
Sign up to save your podcasts
Or


This paper redesigns Latent Diffusion Models for improved consistency by enhancing shift-equivariance, resulting in an alias-free LDM that performs better in video editing and image translation tasks.
https://arxiv.org/abs//2503.09419
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
By Igor Melnyk5
33 ratings
This paper redesigns Latent Diffusion Models for improved consistency by enhancing shift-equivariance, resulting in an alias-free LDM that performs better in video editing and image translation tasks.
https://arxiv.org/abs//2503.09419
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

965 Listeners

1,936 Listeners

435 Listeners

112,408 Listeners

9,927 Listeners

5,512 Listeners

219 Listeners

49 Listeners

94 Listeners

467 Listeners