\r
```bash\r
# Full platform skill (all 150+ apps)\r
npx skills add inference-sh/skills@infsh-cli\r
\r
# Pruna P-Video (fast & economical)\r
npx skills add inference-sh/skills@p-video\r
\r
# Google Veo specific\r
npx skills add inference-sh/skills@google-veo\r
\r
# AI avatars & lipsync\r
npx skills add inference-sh/skills@ai-avatar-video\r
\r
# Text-to-speech (for video narration)\r
npx skills add inference-sh/skills@text-to-speech\r
\r
# Image generation (for image-to-video)\r
npx skills add inference-sh/skills@ai-image-generation\r
\r
# Twitter (post videos)\r
npx skills add inference-sh/skills@twitter-automation\r
```\r
\r
Browse all apps: `infsh app list`\r
\r
## Documentation\r
\r
- [Running Apps](https://inference.sh/docs/apps/running) - How to run apps via CLI\r
- [Streaming Results](https://inference.sh/docs/api/sdk/streaming) - Real-time progress updates\r
- [Content Pipeline Example](https://inference.sh/docs/examples/content-pipeline) - Building media workflows\r
\r
安全使用建议
This skill is an instructions-only wrapper around the inference.sh (infsh) CLI — it doesn't contain code or request secrets itself. Before using: verify you trust inference.sh (the installation link is an external raw GitHub URL), understand that 'infsh login' will create credentials with that service, and review their privacy/terms and any billing. The meta.json's 'requests' dependency and the listed pricing are extraneous for an instruction-only skill — treat them as informational but not required. When supplying image/audio URLs, avoid exposing private/local files via public URLs. If you don't trust inference.sh, don't run the install/login steps.
功能分析
Type: OpenClaw Skill
Name: ai-video-gen-pro
Version: 1.0.0
The skill bundle provides a legitimate interface for AI video generation using the inference.sh CLI. It follows security best practices by restricting the agent's shell access to the specific 'infsh' command via the 'allowed-tools' configuration in SKILL.md. There are no signs of data exfiltration, malicious execution, or harmful prompt injection.
能力评估
Purpose & Capability
The name/description advertise running 40+ models via the inference.sh CLI and the SKILL.md only instructs use of that CLI — that is coherent. Minor mismatch: _meta.json lists a Python requirement ('requests') and pricing info which are unnecessary for an instruction-only skill.
Instruction Scope
SKILL.md confines the agent to running infsh commands, listing apps, and providing input URLs for images/audio. It does not instruct reading unrelated host files or env vars. It does require the user to run 'infsh login', which is expected for a CLI that needs authentication.
Install Mechanism
There is no install spec and no code shipped with the skill (lowest risk). The README points to an external raw GitHub URL for infsh install docs — expected for an instruction-only wrapper, but installing that external CLI is an additional trust step the user must accept.
Credentials
The skill itself requests no env vars or credentials, which is proportional. However, using 'infsh login' implies providing credentials to the inference.sh service; the skill does not declare or manage those. Also note the meta.json 'requests' requirement is unnecessary and unexplained.
Persistence & Privilege
The skill is not force-installed (always: false) and uses the platform default allowing autonomous invocation. That is normal and not excessive here.
如何使用
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install ai-video-gen-pro - 安装完成后,直接呼叫该 Skill 的名称或使用
/ai-video-gen-pro触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.0
Initial release of AI Video Generation skill.
- Generate AI videos with 40+ models (Veo, Seedance, Wan, Grok, and more) via inference.sh CLI.
- Supports text-to-video, image-to-video, lipsync, avatar animation, upscaling, and foley sound.
- Includes usage instructions, model/app IDs, and examples for each capability.
- Suitable for creating social videos, marketing, explainers, product demos, and AI avatars.
- Lists related skills for advanced workflows.
元数据
常见问题
Ai Video Gen Pro 是什么?
Generate AI videos with Google Veo, Seedance, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 1.5 Pro, Wan 2.5, Grok Imagine... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 146 次。
如何安装 Ai Video Gen Pro?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-video-gen-pro」即可一键安装,无需额外配置。
Ai Video Gen Pro 是免费的吗?
是的,Ai Video Gen Pro 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
Ai Video Gen Pro 支持哪些平台?
Ai Video Gen Pro 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Ai Video Gen Pro?
由 bingze00000(@bingze00000)开发并维护,当前版本 v1.0.0。
推荐 Skills