Alibaba Cloud Model Studio:Image to broadcast video - LivePortrait

LivePortrait generates dynamic portrait videos from portrait images and audio files with a human voice. It includes two models: `LivePortrait-detect` (validates image compliance) and `LivePortrait` (generates videos).

Model overview

Model introduction

• LivePortrait-detect validates whether input images meet LivePortrait requirements.
• LivePortrait generates dynamic portrait videos from portrait images and audio files with a human voice.

Performance showcase

Inputs: Human portrait image + Human voice audio file	Outputs: Dynamic human portrait video
Human portrait: Human voice audio: See the video on the right	Human video:
Human portrait: Human voice audio: See the video on the right	Human video:
Human portrait: Human voice audio: See the video on the right	Human video:

Billing and rate limiting

Model	Unit price	QPS limit for task submission API	Number of concurrent tasks
liveportrait-detect	Model call, pay-as-you-go: $0.000574/image	5	No limit for sync APIs
liveportrait	Model call, pay-as-you-go: $0.002868/second		1 (At any given time, only one job is running. Other jobs in the queue are waiting.)

Prerequisites

You have activated Alibaba Cloud Model Studio and obtained an API key: Get your API key.

Model call

The models support pay-as-you-go calls. To call them:

1. Call LivePortrait-detect to validate that your portrait image meets requirements. For more information, see LivePortrait image detection.
2. Call LivePortrait with the image that passed detection and an audio file (must contain a clear human voice) to generate a dynamic portrait video. For more information, see LivePortrait video generation.