AI Briefing#stable-audio-open
The latest AI and developer news about #stable-audio-open, with the original source and a short summary.
The latest AI and developer news about #stable-audio-open, with the original source and a short summary.
Foley Control attaches only a small video cross-attention to a frozen T2A model to learn video synchronization.
ARC post-training generates 12 seconds of 44.1kHz stereo audio in 75ms on an H100.
Stable Audio Open, an open-weight text-to-audio model trained on Creative Commons data, has been released.