SieveSync: Realistic, zero-shot lipsync pipeline using MuseTalk and LivePortraitgithub.com·1 pts·mvoodarla·0
SieveSync: High-quality, zero-shot lipsync built with MuseTalk and LivePortraitsievedata.com·4 pts·mvoodarla·0
Finding highlights in long-form video automatically with custom search termssievedata.com·1 pts·mvoodarla·0
Masked Audio Generation Using a Single Non-Autoregressive Transformerpages.cs.huji.ac.il·1 pts·mvoodarla·0
Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioningtwitter.com·3 pts·mvoodarla·0
Show HN: State of the art audio enhance (open source AudioSR and DeepFilterNet)sievedata.com·8 pts·mvoodarla·1
DA-Clip: Controlling Vision-Language Models for Universal Image Restorationtwitter.com·1 pts·mvoodarla·0
Voicebox: The first generative AI model for speech to generalize across tasksai.facebook.com·7 pts·mvoodarla·2
DINOv2: State-of-the-art computer vision models with self-supervised learningdinov2.metademolab.com·176 pts·mvoodarla·16
Show HN: TrackObject – Drag-and-drop computer vision object trackingtrackobject.xyz·23 pts·mvoodarla·3