p-video-avatar

对比查看原文与翻译

🇺🇸

原文

英文

🇨🇳

翻译

中文

Pruna P-Video-Avatar

Generate talking head avatar videos from a single portrait image via inference.sh CLI.

P-Video-Avatar is the fastest and most cost-effective avatar video model available. Quality on par with Veo 3.0, 18x faster and 6x cheaper than alternatives like Fabric, OmniHuman, and HeyGen.

通过inference.sh CLI，仅用一张肖像图片即可生成说话头像视频。

P-Video-Avatar是目前速度最快、性价比最高的头像视频生成模型。画质与Veo 3.0相当，比Fabric、OmniHuman和HeyGen等竞品快18倍，成本低6倍。

Quick Start

快速开始

Requires inference.sh CLI (
belt
). Install instructions

bash

belt login

需要inference.sh CLI（
belt
）。安装说明

bash

belt login

Generate avatar from portrait + text script

从肖像图片+文本脚本生成头像视频

belt app run pruna/p-video-avatar --input '{ "image": "https://portrait.jpg", "voice_script": "Hello, welcome to our product demo!", "voice": "Zephyr (Female)" }'

undefined

belt app run pruna/p-video-avatar --input '{ "image": "https://portrait.jpg", "voice_script": "Hello, welcome to our product demo!", "voice": "Zephyr (Female)" }'

undefined

Full Workflow: Generate Portrait + Avatar Video

完整工作流：生成肖像图片+头像视频

Use Pruna P-Image to generate the portrait, then P-Video-Avatar to animate it:

bash

undefined

使用Pruna P-Image生成肖像图片，再用P-Video-Avatar使其动起来：

bash

undefined

1. Generate a portrait image with P-Image

1. 使用P-Image生成肖像图片

belt app run pruna/p-image --input '{ "prompt": "professional headshot portrait of a young woman, neutral background, looking at camera, studio lighting, photorealistic", "aspect_ratio": "9:16" }'

2. Use the generated image URL to create the avatar video

2. 使用第一步生成的图片URL创建头像视频

belt app run pruna/p-video-avatar --input '{ "image": "<image-url-from-step-1>", "voice_script": "Hi there! Let me walk you through our latest features.", "voice": "Zephyr (Female)", "resolution": "720p" }'

undefined

undefined

Examples

示例

Text Script with Voice Selection

选择音色的文本脚本

bash

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Welcome to our product walkthrough. Today I will show you three key features.",
  "voice": "Puck (Male)",
  "voice_language": "English (US)",
  "resolution": "720p"
}'

bash

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Welcome to our product walkthrough. Today I will show you three key features.",
  "voice": "Puck (Male)",
  "voice_language": "English (US)",
  "resolution": "720p"
}'

Audio-Driven Avatar

音频驱动头像

Provide your own audio file instead of using built-in TTS:

bash

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "audio": "https://speech.mp3"
}'

When both

audio

and

voice_script

are provided, audio takes priority.

提供自定义音频文件，替代内置TTS：

bash

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "audio": "https://speech.mp3"
}'

当同时提供

audio

和

voice_script

时，音频文件优先级更高。

1080p with Custom Style

1080p分辨率+自定义风格

bash

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "This is exciting news for our community!",
  "voice": "Aoede (Female)",
  "voice_prompt": "Enthusiastic and energetic tone, slightly faster pace",
  "video_prompt": "The person is presenting on stage with dramatic lighting",
  "resolution": "1080p"
}'

bash

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "This is exciting news for our community!",
  "voice": "Aoede (Female)",
  "voice_prompt": "Enthusiastic and energetic tone, slightly faster pace",
  "video_prompt": "The person is presenting on stage with dramatic lighting",
  "resolution": "1080p"
}'

Multilingual Content

多语言内容

bash

undefined

bash

undefined

Spanish

西班牙语

belt app run pruna/p-video-avatar --input '{ "image": "https://portrait.jpg", "voice_script": "Bienvenidos a nuestra demostración de producto.", "voice": "Kore (Female)", "voice_language": "Spanish" }'

Japanese

日语

belt app run pruna/p-video-avatar --input '{ "image": "https://portrait.jpg", "voice_script": "こんにちは、製品デモへようこそ。", "voice": "Leda (Female)", "voice_language": "Japanese" }'

undefined

undefined

Reproducible Generation

可复现生成

bash

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Consistent results every time.",
  "seed": 42
}'

bash

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "Consistent results every time.",
  "seed": 42
}'

