AI Video Generation
Generate videos with 40+ AI models via inference.sh CLI.

Quick Start
CODEBLOCK0
Install note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.
Available Models
Text-to-Video
| Model | App ID | Best For |
|---|
| Veo 3.1 Fast | INLINECODE1 | Fast, with optional audio |
| Veo 3.1 |
google/veo-3-1 | Best quality, frame interpolation |
| Veo 3 |
google/veo-3 | High quality with audio |
| Veo 3 Fast |
google/veo-3-fast | Fast with audio |
| Veo 2 |
google/veo-2 | Realistic videos |
| Grok Video |
xai/grok-imagine-video | xAI, configurable duration |
| Seedance 1.5 Pro |
bytedance/seedance-1-5-pro | With first-frame control |
| Seedance 1.0 Pro |
bytedance/seedance-1-0-pro | Up to 1080p |
Image-to-Video
| Model | App ID | Best For |
|---|
| Wan 2.5 | INLINECODE9 | Animate any image |
| Wan 2.5 I2V |
falai/wan-2-5-i2v | High quality i2v |
| Seedance Lite |
bytedance/seedance-1-0-lite | Lightweight 720p |
Avatar / Lipsync
| Model | App ID | Best For |
|---|
| OmniHuman 1.5 | INLINECODE12 | Multi-character |
| OmniHuman 1.0 |
bytedance/omnihuman-1-0 | Single character |
| Fabric 1.0 |
falai/fabric-1-0 | Image talks with lipsync |
| PixVerse Lipsync |
falai/pixverse-lipsync | Realistic lipsync |
Utilities
| Tool | App ID | Description |
|---|
| HunyuanVideo Foley | INLINECODE16 | Add sound effects to video |
| Topaz Upscaler |
falai/topaz-video-upscaler | Upscale video quality |
| Media Merger |
infsh/media-merger | Merge videos with transitions |
Browse All Video Apps
CODEBLOCK1
Examples
Text-to-Video with Veo
CODEBLOCK2
Grok Video
CODEBLOCK3
Image-to-Video with Wan 2.5
CODEBLOCK4
AI Avatar / Talking Head
CODEBLOCK5
Fabric Lipsync
CODEBLOCK6
PixVerse Lipsync
CODEBLOCK7
Video Upscaling
CODEBLOCK8
Add Sound Effects (Foley)
CODEBLOCK9
Merge Videos
CODEBLOCK10
Related Skills
CODEBLOCK11
Browse all apps: INLINECODE19
Documentation
AI视频生成
通过inference.sh命令行界面,使用40多种AI模型生成视频。

快速开始
bash
安装命令行工具
curl -fsSL https://cli.inference.sh | sh && infsh login
使用Veo生成视频
infsh app run google/veo-3-1-fast --input {prompt: 无人机飞越森林的航拍镜头}
安装说明: 安装脚本仅检测您的操作系统/架构,从dist.inference.sh下载匹配的二进制文件,并验证其SHA-256校验和。无需提升权限或后台进程。提供手动安装与验证方式。
可用模型
文本转视频
| 模型 | 应用ID | 适用场景 |
|---|
| Veo 3.1 Fast | google/veo-3-1-fast | 快速生成,可选音频 |
| Veo 3.1 |
google/veo-3-1 | 最佳质量,帧插值 |
| Veo 3 | google/veo-3 | 高质量带音频 |
| Veo 3 Fast | google/veo-3-fast | 快速生成带音频 |
| Veo 2 | google/veo-2 | 逼真视频 |
| Grok Video | xai/grok-imagine-video | xAI,可配置时长 |
| Seedance 1.5 Pro | bytedance/seedance-1-5-pro | 支持首帧控制 |
| Seedance 1.0 Pro | bytedance/seedance-1-0-pro | 最高1080p |
图片转视频
| 模型 | 应用ID | 适用场景 |
|---|
| Wan 2.5 | falai/wan-2-5 | 动画化任意图片 |
| Wan 2.5 I2V |
falai/wan-2-5-i2v | 高质量图片转视频 |
| Seedance Lite | bytedance/seedance-1-0-lite | 轻量级720p |
虚拟形象/口型同步
| 模型 | 应用ID | 适用场景 |
|---|
| OmniHuman 1.5 | bytedance/omnihuman-1-5 | 多角色 |
| OmniHuman 1.0 |
bytedance/omnihuman-1-0 | 单角色 |
| Fabric 1.0 | falai/fabric-1-0 | 图片说话带口型同步 |
| PixVerse Lipsync | falai/pixverse-lipsync | 逼真口型同步 |
实用工具
| 工具 | 应用ID | 描述 |
|---|
| HunyuanVideo Foley | infsh/hunyuanvideo-foley | 为视频添加音效 |
| Topaz Upscaler |
falai/topaz-video-upscaler | 提升视频画质 |
| Media Merger | infsh/media-merger | 合并视频并添加转场效果 |
浏览所有视频应用
bash
infsh app list --category video
示例
使用Veo进行文本转视频
bash
infsh app run google/veo-3-1-fast --input {
prompt: 花园中花朵绽放的延时摄影
}
Grok视频
bash
infsh app run xai/grok-imagine-video --input {
prompt: 日落时分海浪拍打沙滩,
duration: 5
}
使用Wan 2.5进行图片转视频
bash
infsh app run falai/wan-2-5 --input {
image_url: https://your-image.jpg
}
AI虚拟形象/说话头像
bash
infsh app run bytedance/omnihuman-1-5 --input {
image_url: https://portrait.jpg,
audio_url: https://speech.mp3
}
Fabric口型同步
bash
infsh app run falai/fabric-1-0 --input {
image_url: https://face.jpg,
audio_url: https://audio.mp3
}
PixVerse口型同步
bash
infsh app run falai/pixverse-lipsync --input {
image_url: https://portrait.jpg,
audio_url: https://speech.mp3
}
视频画质提升
bash
infsh app run falai/topaz-video-upscaler --input {video_url: https://...}
添加音效(Foley)
bash
infsh app run infsh/hunyuanvideo-foley --input {
video_url: https://silent-video.mp4,
prompt: 碎石上的脚步声,鸟鸣声
}
合并视频
bash
infsh app run infsh/media-merger --input {
videos: [https://clip1.mp4, https://clip2.mp4],
transition: fade
}
相关技能
bash
完整平台技能(150+应用)
npx skills add inference-sh/skills@inference-sh
Google Veo专用
npx skills add inference-sh/skills@google-veo
AI虚拟形象与口型同步
npx skills add inference-sh/skills@ai-avatar-video
文本转语音(用于视频旁白)
npx skills add inference-sh/skills@text-to-speech
图片生成(用于图片转视频)
npx skills add inference-sh/skills@ai-image-generation
Twitter(发布视频)
npx skills add inference-sh/skills@twitter-automation
浏览所有应用:infsh app list
文档