seedance

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Seedance 2.0 Video Generation

Seedance 2.0 视频生成

Generate videos with synchronized audio using ByteDance's Seedance 2.0 models via inference.sh CLI.

通过inference.sh CLI使用ByteDance的Seedance 2.0模型生成带同步音频的视频。

Quick Start

快速开始

Requires inference.sh CLI (
belt
). Install instructions

bash

belt login

belt app run falai/seedance-2-t2v --input '{
  "prompt": "a jazz band performing in a dimly lit club",
  "generate_audio": true
}'

需要inference.sh CLI（
belt
）。安装说明

bash

belt login

belt app run falai/seedance-2-t2v --input '{
  "prompt": "a jazz band performing in a dimly lit club",
  "generate_audio": true
}'

Seedance 2.0 Models

Seedance 2.0 模型

Model	App ID	Best For
Seedance 2 T2V	`falai/seedance-2-t2v`	Text-to-video with audio
Seedance 2 I2V	`falai/seedance-2-i2v`	Animate images with audio
Seedance 2 R2V	`falai/seedance-2-r2v`	Reference images/videos/audio to video

All models support quality and fast modes, 480p/720p resolution, and synchronized audio generation.

模型	App ID	最佳适用场景
Seedance 2 T2V	`falai/seedance-2-t2v`	带音频的文本转视频
Seedance 2 I2V	`falai/seedance-2-i2v`	带音频的图像动画化
Seedance 2 R2V	`falai/seedance-2-r2v`	基于参考图像/视频/音频生成视频

所有模型均支持质量和快速模式、480p/720p分辨率，以及同步音频生成。

Examples

示例

Text-to-Video with Audio

带音频的文本转视频

bash

belt app run falai/seedance-2-t2v --input '{
  "prompt": "ocean waves crashing on rocks during a storm, dramatic cinematic shot",
  "generate_audio": true,
  "duration": 10,
  "aspect_ratio": "16:9"
}'

bash

belt app run falai/seedance-2-t2v --input '{
  "prompt": "ocean waves crashing on rocks during a storm, dramatic cinematic shot",
  "generate_audio": true,
  "duration": 10,
  "aspect_ratio": "16:9"
}'

Fast Mode (Cheaper)

快速模式（成本更低）

bash

belt app run falai/seedance-2-t2v --input '{
  "prompt": "a butterfly landing on a flower in slow motion",
  "mode": "fast",
  "generate_audio": true
}'

bash

belt app run falai/seedance-2-t2v --input '{
  "prompt": "a butterfly landing on a flower in slow motion",
  "mode": "fast",
  "generate_audio": true
}'

Image-to-Video

图像转视频

Animate a still image into a video:

bash

belt app run falai/seedance-2-i2v --input '{
  "image": "https://your-image.jpg",
  "prompt": "gentle camera movement, leaves rustling in the wind",
  "generate_audio": true
}'

将静态图像动画化为视频：

bash

belt app run falai/seedance-2-i2v --input '{
  "image": "https://your-image.jpg",
  "prompt": "gentle camera movement, leaves rustling in the wind",
  "generate_audio": true
}'

Image-to-Video with Start and End Frames

带起始和结束帧的图像转视频

bash

belt app run falai/seedance-2-i2v --input '{
  "image": "https://start-frame.jpg",
  "end_image": "https://end-frame.jpg",
  "prompt": "smooth transition between scenes",
  "generate_audio": true
}'

bash

belt app run falai/seedance-2-i2v --input '{
  "image": "https://start-frame.jpg",
  "end_image": "https://end-frame.jpg",
  "prompt": "smooth transition between scenes",
  "generate_audio": true
}'

Reference-to-Video

参考素材转视频

Use reference images, videos, or audio in your prompt with

@Image1

@Video1

@Audio1

placeholders:

bash

belt app run falai/seedance-2-r2v --input '{
  "prompt": "A person who looks like @Image1 is walking through a garden",
  "images": ["https://portrait.jpg"],
  "generate_audio": true
}'

在提示词中使用

@Image1

、

@Video1

、

@Audio1

占位符引用图像、视频或音频素材：

bash

belt app run falai/seedance-2-r2v --input '{
  "prompt": "A person who looks like @Image1 is walking through a garden",
  "images": ["https://portrait.jpg"],
  "generate_audio": true
}'

Multi-Reference

多参考素材

bash

belt app run falai/seedance-2-r2v --input '{
  "prompt": "@Image1 and @Image2 are having a conversation at a cafe",
  "images": ["https://person1.jpg", "https://person2.jpg"],
  "generate_audio": true
}'

bash

belt app run falai/seedance-2-r2v --input '{
  "prompt": "@Image1 and @Image2 are having a conversation at a cafe",
  "images": ["https://person1.jpg", "https://person2.jpg"],
  "generate_audio": true
}'

