eachlabs-video-generation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

EachLabs Video Generation

EachLabs 视频生成

Generate new videos from text prompts, images, or reference inputs using 165+ AI models via the EachLabs Predictions API. For editing existing videos (upscaling, lip sync, extension, subtitles), see the

eachlabs-video-edit

skill.

借助EachLabs Predictions API，通过165+种AI模型，基于文本提示词、图片或参考输入生成新视频。若要编辑现有视频（如分辨率提升、唇形同步、视频延长、添加字幕），请查看

eachlabs-video-edit

技能。

Authentication

身份验证

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

Set the

EACHLABS_API_KEY

environment variable or pass it directly. Get your key at eachlabs.ai.

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

可以设置

EACHLABS_API_KEY

环境变量，或者直接传入API密钥。请前往eachlabs.ai获取你的密钥。

Quick Start

快速开始

1. Create a Prediction

1. 创建生成任务

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "pixverse-v5-6-text-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "A golden retriever running through a meadow at sunset, cinematic slow motion",
      "resolution": "720p",
      "duration": "5",
      "aspect_ratio": "16:9"
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "pixverse-v5-6-text-to-video",
    "version": "0.0.1",
    "input": {
      "prompt": "A golden retriever running through a meadow at sunset, cinematic slow motion",
      "resolution": "720p",
      "duration": "5",
      "aspect_ratio": "16:9"
    }
  }'

2. Poll for Result

2. 查询生成结果

bash

curl https://api.eachlabs.ai/v1/prediction/{prediction_id} \
  -H "X-API-Key: $EACHLABS_API_KEY"

Poll until

status

"success"

"failed"

. The output video URL is in the response.

bash

curl https://api.eachlabs.ai/v1/prediction/{prediction_id} \
  -H "X-API-Key: $EACHLABS_API_KEY"

持续查询直到

status

变为

"success"

或

"failed"

。输出视频的URL会包含在响应结果中。

Model Selection Guide

模型选择指南

Text-to-Video

文本转视频

Model	Slug	Best For
Pixverse v5.6	`pixverse-v5-6-text-to-video`	General purpose, audio generation
XAI Grok Imagine	`xai-grok-imagine-text-to-video`	Fast creative
Kandinsky 5 Pro	`kandinsky5-pro-text-to-video`	Artistic, high quality
Seedance v1.5 Pro	`seedance-v1-5-pro-text-to-video`	Cinematic quality
Wan v2.6	`wan-v2-6-text-to-video`	Long/narrative content
Kling v2.6 Pro	`kling-v2-6-pro-text-to-video`	Motion control
Pika v2.2	`pika-v2-2-text-to-video`	Stylized, effects
Minimax Hailuo V2.3 Pro	`minimax-hailuo-v2-3-pro-text-to-video`	High fidelity
Sora 2 Pro	`sora-2-text-to-video-pro`	Premium quality
Veo 3	`veo-3`	Google's best quality
Veo 3.1	`veo3-1-text-to-video`	Latest Google model
LTX v2 Fast	`ltx-v-2-text-to-video-fast`	Fastest generation
Moonvalley Marey	`moonvalley-marey-text-to-video`	Cinematic style
Ovi	`ovi-text-to-video`	General purpose

模型	标识（Slug）	适用场景
Pixverse v5.6	`pixverse-v5-6-text-to-video`	通用场景、支持音频生成
XAI Grok Imagine	`xai-grok-imagine-text-to-video`	快速创意生成
Kandinsky 5 Pro	`kandinsky5-pro-text-to-video`	艺术风格、高质量生成
Seedance v1.5 Pro	`seedance-v1-5-pro-text-to-video`	电影级画质
Wan v2.6	`wan-v2-6-text-to-video`	长视频/叙事类内容
Kling v2.6 Pro	`kling-v2-6-pro-text-to-video`	运动控制
Pika v2.2	`pika-v2-2-text-to-video`	风格化、特效制作
Minimax Hailuo V2.3 Pro	`minimax-hailuo-v2-3-pro-text-to-video`	高保真度
Sora 2 Pro	`sora-2-text-to-video-pro`	旗舰级画质
Veo 3	`veo-3`	Google旗舰级模型
Veo 3.1	`veo3-1-text-to-video`	Google最新模型
LTX v2 Fast	`ltx-v-2-text-to-video-fast`	最快生成速度
Moonvalley Marey	`moonvalley-marey-text-to-video`	电影风格
Ovi	`ovi-text-to-video`	通用场景

