SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation Paper • 2607.21553 • Published 10 days ago • 39 • 5
Viewpoint Textual Inversion: Unleashing Novel View Synthesis with Pretrained 2D Diffusion Models Paper • 2309.07986 • Published Sep 14, 2023 • 4 • 1
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image Paper • 2309.03453 • Published Sep 7, 2023 • 13 • 5