The paper introduces Matryoshka Diffusion (MDM), an end-to-end framework for high-resolution image and video synthesis. MDM uses a diffusion process and a NestedUNet architecture to denoise inputs at multiple resolutions and enables progressive training for high-resolution generation. The approach is effective on various benchmarks and can train a single pixel-space model at high resolutions.

https://arxiv.org/abs//2310.15111

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers