Kandinsky 6.0 Video: Foundation Models for Synchronized Video and Audio Generation Paper • 2610.05608 • Published 12 days ago • 174
KVAE: Family of Tokenizers for Multimodal Generative Models Paper • 2608.05798 • Published Aug 6 • 32
KVAE-Audio Collection KVAE-Audio is a continuous full-band audio waveform autoencoder • 2 items • Updated 10 days ago • 7
KVAE 2.0 Collection KVAE 2.0 is a family of image and video tokenizers with a time compression ratio of 4 and spacial compression ratio of 8 and 16 • 3 items • Updated 10 days ago • 5