Available Voices

可用音色

Female: Zephyr, Kore, Leda, Aoede, Callirrhoe, Autonoe, Despina, Erinome, Laomedeia, Achernar, Gacrux, Pulcherrima, Vindemiatrix, Sulafat

Male: Puck, Charon, Fenrir, Orus, Enceladus, Iapetus, Umbriel, Algenib, Algieba, Schedar, Achird, Zubenelgenubi, Sadachbia, Sadaltager, Alnilam, Rasalgethi

女性音色： Zephyr, Kore, Leda, Aoede, Callirrhoe, Autonoe, Despina, Erinome, Laomedeia, Achernar, Gacrux, Pulcherrima, Vindemiatrix, Sulafat

男性音色： Puck, Charon, Fenrir, Orus, Enceladus, Iapetus, Umbriel, Algenib, Algieba, Schedar, Achird, Zubenelgenubi, Sadachbia, Sadaltager, Alnilam, Rasalgethi

Supported Languages

支持语言

English (US), English (UK), Spanish, French, German, Italian, Portuguese (Brazil), Japanese, Korean, Hindi

英语（美国）、英语（英国）、西班牙语、法语、德语、意大利语、葡萄牙语（巴西）、日语、韩语、印地语

Parameters

参数说明

Parameter	Type	Default	Description
`image`	file	required	Portrait image (jpg, jpeg, png, webp)
`voice_script`	string	-	Text for the person to say
`audio`	file	-	Audio file (overrides voice_script)
`voice`	string	"Zephyr (Female)"	Voice selection
`voice_language`	string	"English (US)"	Output language
`resolution`	string	"720p"	720p or 1080p
`video_prompt`	string	"The person is talking."	Control avatar behavior and background
`voice_prompt`	string	"Say the following."	Control tone, pacing, emotion
`seed`	int	random	Reproducible generation
`disable_safety_filter`	bool	true	Disable content filter
`disable_prompt_upsampling`	bool	false	Skip prompt enhancement

参数	类型	默认值	描述
`image`	文件	必填	肖像图片（jpg、jpeg、png、webp格式）
`voice_script`	字符串	-	头像需要说的文本内容
`audio`	文件	-	音频文件（优先级高于voice_script）
`voice`	字符串	"Zephyr (Female)"	音色选择
`voice_language`	字符串	"English (US)"	输出语言
`resolution`	字符串	"720p"	分辨率可选720p或1080p
`video_prompt`	字符串	"The person is talking."	控制头像动作与背景
`voice_prompt`	字符串	"Say the following."	控制语气、语速、情绪
`seed`	整数	随机值	用于生成可复现的结果
`disable_safety_filter`	布尔值	true	禁用内容过滤
`disable_prompt_upsampling`	布尔值	false	跳过提示词优化

Pricing

定价

Resolution	Price
720p	$0.025 per second of output video
1080p	$0.045 per second of output video

Example: 30-second 720p video = $0.75

分辨率	价格
720p	每秒钟输出视频0.025美元
1080p	每秒钟输出视频0.045美元

示例：30秒720p视频 = 0.75美元

Free Launch Weekend

免费启动周末

P-Video-Avatar is completely free from Thursday May 1, 2026 4:00 PM CET through Sunday May 4, 2026 11:59 PM CET. All costs are on us during this window — no billing, no limits on resolution.

P-Video-Avatar在2026年5月1日星期四欧洲中部时间16:00至2026年5月4日星期日欧洲中部时间23:59期间完全免费。 在此期间所有费用由我们承担——无需计费，分辨率无限制。

Competitive Advantage

竞争优势

Feature	P-Video-Avatar	Fabric 1.0	OmniHuman 1.5	HeyGen Avatar 4
Speed (per sec of video)	~1.83s/s	~34s/s (18x slower)	~28s/s (15x slower)	~26s/s (14x slower)
Cost per second	$0.025	$0.14 (5.6x more)	$0.16 (6.4x more)	$0.075 (3x more)
Built-in TTS	Yes	Yes	No	Yes
Dynamic Background	Yes	Yes	No	Yes
1080p Support	Yes	No	No	Yes

特性	P-Video-Avatar	Fabric 1.0	OmniHuman 1.5	HeyGen Avatar 4
速度（每生成1秒视频所需时间）	~1.83秒/秒	~34秒/秒（慢18倍）	~28秒/秒（慢15倍）	~26秒/秒（慢14倍）
每秒成本	0.025美元	0.14美元（贵5.6倍）	0.16美元（贵6.4倍）	0.075美元（贵3倍）
内置TTS	是	是	否	是
动态背景	是	是	否	是
支持1080p	是	否	否	是

Use Cases

适用场景

Marketing: Product demos, UGC-style ads with AI presenters
Education: Course videos, explainers, tutoring content
Localization: Dub content across 10 languages from one image
Social Media: Consistent virtual influencer content
Corporate: Training, onboarding, announcements
Gaming: Character avatars, NPC dialogue videos
Customer Support: Personalized video responses

营销领域：产品演示、AI主持人风格的UGC广告
教育领域：课程视频、讲解内容、辅导素材
本地化：通过一张图片将内容配音成10种语言
社交媒体：持续产出虚拟网红内容
企业场景：培训、入职引导、公告
游戏领域：角色头像、NPC对话视频
客户支持：个性化视频回复

Tips

使用技巧

Use high-quality portrait photos (front-facing, good lighting)
The output video aspect ratio matches the input image
Use
```
video_prompt
```
to control dynamic backgrounds and body language
Use
```
voice_prompt
```
to control speaking style, emotion, and pacing
Keep videos under 3 minutes for best visual consistency
Generate portraits with
```
pruna/p-image
```
using aspect ratio
```
9:16
```
for vertical avatar videos

使用高质量肖像照片（正面朝向、光线良好）
输出视频的宽高比与输入图片一致
使用
```
video_prompt
```
控制动态背景和肢体语言
使用
```
voice_prompt
```
控制说话风格、情绪和语速
视频时长控制在3分钟以内以获得最佳视觉一致性
使用
```
pruna/p-image
```
生成宽高比为9:16的肖像图片，用于竖版头像视频

Related Pruna Models

Generate portrait images

生成肖像图片

belt app run pruna/p-image --input '{"prompt": "professional headshot portrait"}'

General video generation

通用视频生成

belt app run pruna/p-video --input '{"prompt": "cinematic scene"}'

Image editing

图片编辑

belt app run pruna/p-image-edit --input '{"prompt": "change background", "image": "https://photo.jpg"}'

undefined

belt app run pruna/p-image-edit --input '{"prompt": "change background", "image": "https://photo.jpg"}'

undefined

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

Pruna video generation

Pruna视频生成

npx skills add inference-sh/skills@p-video

Pruna image generation

Pruna图片生成

npx skills add inference-sh/skills@p-image

All video generation models

所有视频生成模型

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

Image generation (for creating portraits)

图片生成（用于创建肖像）

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


Browse all Pruna apps: `belt app list --namespace pruna`

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


浏览所有Pruna应用：`belt app list --namespace pruna`

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

p-video-avatar

原文

翻译

Pruna P-Video-Avatar

Pruna P-Video-Avatar

Quick Start

快速开始

Generate avatar from portrait + text script

从肖像图片+文本脚本生成头像视频

Full Workflow: Generate Portrait + Avatar Video

完整工作流：生成肖像图片+头像视频

1. Generate a portrait image with P-Image

1. 使用P-Image生成肖像图片

2. Use the generated image URL to create the avatar video

2. 使用第一步生成的图片URL创建头像视频

Examples

示例

Text Script with Voice Selection

选择音色的文本脚本

Audio-Driven Avatar

音频驱动头像

1080p with Custom Style

1080p分辨率+自定义风格

Multilingual Content

多语言内容

Spanish

西班牙语

Japanese

日语

Reproducible Generation

可复现生成

Available Voices

可用音色

Supported Languages

支持语言

Parameters

参数说明

Pricing

定价

Free Launch Weekend

免费启动周末

Competitive Advantage

竞争优势

Use Cases

适用场景

Tips

使用技巧

Related Pruna Models

相关Pruna模型

Generate portrait images

生成肖像图片

General video generation

通用视频生成

Image editing

图片编辑

Related Skills

相关技能

Full platform skill (all 250+ apps)

全平台技能（包含250+应用）

Pruna video generation

Pruna视频生成

Pruna image generation

Pruna图片生成

All video generation models

所有视频生成模型

Image generation (for creating portraits)

图片生成（用于创建肖像）

Documentation

文档