24 January 2024
Google shows off Lumiere, a space-time diffusion model for realistic AI videos - 2024-01-24 20:57:05Z
Title:Google shows off Lumiere, a space-time diffusion model for realistic AI videos Summary: Lumiere was trained on a dataset of 30 million videos, along with their text captions, and is capable of generating 80 frames at 16 fps. The source of this data, however, remains unclear at this stage. Link: Google shows off Lumiere, a space-time diffusion model for realistic AI videos
