EachLabs AI视频编辑API：25+模型实现视频扩展、唇形同步、超分辨率与风格转换

eachlabs-video-edit by eachlabs/skills

76 周安装量

8 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/eachlabs/skills --skill eachlabs-video-edit

AI/机器学习内容创作 API

🇨🇳中文介绍

EachLabs 视频编辑

使用 EachLabs Predictions API，通过 25 个以上的 AI 模型来编辑、转换和增强现有视频。

身份验证

Header: X-API-Key: <your-api-key>

设置 EACHLABS_API_KEY 环境变量。在 eachlabs.ai 获取您的密钥。

模型选择指南

视频扩展

模型	Slug	最佳用途
Veo 3.1 Extend	`veo3-1-extend-video`	最佳质量的扩展
Veo 3.1 Fast Extend	`veo3-1-fast-extend-video`	快速扩展
PixVerse v5 Extend

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

唇形同步与说话头像

模型	Slug	最佳用途
Sync Lipsync v2 Pro	`sync-lipsync-v2-pro`	最佳唇形同步质量
PixVerse Lip Sync	`pixverse-lip-sync`	PixVerse 唇形同步
LatentSync	`latentsync`	开源唇形同步
Video Retalking	`video-retalking`	基于音频的唇形同步

模型	Slug	最佳用途
Runway Gen4 Aleph	`runway-gen4-aleph`	视频转换
Kling O1 Video Edit	`kling-o1-video-to-video-edit`	AI 视频编辑
Kling O1 V2V Reference	`kling-o1-video-to-video-reference`	基于参考的编辑
ByteDance Video Stylize	`bytedance-video-stylize`	风格迁移
Wan v2.2 Animate Move	`wan-v2-2-14b-animate-move`	运动动画
Wan v2.2 Animate Replace	`wan-v2-2-14b-animate-replace`	对象替换

视频超分辨率与增强

模型	Slug	最佳用途
Topaz Upscale Video	`topaz-upscale-video`	最佳质量超分辨率
Luma Ray 2 Video Reframe	`luma-dream-machine-ray-2-video-reframe`	视频重新构图
Luma Ray 2 Flash Reframe	`luma-dream-machine-ray-2-flash-video-reframe`	快速重新构图

模型	Slug	最佳用途
FFmpeg Merge Audio Video	`ffmpeg-api-merge-audio-video`	合并音轨
MMAudio V2	`mm-audio-v-2`	为视频添加音频
MMAudio	`mmaudio`	为视频添加音频
Auto Subtitle	`auto-subtitle`	生成字幕
Merge Videos	`merge-videos`	拼接视频

模型	Slug	最佳用途
Heygen Video Translate	`heygen-video-translate`	翻译视频语音

模型	Slug	最佳用途
Motion Fast	`motion-fast`	快速动作迁移
Infinitalk V2V	`infinitalk-video-to-video`	从视频生成说话头像

人脸替换（视频）

模型	Slug	最佳用途
Faceswap Video	`faceswap-video`	替换视频中的人脸

检查模型 GET https://api.eachlabs.ai/v1/model?slug=<slug> — 验证模型是否存在，并返回包含确切输入参数的 request_schema。在创建预测之前务必执行此步骤，以确保输入正确。
POST https://api.eachlabs.ai/v1/prediction，包含模型 slug、版本 "0.0.1" 以及符合 schema 的输入
轮询 GET https://api.eachlabs.ai/v1/prediction/{id} 直到状态变为 "success" 或 "failed"
提取响应中的输出视频 URL

使用 Veo 3.1 扩展视频

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "veo3-1-extend-video",
    "version": "0.0.1",
    "input": {
      "video_url": "https://example.com/video.mp4",
      "prompt": "Continue the scene with the camera slowly pulling back"
    }
  }'

使用 Sync v2 Pro 进行唇形同步

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "sync-lipsync-v2-pro",
    "version": "0.0.1",
    "input": {
      "video_url": "https://example.com/talking-head.mp4",
      "audio_url": "https://example.com/new-audio.mp3"
    }
  }'

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "auto-subtitle",
    "version": "0.0.1",
    "input": {
      "video_url": "https://example.com/video.mp4"
    }
  }'

合并音频与视频

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "ffmpeg-api-merge-audio-video",
    "version": "0.0.1",
    "input": {
      "video_url": "https://example.com/video.mp4",
      "audio_url": "https://example.com/music.mp3",
      "start_offset": 0
    }
  }'

使用 Topaz 提升视频分辨率

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "topaz-upscale-video",
    "version": "0.0.1",
    "input": {
      "video_url": "https://example.com/low-res-video.mp4"
    }
  }'

查看 references/MODELS.md 获取每个模型的完整参数详情。

🇺🇸English

EachLabs Video Edit

Edit, transform, and enhance existing videos using 25+ AI models via the EachLabs Predictions API.