Reference with Audio

带音频参考的视频生成

bash

belt app run falai/seedance-2-r2v --input '{
  "prompt": "A musician who looks like @Image1 is performing @Audio1",
  "images": ["https://musician.jpg"],
  "audios": ["https://music.mp3"],
  "generate_audio": true
}'

bash

belt app run falai/seedance-2-r2v --input '{
  "prompt": "A musician who looks like @Image1 is performing @Audio1",
  "images": ["https://musician.jpg"],
  "audios": ["https://music.mp3"],
  "generate_audio": true
}'

Pricing

定价

Mode	720p	480p
Quality	~$0.30/sec	~$0.13/sec
Fast	~$0.24/sec	~$0.11/sec

模式	720p	480p
质量模式	~$0.30/秒	~$0.13/秒
快速模式	~$0.24/秒	~$0.11/秒

Parameters (T2V)

参数（T2V）

Parameter	Type	Default	Description
`prompt`	string	required	Text description of the video
`generate_audio`	boolean	false	Generate synchronized audio
`duration`	enum	-	Duration in seconds (4–10)
`aspect_ratio`	enum	-	16:9, 9:16, 1:1, 4:3, 3:4
`resolution`	enum	-	480p or 720p
`mode`	enum	quality	quality or fast
`seed`	integer	random	Reproducible generation

参数	类型	默认值	说明
`prompt`	string	必填	视频的文本描述
`generate_audio`	boolean	false	生成同步音频
`duration`	enum	-	视频时长（4–10秒）
`aspect_ratio`	enum	-	宽高比：16:9、9:16、1:1、4:3、3:4
`resolution`	enum	-	分辨率：480p或720p
`mode`	enum	quality	模式：quality（质量模式）或fast（快速模式）
`seed`	integer	随机值	可复现生成结果

Parameters (I2V)

参数（I2V）

Same as T2V plus:

Parameter	Type	Description
`image`	file	Starting frame image (required)
`end_image`	file	Optional ending frame

与T2V参数相同，新增以下参数：

参数	类型	说明
`image`	file	起始帧图像（必填）
`end_image`	file	可选的结束帧

Parameters (R2V)

参数（R2V）

Same as T2V plus:

Parameter	Type	Description
`images`	array	Reference images (@Image1, @Image2, ...)
`videos`	array	Reference videos (@Video1, @Video2, ...)
`audios`	array	Reference audio (@Audio1, @Audio2, ...)

与T2V参数相同，新增以下参数：

参数	类型	说明
`images`	array	参考图像（@Image1、@Image2等）
`videos`	array	参考视频（@Video1、@Video2等）
`audios`	array	参考音频（@Audio1、@Audio2等）

Search Seedance Apps

搜索Seedance应用

bash

belt app list --search "seedance"

bash

belt app list --search "seedance"

Related Skills

Full platform skill (all 250+ apps)

全平台技能（包含250+应用）

npx skills add inference-sh/skills@infsh-cli

All video generation models

所有视频生成模型

npx skills add inference-sh/skills@ai-video-generation

Google Veo

npx skills add inference-sh/skills@google-veo

Image generation (for image-to-video)

图像生成（用于图像转视频）

npx skills add inference-sh/skills@ai-image-generation

AI avatars & lipsync

AI虚拟形象与唇形同步

npx skills add inference-sh/skills@ai-avatar-video


Browse all video apps: `belt app list --category video`

npx skills add inference-sh/skills@ai-avatar-video


浏览所有视频应用：`belt app list --category video`

Documentation

文档

Running Apps - How to run apps via CLI
Streaming Results - Real-time progress updates
Content Pipeline Example - Building media workflows

运行应用 - 如何通过CLI运行应用
流式结果 - 实时进度更新
内容流水线示例 - 构建媒体工作流

seedance

Original

Translation

Seedance 2.0 Video Generation

Seedance 2.0 视频生成

Quick Start

快速开始

Seedance 2.0 Models

Seedance 2.0 模型

Examples

示例

Text-to-Video with Audio

带音频的文本转视频

Fast Mode (Cheaper)

快速模式（成本更低）

Image-to-Video

图像转视频

Image-to-Video with Start and End Frames

带起始和结束帧的图像转视频

Reference-to-Video

参考素材转视频

Multi-Reference

多参考素材

Reference with Audio

带音频参考的视频生成

Pricing

定价

Parameters (T2V)

参数（T2V）

Parameters (I2V)

参数（I2V）

Parameters (R2V)

参数（R2V）

Search Seedance Apps

搜索Seedance应用

Related Skills

相关技能

Full platform skill (all 250+ apps)

全平台技能（包含250+应用）

All video generation models

所有视频生成模型

Google Veo

Google Veo

Image generation (for image-to-video)

图像生成（用于图像转视频）

AI avatars & lipsync

AI虚拟形象与唇形同步

Documentation

文档