Eliminating Oversaturation and Artifacts of High Guidance Scales in Diffusion Models Paper • 2410.02416 • Published Oct 3, 2024 • 26
Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion Paper • 2408.00458 • Published Aug 1, 2024 • 11
No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models Paper • 2407.02687 • Published Jul 2, 2024 • 22
LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models Paper • 2405.14477 • Published May 23, 2024 • 17