Authentication

Header: X-API-Key: <your-api-key>

Set the EACHLABS_API_KEY environment variable. Get your key at eachlabs.ai.

Model Selection Guide

Video Extension

Model	Slug	Best For
Veo 3.1 Extend	`veo3-1-extend-video`	Best quality extension
Veo 3.1 Fast Extend	`veo3-1-fast-extend-video`	Fast extension
PixVerse v5 Extend	`pixverse-v5-extend`	PixVerse extension
PixVerse v4.5 Extend	`pixverse-v4-5-extend`	Older PixVerse extension

Lip Sync & Talking Head

Model	Slug	Best For
Sync Lipsync v2 Pro	`sync-lipsync-v2-pro`	Best lip sync quality
PixVerse Lip Sync	`pixverse-lip-sync`	PixVerse lip sync
LatentSync	`latentsync`	Open-source lip sync
Video Retalking	`video-retalking`	Audio-based lip sync

Video Transformation

Model	Slug	Best For
Runway Gen4 Aleph	`runway-gen4-aleph`	Video transformation
Kling O1 Video Edit	`kling-o1-video-to-video-edit`	AI video editing
Kling O1 V2V Reference	`kling-o1-video-to-video-reference`	Reference-based edit
ByteDance Video Stylize	`bytedance-video-stylize`	Style transfer
Wan v2.2 Animate Move	`wan-v2-2-14b-animate-move`

Video Upscaling & Enhancement

Model	Slug	Best For
Topaz Upscale Video	`topaz-upscale-video`	Best quality upscale
Luma Ray 2 Video Reframe	`luma-dream-machine-ray-2-video-reframe`	Video reframing
Luma Ray 2 Flash Reframe	`luma-dream-machine-ray-2-flash-video-reframe`	Fast reframing

Audio & Subtitles

Model	Slug	Best For
FFmpeg Merge Audio Video	`ffmpeg-api-merge-audio-video`	Merge audio track
MMAudio V2	`mm-audio-v-2`	Add audio to video
MMAudio	`mmaudio`	Add audio to video
Auto Subtitle	`auto-subtitle`	Generate subtitles
Merge Videos	`merge-videos`

Video Translation

Model	Slug	Best For
Heygen Video Translate	`heygen-video-translate`	Translate video speech

Motion Transfer

Model	Slug	Best For
Motion Fast	`motion-fast`	Fast motion transfer
Infinitalk V2V	`infinitalk-video-to-video`	Talking head from video

Face Swap (Video)

Model	Slug	Best For
Faceswap Video	`faceswap-video`	Swap face in video

Prediction Flow

Check model GET https://api.eachlabs.ai/v1/model?slug=<slug> — validates the model exists and returns the request_schema with exact input parameters. Always do this before creating a prediction to ensure correct inputs.
POST https://api.eachlabs.ai/v1/prediction with model slug, version "0.0.1", and input matching the schema
Poll GET https://api.eachlabs.ai/v1/prediction/{id} until status is "success" or "failed"
Extract the output video URL from the response

Examples

Extend a Video with Veo 3.1

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "veo3-1-extend-video",
    "version": "0.0.1",
    "input": {
      "video_url": "https://example.com/video.mp4",
      "prompt": "Continue the scene with the camera slowly pulling back"
    }
  }'

Lip Sync with Sync v2 Pro

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "sync-lipsync-v2-pro",
    "version": "0.0.1",
    "input": {
      "video_url": "https://example.com/talking-head.mp4",
      "audio_url": "https://example.com/new-audio.mp3"
    }
  }'

Add Subtitles

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "auto-subtitle",
    "version": "0.0.1",
    "input": {
      "video_url": "https://example.com/video.mp4"
    }
  }'

Merge Audio with Video

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "ffmpeg-api-merge-audio-video",
    "version": "0.0.1",
    "input": {
      "video_url": "https://example.com/video.mp4",
      "audio_url": "https://example.com/music.mp3",
      "start_offset": 0
    }
  }'

Upscale Video with Topaz

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "topaz-upscale-video",
    "version": "0.0.1",
    "input": {
      "video_url": "https://example.com/low-res-video.mp4"
    }
  }'

Parameter Reference

See references/MODELS.md for complete parameter details for each model.

Weekly Installs

Repository

eachlabs/skills

GitHub Stars

First Seen

Feb 9, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

gemini-cli75

cursor74

opencode74

kimi-cli73

codex73

github-copilot73

超能力技能使用指南：AI助手技能调用优先级与工作流程详解

52,100 周安装