-
Stabilizing RLHF through Advantage Model and Selective Rehearsal
Paper • 2309.10202 • Published • 9 -
MagiCapture: High-Resolution Multi-Concept Portrait Customization
Paper • 2309.06895 • Published • 27 -
Training-free Camera Control for Video Generation
Paper • 2406.10126 • Published • 12 -
An Image is Worth 32 Tokens for Reconstruction and Generation
Paper • 2406.07550 • Published • 55
Collections
Discover the best community collections!
Collections including paper arxiv:2309.06895
-
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
Paper • 2309.06380 • Published • 32 -
PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Models
Paper • 2309.05793 • Published • 50 -
DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models
Paper • 2309.06933 • Published • 12 -
MagiCapture: High-Resolution Multi-Concept Portrait Customization
Paper • 2309.06895 • Published • 27
-
OmnimatteRF: Robust Omnimatte with 3D Background Modeling
Paper • 2309.07749 • Published • 7 -
AudioSR: Versatile Audio Super-resolution at Scale
Paper • 2309.07314 • Published • 23 -
Generative Image Dynamics
Paper • 2309.07906 • Published • 52 -
MagiCapture: High-Resolution Multi-Concept Portrait Customization
Paper • 2309.06895 • Published • 27
-
MVDream: Multi-view Diffusion for 3D Generation
Paper • 2308.16512 • Published • 100 -
Learning Disentangled Avatars with Hybrid 3D Representations
Paper • 2309.06441 • Published • 4 -
Dynamic Mesh-Aware Radiance Fields
Paper • 2309.04581 • Published • 6 -
Towards Practical Capture of High-Fidelity Relightable Avatars
Paper • 2309.04247 • Published • 9