Phantom: Subject-consistent video generation via cross-modal alignment
Paper • 2502.11079 • Published • 58
VicML
hohonu-vicml
AI & ML interests
None yet
Organizations
upvoted a paper over 1 year ago
upvoted 6
papers about 2 years ago
Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion
Paper • 2407.13759 • Published • 18
Diffree: Text-Guided Shape Free Object Inpainting with Diffusion Model
Paper • 2407.16982 • Published • 42
FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention
Paper • 2407.19918 • Published • 51
Improving 2D Feature Representations by 3D-Aware Fine-Tuning
Paper • 2407.20229 • Published • 7
Tora: Trajectory-oriented Diffusion Transformer for Video Generation
Paper • 2407.21705 • Published • 27
Berkeley Humanoid: A Research Platform for Learning-based Control
Paper • 2407.21781 • Published • 8
upvoted 5
papers over 2 years ago
Training-free Camera Control for Video Generation
Paper • 2406.10126 • Published • 13
L4GM: Large 4D Gaussian Reconstruction Model
Paper • 2406.10324 • Published • 13
The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing
Paper • 2406.10601 • Published • 70
HeadStudio: Text to Animatable Head Avatars with 3D Gaussian Splatting
Paper • 2402.06149 • Published • 18
TrailBlazer: Trajectory Control for Diffusion-Based Video Generation
Paper • 2401.00896 • Published • 15
upvoted a paper almost 3 years ago