Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

(WIP) #212

Draft
wants to merge 2 commits into
base: realtime-ai-experimental
Choose a base branch
from

Conversation

emranemran
Copy link
Contributor

No description provided.

@j0sh
Copy link
Contributor

j0sh commented Sep 24, 2024

Multi stage ffmpeg build + test runtime here (currently broken due to missing video codec sdk libs) - 3cb4e3d

branch diff

@j0sh
Copy link
Contributor

j0sh commented Sep 24, 2024

Updated my branch with a fix and some more documentation - apparently the container requires adding video to the NVIDIA_DRIVER_CAPABILITIES env var in order to use the video codec SDK within a nvidia container. In the README, -eNVIDIA_DRIVER_CAPABILITIES=all is set but I am not sure what the implications of that are.

@j0sh
Copy link
Contributor

j0sh commented Sep 25, 2024

New branch that adds preliminary image-to-video output: https://github.com/j0sh/livepeer-ai-worker/compare/ja/realtime-ffmpeg...j0sh:livepeer-ai-worker:ja/realtime-video-out?expand=1

Now we can send images into python and transcode them into videos, in addition to sending video into the container

There is not much of a real interface yet for the python parts

given an input <stream-name> transcoded outputs will be available under <stream-name>/out

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants