happyhorse

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

HappyHorse 1.0 Video Generation

HappyHorse 1.0 视频生成

Generate and edit physically realistic videos with Alibaba's HappyHorse 1.0 models via inference.sh CLI.

通过inference.sh CLI使用阿里巴巴的HappyHorse 1.0模型生成和编辑具有真实物理效果的视频。

Quick Start

快速开始

Requires inference.sh CLI (
belt
). Install instructions

bash

belt login

belt app run alibaba/happyhorse-1-0-t2v --input '{"prompt": "a horse galloping across a sunlit meadow"}'

需要inference.sh CLI（
belt
工具）。安装说明

bash

belt login

belt app run alibaba/happyhorse-1-0-t2v --input '{"prompt": "a horse galloping across a sunlit meadow"}'

HappyHorse Models

HappyHorse 模型

Model	App ID	Best For
T2V	`alibaba/happyhorse-1-0-t2v`	Text-to-video, physically realistic motion
I2V	`alibaba/happyhorse-1-0-i2v`	Animate a single image
R2V	`alibaba/happyhorse-1-0-r2v`	Preserve characters from up to 9 reference images
Video Edit	`alibaba/happyhorse-1-0-video-edit`	Edit existing videos with natural language

All models support 720P/1080P resolution, up to 15 seconds duration.

模型	App ID	最佳适用场景
T2V	`alibaba/happyhorse-1-0-t2v`	文本转视频、真实物理运动效果
I2V	`alibaba/happyhorse-1-0-i2v`	单张图片动效生成
R2V	`alibaba/happyhorse-1-0-r2v`	保留最多9张参考图中的角色特征
Video Edit	`alibaba/happyhorse-1-0-video-edit`	用自然语言编辑现有视频

所有模型均支持720P/1080P分辨率，最长时长15秒。

Examples

示例

Text-to-Video

文本转视频

bash

belt app run alibaba/happyhorse-1-0-t2v --input '{
  "prompt": "a golden retriever running through autumn leaves in a park, slow motion",
  "duration": 10,
  "resolution": "1080P",
  "ratio": "16:9"
}'

bash

belt app run alibaba/happyhorse-1-0-t2v --input '{
  "prompt": "a golden retriever running through autumn leaves in a park, slow motion",
  "duration": 10,
  "resolution": "1080P",
  "ratio": "16:9"
}'

Image-to-Video

图片转视频

Animate a still image:

bash

belt app run alibaba/happyhorse-1-0-i2v --input '{
  "first_frame": "https://your-image.jpg",
  "prompt": "gentle camera zoom, clouds moving in the sky",
  "duration": 8,
  "resolution": "720P"
}'

将静态图片生成动态视频：

bash

belt app run alibaba/happyhorse-1-0-i2v --input '{
  "first_frame": "https://your-image.jpg",
  "prompt": "gentle camera zoom, clouds moving in the sky",
  "duration": 8,
  "resolution": "720P"
}'

Reference-to-Video (Character Preservation)

参考图转视频（角色保留）

Generate videos that preserve characters from reference images (up to 9):

bash

belt app run alibaba/happyhorse-1-0-r2v --input '{
  "prompt": "a woman walking through a busy market street",
  "reference_images": ["https://portrait.jpg"],
  "duration": 10,
  "resolution": "720P"
}'

生成保留参考图中角色特征的视频（最多支持9张参考图）：

bash

belt app run alibaba/happyhorse-1-0-r2v --input '{
  "prompt": "a woman walking through a busy market street",
  "reference_images": ["https://portrait.jpg"],
  "duration": 10,
  "resolution": "720P"
}'

Multi-Character Reference

多角色参考

bash

belt app run alibaba/happyhorse-1-0-r2v --input '{
  "prompt": "two friends sitting at a cafe having coffee",
  "reference_images": ["https://person1.jpg", "https://person2.jpg"],
  "ratio": "16:9"
}'

bash

belt app run alibaba/happyhorse-1-0-r2v --input '{
  "prompt": "two friends sitting at a cafe having coffee",
  "reference_images": ["https://person1.jpg", "https://person2.jpg"],
  "ratio": "16:9"
}'

Video Editing

视频编辑

Edit existing videos using natural language instructions:

bash

belt app run alibaba/happyhorse-1-0-video-edit --input '{
  "video": "https://your-video.mp4",
  "prompt": "change the background to a snowy mountain landscape"
}'

使用自然语言指令编辑现有视频：

bash

belt app run alibaba/happyhorse-1-0-video-edit --input '{
  "video": "https://your-video.mp4",
  "prompt": "change the background to a snowy mountain landscape"
}'

Video Editing with Reference Images

结合参考图的视频编辑

bash

belt app run alibaba/happyhorse-1-0-video-edit --input '{
  "video": "https://your-video.mp4",
  "prompt": "replace the person with the character from the reference image",
  "reference_images": ["https://character.jpg"]
}'

bash

belt app run alibaba/happyhorse-1-0-video-edit --input '{
  "video": "https://your-video.mp4",
  "prompt": "replace the person with the character from the reference image",
  "reference_images": ["https://character.jpg"]
}'

Video Editing with Audio Control

带音频控制的视频编辑

bash

belt app run alibaba/happyhorse-1-0-video-edit --input '{
  "video": "https://your-video.mp4",
  "prompt": "make the scene look like a rainy day",
  "audio_setting": "generate"
}'

bash

belt app run alibaba/happyhorse-1-0-video-edit --input '{
  "video": "https://your-video.mp4",
  "prompt": "make the scene look like a rainy day",
  "audio_setting": "generate"
}'

Pricing

定价

Resolution	Price
720P	$0.14 per second
1080P	$0.24 per second

Video Edit is billed on input + output duration.

