Search papers, labs, and topics across Lattice.
Utrecht University
2
0
4
6
Vidu S2, which comprises Vidu S2-Avatar, a real-time interactive digital-character model, and Vidu S2-Editing, a real-time video editing model, is presented and the feasibility of real-time spatial video generation for both Vidu S2-Avatar and Vidu S2-Editing is explored.
Latent diffusion models can be significantly improved by matching the power spectral density between images and latents, unifying previous observations of over-noisy or over-smoothed latents under a single "Spectrum Matching Hypothesis."