UniRouteUniRoute

omnihuman-1-5 / subject-detection

Commercial use

OmniHuman 1.5 是 ByteDance 的 AI 虚拟人与数字人模型,可将单张图片和音频转化为逼真的口播视频,实现自然的唇形同步、丰富的面部表情与栩栩如生的动作。

Model Type:
Pricing: 价格待定
查看完整价格

omnihuman-1-5/human-identification USD / 张

规格 / 通道官方云厂商

omnihuman-1-5/subject-detection USD / 张

规格 / 通道官方云厂商

omnihuman-1-5 USD / 秒

规格 / 通道官方云厂商
Standard$0.27$0.189

Input

image_url

File uploads require configured image storage. A public HTTPS image URL can be used directly.

Portrait image URL link (supports detection of up to 5 subjects)

Output

output typetextExample output

No public output example available

Examples

Explore different use cases and parameter configurations

README

Complete guide to using omnihuman-1-5/subject-detection