HackerTrans
TopNewTrendsCommentsPastAskShowJobs

cleardusk

no profile record

Submissions

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

github.com
64 points·by cleardusk·2 bulan yang lalu·15 comments

[untitled]

1 points·by cleardusk·2 bulan yang lalu·0 comments

[untitled]

1 points·by cleardusk·2 tahun yang lalu·0 comments

LivePortrait: A fast, controllable portrait animation model

github.com
203 points·by cleardusk·2 tahun yang lalu·25 comments

comments

cleardusk
·2 bulan yang lalu·discuss
vllm-omni support is on the way : )
cleardusk
·2 bulan yang lalu·discuss
:D
cleardusk
·2 tahun yang lalu·discuss
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? :-(
cleardusk
·2 tahun yang lalu·discuss
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.
cleardusk
·2 tahun yang lalu·discuss
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.
cleardusk
·2 tahun yang lalu·discuss
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.
cleardusk
·2 tahun yang lalu·discuss
Fixed! h_h