Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
First page
Paper summary
High-resolution video synthesis with latent diffusion.
Ask this paper
01
Latent video diffusion: Extends Stable Diffusion-style latent diffusion to video generation with temporal attention layers.
02
512x1024 driving videos: Validates on real driving videos at 512x1024 resolution, achieving state-of-the-art performance.
03
Creative content: Also validated on creative content creation tasks, demonstrating versatility beyond driving scenarios.
04
Video generation foundation: A key paper in the latent-video-diffusion lineage that led to Stable Video Diffusion, SVD, and later open video models.