Image-to-Video

图片转视频

Model	Slug	Best For
Pixverse v5.6	`pixverse-v5-6-image-to-video`	General purpose
XAI Grok Imagine	`xai-grok-imagine-image-to-video`	Creative edits
Wan v2.6 Flash	`wan-v2-6-image-to-video-flash`	Fastest
Wan v2.6	`wan-v2-6-image-to-video`	High quality
Seedance v1.5 Pro	`seedance-v1-5-pro-image-to-video`	Cinematic
Kandinsky 5 Pro	`kandinsky5-pro-image-to-video`	Artistic
Kling v2.6 Pro I2V	`kling-v2-6-pro-image-to-video`	Best Kling quality
Kling O1	`kling-o1-image-to-video`	Latest Kling model
Pika v2.2 I2V	`pika-v2-2-image-to-video`	Effects, PikaScenes
Minimax Hailuo V2.3 Pro	`minimax-hailuo-v2-3-pro-image-to-video`	High fidelity
Sora 2 I2V	`sora-2-image-to-video`	Premium quality
Veo 3.1 I2V	`veo3-1-image-to-video`	Google's latest
Runway Gen4 Turbo	`gen4-turbo`	Fast, film quality
Veed Fabric 1.0	`veed-fabric-1-0`	Social media

模型	标识（Slug）	适用场景
Pixverse v5.6	`pixverse-v5-6-image-to-video`	通用场景
XAI Grok Imagine	`xai-grok-imagine-image-to-video`	创意编辑
Wan v2.6 Flash	`wan-v2-6-image-to-video-flash`	最快生成速度
Wan v2.6	`wan-v2-6-image-to-video`	高质量生成
Seedance v1.5 Pro	`seedance-v1-5-pro-image-to-video`	电影级画质
Kandinsky 5 Pro	`kandinsky5-pro-image-to-video`	艺术风格
Kling v2.6 Pro I2V	`kling-v2-6-pro-image-to-video`	Kling系列最高画质
Kling O1	`kling-o1-image-to-video`	Kling最新模型
Pika v2.2 I2V	`pika-v2-2-image-to-video`	特效制作、PikaScenes场景
Minimax Hailuo V2.3 Pro	`minimax-hailuo-v2-3-pro-image-to-video`	高保真度
Sora 2 I2V	`sora-2-image-to-video`	旗舰级画质
Veo 3.1 I2V	`veo3-1-image-to-video`	Google最新模型
Runway Gen4 Turbo	`gen4-turbo`	快速生成、电影级画质
Veed Fabric 1.0	`veed-fabric-1-0`	社交媒体适用

Transitions & Effects

转场与特效

Model	Slug	Best For
Pixverse v5.6 Transition	`pixverse-v5-6-transition`	Smooth transitions
Pika v2.2 PikaScenes	`pika-v2-2-pikascenes`	Scene effects
Pixverse v4.5 Effect	`pixverse-v4-5-effect`	Video effects
Veo 3.1 First Last Frame	`veo3-1-first-last-frame-to-video`	Interpolation

模型	标识（Slug）	适用场景
Pixverse v5.6 Transition	`pixverse-v5-6-transition`	平滑转场
Pika v2.2 PikaScenes	`pika-v2-2-pikascenes`	场景特效
Pixverse v4.5 Effect	`pixverse-v4-5-effect`	视频特效
Veo 3.1 First Last Frame	`veo3-1-first-last-frame-to-video`	帧插值

Motion Control & Animation

运动控制与动画

Model	Slug	Best For
Kling v2.6 Pro Motion	`kling-v2-6-pro-motion-control`	Pro motion control
Kling v2.6 Standard Motion	`kling-v2-6-standard-motion-control`	Standard motion
Motion Fast	`motion-fast`	Fast motion transfer
Motion Video 14B	`motion-video-14b`	High quality motion
Wan v2.6 R2V	`wan-v2-6-reference-to-video`	Reference-based
Kling O1 Reference I2V	`kling-o1-reference-image-to-video`	Reference-based

模型	标识（Slug）	适用场景
Kling v2.6 Pro Motion	`kling-v2-6-pro-motion-control`	专业级运动控制
Kling v2.6 Standard Motion	`kling-v2-6-standard-motion-control`	标准运动控制
Motion Fast	`motion-fast`	快速动作迁移
Motion Video 14B	`motion-video-14b`	高质量动作生成
Wan v2.6 R2V	`wan-v2-6-reference-to-video`	参考素材驱动
Kling O1 Reference I2V	`kling-o1-reference-image-to-video`	参考素材驱动

Talking Head & Lip Sync

数字人播报与唇形同步

Model	Slug	Best For
Bytedance Omnihuman v1.5	`bytedance-omnihuman-v1-5`	Full body animation
Creatify Aurora	`creatify-aurora`	Audio-driven avatar
Infinitalk I2V	`infinitalk-image-to-video`	Image talking head
Infinitalk V2V	`infinitalk-video-to-video`	Video talking head
Sync Lipsync v2 Pro	`sync-lipsync-v2-pro`	Lip sync
Kling Avatar v2 Pro	`kling-avatar-v2-pro`	Pro avatar
Kling Avatar v2 Standard	`kling-avatar-v2-standard`	Standard avatar
Echomimic V3	`echomimic-v3`	Face animation
Stable Avatar	`stable-avatar`	Stable talking head

