←back to thread

Ovi: Twin backbone cross-modal fusion for audio-video generation

(github.com)
280 points montyanderson | 1 comments | 22 Oct 25 19:42 UTC | HN request time: 0s | source
Show context
pavlov ◴[22 Oct 25 20:43 UTC] No.45674896[source]▶
Seems like the video model is based on Wan2.2.

Lots of activity around Wan lately. It’s nice to see flexible open models make a strong showing against the massively funded closed competitors like OpenAI and Runway.

replies(2): >>45675188 #>>45675537 #
cubefox ◴[22 Oct 25 21:11 UTC] No.45675188[source]▶
And Google.
replies(2): >>45675465 #>>45675667 #
echelon ◴[22 Oct 25 21:36 UTC] No.45675465[source]▶
OpenAI wowed the world with a video model that was also a script writing, editing, dubbing, foley, and music model.

Kling still has the best proprietary video model, but Sora 2 is so smart that you don't need to edit anything if your target is social.

I don't see how Runway, Pika, or the rest of the purely foundation video model startups survive against the giants and the incredible open source Chinese models. They've got to be sweating bullets right now.

Everyone's also sleeping on xAI's high quality and insanely fast video model (10 second generations) that they're giving away completely for free without watermarks.

replies(2): >>45676805 #>>45676806 #
1. ◴[23 Oct 25 00:20 UTC] No.45676805[source]▶