Recent joint audio-video generative models can synthesize realistic videos with synchronized sound, but typically generate audio as a single mixed track. This limits source-level control and differs from practical audiovisual workflows, where speech, music, sound effects, and ambient sounds are represented as separate...
This work explores the latent space of a pre-trained, frozen encoder for text-to-image personalization, and shows that meaningful directions can be identified within this space and within subspaces defined by selected tokens, enabling localized, fine-grained, and semantically coherent edits.
Daniel Garibi, Ronen Kamenetsky, Hadar Averbuch-Elor et al.· arXiv.org· 0 citations
It is revealed that routing along the audio-video edge is bidirectional: audio can influence video generation, while video can influence audio generation, and biases encoded in the model's parameters and emerges as a major contributor to leakage.
Sagi Polaczek, Noa Kraicer, G. Metzer et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