模型	标识（Slug）	适用场景
Bytedance Omnihuman v1.5	`bytedance-omnihuman-v1-5`	全身动画
Creatify Aurora	`creatify-aurora`	音频驱动虚拟形象
Infinitalk I2V	`infinitalk-image-to-video`	图片生成数字人播报
Infinitalk V2V	`infinitalk-video-to-video`	视频生成数字人播报
Sync Lipsync v2 Pro	`sync-lipsync-v2-pro`	唇形同步
Kling Avatar v2 Pro	`kling-avatar-v2-pro`	专业级虚拟形象
Kling Avatar v2 Standard	`kling-avatar-v2-standard`	标准虚拟形象
Echomimic V3	`echomimic-v3`	面部动画
Stable Avatar	`stable-avatar`	稳定数字人播报

Prediction Flow

生成任务流程

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 parameters matching the schema

Poll

GET https://api.eachlabs.ai/v1/prediction/{id}

until status is

"success"

"failed"

Extract the output video URL from the response

验证模型：调用
```
GET https://api.eachlabs.ai/v1/model?slug=<slug>
```
—— 验证模型是否存在，并返回包含精确输入参数的
```
request_schema
```
。创建生成任务前务必执行此步骤，确保输入参数正确。
提交请求：调用
```
POST https://api.eachlabs.ai/v1/prediction
```
，传入模型标识、版本
```
"0.0.1"
```
，以及符合schema要求的输入参数。

轮询结果：调用

GET https://api.eachlabs.ai/v1/prediction/{id}

，直到状态变为

"success"

或

"failed"

。

提取结果：从响应中获取输出视频的URL。

Examples

示例

Image-to-Video with Wan v2.6 Flash

基于Wan v2.6 Flash的图片转视频

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "wan-v2-6-image-to-video-flash",
    "version": "0.0.1",
    "input": {
      "image_url": "https://example.com/photo.jpg",
      "prompt": "The person turns to face the camera and smiles",
      "duration": "5",
      "resolution": "1080p"
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "wan-v2-6-image-to-video-flash",
    "version": "0.0.1",
    "input": {
      "image_url": "https://example.com/photo.jpg",
      "prompt": "The person turns to face the camera and smiles",
      "duration": "5",
      "resolution": "1080p"
    }
  }'

Video Transition with Pixverse

基于Pixverse的视频转场

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "pixverse-v5-6-transition",
    "version": "0.0.1",
    "input": {
      "prompt": "Smooth morphing transition between the two images",
      "first_image_url": "https://example.com/start.jpg",
      "end_image_url": "https://example.com/end.jpg",
      "duration": "5",
      "resolution": "720p"
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "pixverse-v5-6-transition",
    "version": "0.0.1",
    "input": {
      "prompt": "Smooth morphing transition between the two images",
      "first_image_url": "https://example.com/start.jpg",
      "end_image_url": "https://example.com/end.jpg",
      "duration": "5",
      "resolution": "720p"
    }
  }'

Motion Control with Kling v2.6

基于Kling v2.6的运动控制

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "kling-v2-6-pro-motion-control",
    "version": "0.0.1",
    "input": {
      "image_url": "https://example.com/character.jpg",
      "video_url": "https://example.com/dance-reference.mp4",
      "character_orientation": "video"
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "kling-v2-6-pro-motion-control",
    "version": "0.0.1",
    "input": {
      "image_url": "https://example.com/character.jpg",
      "video_url": "https://example.com/dance-reference.mp4",
      "character_orientation": "video"
    }
  }'

Talking Head with Omnihuman

基于Omnihuman的数字人播报

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "bytedance-omnihuman-v1-5",
    "version": "0.0.1",
    "input": {
      "image_url": "https://example.com/portrait.jpg",
      "audio_url": "https://example.com/speech.mp3",
      "resolution": "1080p"
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "bytedance-omnihuman-v1-5",
    "version": "0.0.1",
    "input": {
      "image_url": "https://example.com/portrait.jpg",
      "audio_url": "https://example.com/speech.mp3",
      "resolution": "1080p"
    }
  }'

Prompt Tips

提示词技巧

Be specific about motion: "camera slowly pans left" rather than "nice camera movement"
Include style keywords: "cinematic", "anime", "3D animation", "cyberpunk"
Describe timing: "slow motion", "time-lapse", "fast-paced"
For image-to-video, describe what should change from the static image
Use negative prompts to avoid unwanted elements (where supported)

明确描述运动细节：比如用“镜头缓慢向左平移”而非“不错的镜头运动”
加入风格关键词：如“电影感”、“动漫风格”、“3D动画”、“赛博朋克”
说明节奏：如“慢动作”、“延时摄影”、“快节奏”
图片转视频场景中，描述静态图片需要发生的变化
支持的模型可使用负面提示词排除不需要的元素

Parameter Reference

参数参考

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

请查看references/MODELS.md获取每个模型的完整参数详情。