cleardusk

Joined 8 years ago

Karma

235

Submissions

29

Member since

Oct 17

https://guojianzhu.com

View on Hacker News

Recent submissions

Comment · 5 months ago

vllm-omni support is on the way : )

Comment · 5 months ago

Show HN: Lance – image/video generation and understanding in one model github.com

64 cleardusk 5 months ago 15 comments

Comment · 2 years ago

I scanned the open codec page: https://en.wikipedia.org/wiki/List_of_open-source_codecs I'm a little confused, is H.265 not OPEN? :-(

Comment · 2 years ago

Thanks for the reminder. The homepage is a GitHub page and does not support git lfs, so I have compressed the files as much as possible to reduce their size. We consider re-encode the mp4 files to x264, and provide a packed zip of the homepage.

Comment · 2 years ago

Understood. The core dependency of InsightFace in LivePortrait is the face detection algo. The face detection is easily to be replaced with self-developed or MIT-licensed model.

Comment · 2 years ago

https://github.com/deepinsight/insightface?tab=readme-ov-fil... ---------- The code of InsightFace is released under the MIT License. There is no limitation for both academic and commercial usage.

Comment · 2 years ago

LivePortrait: A fast, controllable portrait animation model github.com

203 cleardusk 2 years ago 25 comments

Comment · 6 years ago

Comment · 6 years ago

Not a random face. But it may not look very similar.