Tuning-Free Noise Rectification for High Fidelity Image-to-Video Generation

[PDF] arxiv.org

Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach

Y Liu, Y Ren, X Cun, A Artola, Y Liu, T Zeng… - arXiv preprint arXiv …, 2024 - arxiv.org
Diffusion models have revolutionized image generation, and their extension to video
generation has shown promise. However, current video diffusion models~(VDMs) rely on a …
相关文章 所有 2 个版本