-
FreeNoise: Tuning-Free Longer Video Diffusion Via Noise Rescheduling
Paper • 2310.15169 • Published • 10 -
FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models
Paper • 2406.16863 • Published • 11 -
CineScale: Free Lunch in High-Resolution Cinematic Visual Generation
Paper • 2508.15774 • Published • 20
Haonan Qiu
MoonQiu
AI & ML interests
None yet
Recent Activity
upvoted a paper about 10 hours ago
Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation upvoted a paper 28 days ago
VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward authored a paper about 2 months ago
DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement LearningOrganizations
-
FreeNoise: Tuning-Free Longer Video Diffusion Via Noise Rescheduling
Paper • 2310.15169 • Published • 10 -
FreeTraj: Tuning-Free Trajectory Control in Video Diffusion Models
Paper • 2406.16863 • Published • 11 -
CineScale: Free Lunch in High-Resolution Cinematic Visual Generation
Paper • 2508.15774 • Published • 20
models 0
None public yet
datasets 0
None public yet