分辨率	价格
720P	每秒0.14美元
1080P	每秒0.24美元

视频编辑按输入+输出时长计费。

Parameters (T2V)

参数（T2V）

Parameter	Type	Default	Description
`prompt`	string	required	Text description of the video
`duration`	integer	5	Duration in seconds (3–15)
`resolution`	enum	720P	720P or 1080P
`ratio`	enum	16:9	16:9, 9:16, 1:1, 4:3, 3:4, 21:9
`seed`	integer	random	Reproducible generation
`watermark`	boolean	false	Add HappyHorse watermark

参数	类型	默认值	说明
`prompt`	string	必填	视频的文字描述
`duration`	integer	5	视频时长（3–15秒）
`resolution`	enum	720P	720P或1080P
`ratio`	enum	16:9	16:9、9:16、1:1、4:3、3:4、21:9
`seed`	integer	随机值	用于生成可复现的视频
`watermark`	boolean	false	添加HappyHorse水印

Parameters (I2V)

参数（I2V）

Parameter	Type	Default	Description
`first_frame`	file	required	First frame image (JPEG, PNG, WebP)
`prompt`	string	-	Optional text description
`duration`	integer	5	Duration in seconds (3–15)
`resolution`	enum	720P	720P or 1080P
`seed`	integer	random	Reproducible generation

参数	类型	默认值	说明
`first_frame`	file	必填	首帧图片（支持JPEG、PNG、WebP格式）
`prompt`	string	-	可选的文字描述
`duration`	integer	5	视频时长（3–15秒）
`resolution`	enum	720P	720P或1080P
`seed`	integer	随机值	用于生成可复现的视频

Parameters (R2V)

参数（R2V）

Parameter	Type	Default	Description
`prompt`	string	required	Text description of the scene
`reference_images`	array	required	Up to 9 character reference images
`duration`	integer	5	Duration in seconds (3–15)
`resolution`	enum	720P	720P or 1080P
`ratio`	enum	16:9	16:9, 9:16, 1:1, 4:3, 3:4, 21:9
`seed`	integer	random	Reproducible generation

参数	类型	默认值	说明
`prompt`	string	必填	场景的文字描述
`reference_images`	array	必填	最多9张角色参考图
`duration`	integer	5	视频时长（3–15秒）
`resolution`	enum	720P	720P或1080P
`ratio`	enum	16:9	16:9、9:16、1:1、4:3、3:4、21:9
`seed`	integer	随机值	用于生成可复现的视频

Parameters (Video Edit)

参数（Video Edit）

Parameter	Type	Default	Description
`video`	file	required	Video to edit (MP4/MOV, H.264)
`prompt`	string	required	Editing instruction
`reference_images`	array	-	Up to 5 reference images
`audio_setting`	enum	auto	auto, generate, or keep_original
`resolution`	enum	720P	720P or 1080P
`seed`	integer	random	Reproducible generation

参数	类型	默认值	说明
`video`	file	必填	待编辑的视频（支持MP4/MOV格式，H.264编码）
`prompt`	string	必填	编辑指令
`reference_images`	array	-	最多5张参考图
`audio_setting`	enum	auto	auto、generate或keep_original
`resolution`	enum	720P	720P或1080P
`seed`	integer	随机值	用于生成可复现的编辑效果

Search HappyHorse Apps

搜索HappyHorse应用

bash

belt app list --search "happyhorse"

bash

belt app list --search "happyhorse"

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

Seedance 2.0

npx skills add inference-sh/skills@seedance

Google Veo

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

Image generation (for image-to-video)

图片生成（用于图片转视频）

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


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

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


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
流式返回结果 - 实时进度更新
内容流水线示例 - 构建媒体工作流

happyhorse

Original

Translation

HappyHorse 1.0 Video Generation

HappyHorse 1.0 视频生成

Quick Start

快速开始

HappyHorse Models

HappyHorse 模型

Examples

示例

Text-to-Video

文本转视频

Image-to-Video

图片转视频

Reference-to-Video (Character Preservation)

参考图转视频（角色保留）

Multi-Character Reference

多角色参考

Video Editing

视频编辑

Video Editing with Reference Images

结合参考图的视频编辑

Video Editing with Audio Control

带音频控制的视频编辑

Pricing

定价

Parameters (T2V)

参数（T2V）

Parameters (I2V)

参数（I2V）

Parameters (R2V)

参数（R2V）

Parameters (Video Edit)

参数（Video Edit）

Search HappyHorse Apps

搜索HappyHorse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

Seedance 2.0

Seedance 2.0

Google Veo

Google Veo

Image generation (for image-to-video)

图片生成（用于图片转视频）

Documentation

文档