High-quality zero-shot lipsync pipeline built on LivePortrait

[mvoodarla]

Hey folks! My team has been exploring zero-shot lipsyncing for a bit and we think we've improved on MuseTalk's quality quite a bit by using LivePortrait to neutralize expression and CodeFormer to enhance. Here's an example.

short.mp4

We wrote a technical blog on it: https://www.sievedata.com/blog/sievesync-zero-shot-lipsync-api-developers

Hope to put out an OSS repo soon too :)

Anything we don't talk about in the blog that we should in our repo release?

[shadowcz007]

嘿，伙计们！我的团队一直在探索零镜头唇语同步，我们认为我们通过使用LivePortrait来中和表达和和CodeFormer来增强，我们大大提高了MuseTalk的质量。这里有一个例子。

短.mp4

我们在上面写了一个技术博客：https://www.sievedata.com/blog/sievesync-zero-shot-lipsync-api-developers

也希望尽快推出OSS回购:)

我们在博客中没有谈论什么，我们应该在回购发布中谈论什么？

I'll try your project when I have time.

[mvoodarla]

we just put out a repo here too! https://github.com/sieve-community/sievesync